Documentation Reference · 06

MCP Server, CLI & API Reference

Connect any MCP-compatible agent — or use the CLI directly from your terminal. One platform, two interfaces, 60+ tools across every domain in the workspace.

快速開始

託管 MCP 透過 Streamable HTTP 運行 OAuth。直接由 Siftable URL 開始就得,唔使複製同貼上權杖。

1. 新增託管 MCP URL

新增 https://siftable.io/api/v1/mcp 作為遠端 MCP 伺服器或連接器。請唔好使用已停用嘅 /sse 端點。

2. 完成 OAuth

喺你嘅用戶端選擇 Connect、Authenticate 或 Login,並喺 Siftable 同意畫面批准存取。請唔好喺呢個設定度加入 Authorization 標頭。

claude_code_config.json
{
  "mcpServers": {
    "siftable": {
      "type": "http",
      "url": "https://siftable.io/api/v1/mcp"
    }
  }
}

3. 驗證連接

先呼叫 context_current,然後列出專案或任務。當你需要執行其他操作時,請使用 find_capability。

Example agent interaction
# Agent calls:
project_list()
task_list(status: "in_progress")
calendar_list_events(startDate: "2026-02-17", endDate: "2026-02-23")

# Agent now has your full operational context.

CLI Installation

Siftable CLI 為你提供完整嘅終端機指令介面以及互動式 copilot。佢使用同託管 MCP 相同嘅記錄,並配備 CLI 專用嘅身份驗證同埋本地功能。二進制檔案會安裝為 sift(以及 siftableexf 嘅兼容別名)。

1. Install

Terminal
npm install  -g @siftable/cli     # npm
bun  install -g @siftable/cli     # bun
pnpm add     -g @siftable/cli     # pnpm

# or run without installing
npx @siftable/cli <command>

2. Authenticate

The CLI uses device flow authentication — it opens your browser, you approve, and a token is stored locally.

Terminal
$ sift auth login

  Your verification code: ZFMV-SBGJ

  Opening browser...
  If the browser didn't open, visit: https://siftable.io/app/device?code=ZFMV-SBGJ

  Waiting for authorization...
  Logged in successfully!

3. Run your first command

Terminal
$ sift projects list

 NAME                STATUS    TASKS
 Siftable            active    12
 Marketing Site      active    4
 Mobile App          planning  0

$ sift projects context <id>

# Full project context: tasks, signals, notes, members.

Every CLI command supports --json for machine-readable output. Pipe it into jq, feed it to scripts, or let agents parse it directly.

認證

託管 MCP 請使用 OAuth,互動式 CLI 會話請使用裝置流程,而非互動式自動化或本地 MCP 用戶端則請使用 PAT。

裝置流程 (CLI)

執行 sift auth login。CLI 會打開你嘅瀏覽器,你用 Google 登入並批准裝置代碼。PAT 會自動生成並儲存喺 ~/.config/siftable/ 入面。唔使複製貼上任何權杖。

PAT(自動化及本地 MCP)

對於非互動式自動化或本地 MCP 用戶端,請喺 Settings → Integrations → Developer / AI Clients 建立權杖,並喺 Authorization 標頭傳遞。靜態權杖不支援使用 OAuth 權限提升功能。

HTTP Header
Authorization: Bearer sift_pat_your_token_here

Token 嘅權限範圍僅限於特定領域(例如只限任務、只限日曆、完全存取等)。對於 CI 管道,請將 SIFT_TOKEN 設為環境變數。

Auth Commands
$ sift auth login
$ sift auth status
$ sift auth logout

Token 權限範圍同可用嘅寫入操作取決於你嘅工作區設定同埋計劃。請前往「設定」→「整合」→「開發者 / AI 客戶端」同埋「定價」查看你帳戶目前嘅限制。

MCP 連接

Siftable 託管 MCP 配合 OAuth 使用 Streamable HTTP。端點為:

MCP Endpoint
https://siftable.io/api/v1/mcp

將呢個 URL 用於支援 OAuth 嘅遠端客戶端,包括 ChatGPT、Codex、Cursor、Claude、Grok,以及兼容嘅 MCP SDK 實作。託管 MCP 設定指南中包含特定客戶端嘅步驟。

任務

Task Domain 6 tools
MCP ToolCLIAccessDescription
task_list sift tasks list READ List tasks with filters: status (inbox, next_action, in_progress, waiting_for, completed, archived), phase, project, limit.
task_get sift tasks get READ Get a single task with full details: description, due date, priority, project, linked code.
task_create sift tasks create WRITE Create a task. Accepts title, description, priority (do_now, schedule, delegate, someday), project, due date.
task_update sift tasks update WRITE Update task fields: title, description, status, priority, due date, project assignment.
task_complete sift tasks complete WRITE Mark a task as completed.
task_delete sift tasks delete DELETE Permanently delete a task.
CLI Examples
$ sift tasks list --status in_progress

 TITLE                     STATUS        PRIORITY   DUE
 Ship CLI docs             in_progress   do_now     2026-02-27
 Fix device flow auth      in_progress   do_now     -

$ sift tasks create --title "Review PR #312" --priority do_now --json
{"id":"abc-123","title":"Review PR #312","status":"inbox","priority":"do_now"}

日曆

Calendar Domain 4 tools
MCP ToolCLIAccessDescription
calendar_list_events sift calendar list READ List events in a date range. Returns title, start/end times, location, description. Supports limit.
calendar_create_event sift calendar create WRITE Create a calendar event. Requires title, startTime, endTime (ISO 8601). Optional: description, location.
calendar_update_event sift calendar update WRITE Update an existing event's title, times, description, or location.
calendar_delete_event sift calendar delete DELETE Remove an event from the calendar.
CLI Examples
$ sift calendar list --start 2026-02-24 --end 2026-02-28

 TITLE                  START              END                LOCATION
 Team standup           Feb 25 09:00       Feb 25 09:30       Zoom
 Product review         Feb 26 14:00       Feb 26 15:00       Conf Room B

$ sift calendar create --title "Ship CLI v0.3" \
    --start 2026-02-27T10:00:00Z --end 2026-02-27T10:30:00Z

項目

Project Domain 5 tools
MCP ToolCLIAccessDescription
project_list sift projects list READ List projects. Filter by status (planning, active, on_hold, blocked, completed). Include archived.
project_get_context sift projects context READ Full project context: tasks, notes, members, signals. The richest single call for understanding a project.
project_create sift projects create WRITE Create a project with name, summary, status, and emoji.
project_update sift projects update WRITE Update project name, summary, status, or emoji.
project_archive sift projects archive WRITE Archive a completed or inactive project.

知識庫

Knowledge Domain 6 tools
MCP ToolCLIAccessDescription
note_search sift notes search READ Semantic + full-text search across notes. Filter by project.
note_list sift notes list READ List notes. Filter by type (note, concept, meeting, reference, daily, dataset) and project.
note_get sift notes get READ Get full note content by ID.
note_create sift notes create WRITE Create a note with title, markdown content, type, and optional project.
note_update sift notes update WRITE Update note title, content, or type.
note_delete sift notes delete DELETE Delete a note.

Datasets

Dataset Domain 19 commands

Structured datasets support grounded summaries, grouped analysis, ranking, bucketing, time-series work, import/export, schema changes, and record mutations from the same CLI and MCP-backed platform.

CapabilityCLIAccessDescription
Browse and inspect sift datasets list, get, query, summarize READ List datasets, inspect schema, query records, and get row-count and sample summaries.
Grounded analysis sift datasets analyze, aggregate, compare READ Generate natural-language insights, grouped metrics, and side-by-side segment comparisons.
Ranking and bucketing sift datasets rank, bucket READ Sort or score records, then bucket numeric or date fields into ranges with metrics per bucket.
Time series and plots sift datasets timeseries, plot READ Compute lag, pct-change, rolling windows, drawdown, or normalize plotting payloads from derived results.
Import and export sift datasets import, export WRITE Bring CSVs in, append to existing datasets, or export filtered results back to CSV.
Create and materialize sift datasets create, materialize WRITE Create datasets directly or turn a derived result into a new scratch dataset.
Schema and records sift datasets schema, add, update-record, delete-record WRITE Modify field definitions, add rows, update rows, and delete rows with explicit commands.
Derived workflows sift datasets join, compute READ Join dataset slices and compute derived fields before materializing or plotting the result.
CLI Examples
$ sift datasets list
$ sift datasets summarize <dataset-id>
$ sift datasets analyze <dataset-id> --focus-fields BMI,Outcome
$ sift datasets aggregate <dataset-id> --group-by Outcome \
    --metrics '[{"operation":"count","as":"rows"},{"operation":"avg","field":"BMI","as":"avg_bmi"}]'
$ sift datasets compare <dataset-id> --segment-field Outcome \
    --metrics '[{"operation":"avg","field":"Glucose","as":"avg_glucose"}]'
$ sift datasets rank <dataset-id> --sorts '[{"field":"BMI","direction":"desc"}]' --limit 10
$ sift datasets bucket <dataset-id> --field Age --bucket-count 5 \
    --metrics '[{"operation":"count","as":"rows"}]'

人脈

People Domain 5 tools
MCP ToolCLIAccessDescription
people_search sift people search READ Search contacts by name. Returns relationship type, company, contact info, interaction history.
sift people list READ List all contacts. CLI-only convenience wrapper.
person_create sift people create WRITE Create a contact with name, relationship, company, and contact details.
person_update sift people update WRITE Update a contact's details, relationship, or company.
person_delete sift people delete DELETE Delete a contact.

代碼記憶

Code Memory Domain 4 tools

儲存同提取關於你代碼庫嘅精選事實。用 Git、rg 或者你嘅編輯器喺本機檢查源碼;Siftable 唔會寄存源碼索引或源碼搜尋。

MCP ToolCLIAccessDescription
code_memory_store sift code memory store WRITE Store a fact. Categories: architecture, integration, convention, entrypoint, gotcha, ownership. Optional: file path, repository.
code_memory_search sift code memory search READ Semantic search over stored code facts. Filter by category or repository.
code_memory_list sift code memory list READ List all stored code memories. Filter by repository.
code_memory_delete sift code memory delete DELETE Delete a stored code memory by ID.

文檔

Document Domain 1 command
MCP ToolCLIAccessDescription
upload_document sift documents upload WRITE Upload a PDF, Markdown, or text file into Knowledge. Set by file path or inline content. Auto-detects type.

Vault

Vault Domain 5 tools

Encrypted secret storage. Store API keys, credentials, OAuth tokens, SSH keys, and sensitive notes. Values are encrypted at rest and audit-logged on read.

MCP ToolCLIAccessDescription
vault_create sift vault create WRITE Store a new encrypted secret. Types: env_var, credential, oauth_token, ssh_key, certificate, note.
vault_list sift vault list READ List vault entries (metadata only — never decrypted values). Filter by type or category.
vault_search sift vault search READ Search vault entries by name, slug, or description. Returns metadata only.
vault_update sift vault update WRITE Update vault entry metadata: name, tags, category, description.
CLI Examples
$ sift vault create --name "Stripe API Key" --json
# Interactive prompt for sensitive payload values

$ sift vault list

 NAME                TYPE         CATEGORY     CREATED
 Stripe API Key      env_var      payments     2026-02-25
 GitHub PAT          credential   devtools     2026-02-20

$ sift vault materialize run --help
# Approved plaintext goes only to the exact local destination.

$ sift env pull --help
# Pull an approved .sift/environment.yaml bundle.

Workflows

Cross-domain recipes that combine multiple tools. These patterns work identically via MCP or CLI.

Link Code to Tasks

Connect implementation work to the task that motivated it. Agents and teammates can trace why code changed.

MCP
task_create(title: "Implement device flow auth", priority: "do_now")
# ... implement the feature ...
task_link_code(taskId: "abc-123", repositoryId: "repo-456",
  commitSha: "5cf5f22", filePath: "src/services/deviceAuthService.ts",
  notes: "Fixed verification_uri to use /app/device")
task_complete(taskId: "abc-123")
CLI
$ sift tasks create --title "Implement device flow auth" --priority do_now
$ sift code link abc-123 --repo repo-456 \
    --commit 5cf5f22 --file src/services/deviceAuthService.ts
$ sift tasks complete abc-123

Project Onboarding

New to a project? Pull the full context in three commands.

CLI
# 1. Get the big picture
$ sift projects context <id>

# 2. See what's in flight
$ sift tasks list --project <id> --status in_progress

# 3. Check code conventions
$ sift code memory search "architecture and conventions"

End-of-Day Review

Summarize what happened today. Works great as an agent prompt or a manual check.

MCP (agent prompt)
# Agent calls:
calendar_list_events(startDate: "2026-02-26", endDate: "2026-02-26")
task_list(status: "completed", limit: 20)
task_list(status: "in_progress")

# Agent now has: today's meetings, completed tasks, and remaining work.
# It can draft a standup summary, update project status, or flag blockers.
CLI
$ sift calendar list --start 2026-02-26 --end 2026-02-26
$ sift tasks list --status completed --limit 20 --json | jq '.tasks[] | .title'
$ sift tasks list --status in_progress

Store a Debug Discovery

Found a gotcha? Store it so your future self (or your agent) doesn't rediscover it the hard way.

CLI
$ sift code memory store \
    --fact "Device flow verification_uri must use /app/device (SPA path), not /device (marketing homepage)" \
    --category gotcha \
    --file src/services/deviceAuthService.ts

冪等性

寫入操作(task_create、note_create、calendar_create_event 等)接受可選嘅 idempotencyKey 參數。如果你用相同嘅鍵重試請求,Siftable 返回原始結果而唔係建立重複。

Idempotent task creation
task_create(
  title: "Review PR #247",
  priority: "do_now",
  idempotencyKey: "agent-run-42-task-pr247"
)

# Safe to retry. Same key = same result.

權限

Token 按範疇限定。一個只限日曆嘅 token 讀唔到任務或人脈。將你嘅 token 限定到你嘅 agent 需要嘅最低存取權限。

可用嘅範圍:

  • tasks:read / tasks:write — Task listing, CRUD, and completion
  • calendar:read / calendar:write — Event listing and creation
  • projects:read / projects:write — Project management and context
  • knowledge:read / knowledge:write — Notes, search, document upload
  • people:read / people:write — Contact search and CRM updates
  • work:read / work:write — Agent work queue items
  • org:read — Workspace org metadata
  • mcp:* — All MCP operations (recommended for IDE and agent use)

可用嘅寫入操作取決於你嘅 token 權限範圍同目前嘅工作區計劃。喺正式環境依賴寫入操作之前,請先檢查你發出嘅 token 同目前嘅定價頁面。

CLI 指令參考

All 169 commands from @siftable/cli@0.5.29, generated from the oclif manifest so this page cannot drift from sift --help. Every command also accepts the global flags (--json, --token, --api-url, --workspace, --no-input).

所有指令都支援呢啲全域 flag:--json (原始 JSON 輸出)、--token / SIFT_TOKEN--api-url / SIFT_API_URL (預設係 https://siftable.io)、--workspace / SIFT_WORKSPACE_ID,同埋 --no-input (停用提示)。具破壞性嘅指令需要加上 --confirm 或者 -y

一般

頂層指令同診斷。

5 個指令
Shellsift
sift capabilities

顯示 Siftable CLI 嘅功能同埋就緒狀態

Shellsift
sift commands

顯示啱 Agent 用嘅指令主題同埋工作流入口

Shellsift
sift doctor

診斷本地 Siftable CLI 設定,唔會顯示敏感資料

Shellsift
sift interactive

啟動 Siftable 終端機副駕駛 (sift interactive) —— 一個喺進程入面幫你處理任務、工作、日曆、項目同人脈嘅 AI 助手。

Flags
--connected-models — List eligible connected models and exit
--connection <value> needs model — Select a Model Connection UUID for a gateway invocation
--max-output-tokens <value> needs prompt — Maximum connected-model output tokens (1-32768)
--model <value> — Select an eligible connected model for a gateway invocation
--prompt <value> needs model — Invoke the selected connected model once and exit
--stream needs prompt — Consume selected connected-model output incrementally
Shellsift
sift mermaid

喺終端機渲染 Mermaid 圖表(流程圖、時序圖、狀態圖、類別圖、ER、C4、架構圖、心智圖)。支援讀取 .mmd 檔案或 stdin。

Arguments
file — Path to a .mmd file (omit to read stdin)
Flags
--ascii — Use ASCII glyphs instead of Unicode box drawing
--color <none|truecolor> default: "truecolor" — Color mode
--height <value> — Fit into an exact N-row pane (pads/clips)
--max-height <value> — Bound the diagram to N rows (no padding)
--max-width <value> — Bound the diagram to N columns (no padding)
--overflow <allow|clip|error> default: "clip" — What to do when the diagram exceeds the bounds
--unicode — Use Unicode box drawing (default)
--width <value> — Fit into an exact N-column pane (pads/clips)

Agents

Agent 別名。

6 個指令
Shellsift
sift agents create

建立 Agent 別名

Flags
--alias <value> required — Stable alias slug, e.g. codex
--capabilities <value> — Capabilities JSON object
--hidden — Hide from normal user-visible lists
--name <value> — Display name
--operator <value> — Linked daemon/operator ID
--permissions <value> — Default permissions JSON object
--type <value> default: "custom" — Agent type
Shellsift
sift agents disable

停用 Agent 別名

Arguments
alias required — Agent alias or ID
Shellsift
sift agents get

獲取 Agent 別名

Arguments
alias required — Agent alias or ID
Shellsift
sift agents list

列出 Agent 別名

Flags
--include-disabled — Include disabled aliases
Shellsift
sift agents update

更新 Agent 別名

Arguments
alias required — Agent alias or ID
Flags
--capabilities <value> — Capabilities JSON object
--hidden — Hide from normal user-visible lists
--name <value> — Display name
--operator <value> — Linked daemon/operator ID
--permissions <value> — Default permissions JSON object
--status <active|disabled> — Alias status
--type <value> — Agent type
--visible — Show in normal user-visible lists
Shellsift
sift agents work

列出分配畀 Agent 別名嘅工作

Arguments
alias required — Agent alias or ID
Flags
--limit <value> — Maximum results
--status <value> — Work item status

Ai

5 commands
Shellsift
sift ai connect

Show the secure browser flow for adding a non-exportable Model Connection

Flags
--url <value> default: "https://siftable.io/settings/model-connections" — Siftable Model Connections settings URL
Shellsift
sift ai invoke

Invoke an eligible connected model (requires ai:invoke and ai:connections:use)

Flags
--connection <value> required — Model Connection UUID returned by sift ai list
--max-output-tokens <value> — Maximum output tokens (1-32768)
--model <value> required — Eligible model ID returned by sift ai list
--prompt <value> required — Prompt text
--stream — Consume and print incremental connected-model output
Shellsift
sift ai list

List eligible connected models (requires ai:models:read)

Shellsift
sift ai status

Show non-secret Model Connection status (requires ai:connections:use)

Arguments
connection — Optional Model Connection UUID
Shellsift
sift ai usage

Show connected-model usage totals (requires ai:usage:read)

Flags
--from <value> — ISO-8601 period start
--to <value> — ISO-8601 period end

Approvals

2 commands
Shellsift
sift approvals request

Request a governed action approval; this command cannot approve or consume it

Flags
--action <value> required — Governed action identifier
--destination <value> default: "{}" — Destination binding JSON object
--expires-in <value> — Approval lifetime in seconds (30-600)
--operation <value> required — Operation identifier
--purpose <value> required — Human-readable non-secret purpose
--resource-id <value> required — Resource identifier
--resource-type <value> required — Resource type identifier
Shellsift
sift approvals status

Inspect a governed approval requested by this CLI identity

Arguments
id required — Approval ID

認證

認證指令。

3 個指令
Shellsift
sift auth login

喺 Siftable 進行認證

Flags
--scope <ai:models:read|ai:invoke|ai:usage:read|ai:connections:use|vault:metadata:read|vault:manage|vault:audit:read> repeatable — Incremental AI invocation or Vault scope to request (repeatable; management AI scopes and plaintext reveal are unavailable)
Shellsift
sift auth logout

移除已儲存嘅認證

Shellsift
sift auth status

顯示認證狀態

Billing

4 commands
Shellsift
sift billing fallback decide

Allow, deny, or always allow personal funding for a quoted workspace operation

Flags
--decision <allow|deny|always_allow> required
--monthly-cap-micros <value> — Monthly micro-USD cap for always_allow
--quote <value> required — Server-issued operation quote ID
Shellsift
sift billing fallback policy

Read or update the workspace personal-fallback policy

Flags
--disabled — Disable and revoke personal fallback
--enabled — Enable personal fallback
Shellsift
sift billing fallback revoke

Revoke one of your active personal-fallback consents

Arguments
consentId required
Shellsift
sift billing fallback status

Show your active personal-fallback decisions for a workspace

日曆

日曆活動。

4 個指令
Shellsift
sift calendar create

建立日曆活動

Flags
--description <value> — Event description
--end <value> required — End time (ISO 8601)
--location <value> — Event location
--start <value> required — Start time (ISO 8601)
--title <value> required — Event title
Shellsift
sift calendar delete

刪除日曆活動

Arguments
id required — Event ID
Flags
-y, --yes — Skip confirmation
Shellsift
sift calendar list

列出日曆活動

Flags
--end <value> — End date (ISO 8601)
--limit <value> — Maximum number of results
--start <value> — Start date (ISO 8601)
Shellsift
sift calendar update

更新日曆活動

Arguments
id required — Event ID
Flags
--description <value> — Event description
--end <value> — End time (ISO 8601)
--location <value> — Event location
--start <value> — Start time (ISO 8601)
--title <value> — Event title

Capabilities

5 commands
Shellsift
sift capabilities create

Create a reviewed server-brokered Vault capability

Flags
--adapter <value> required — Reviewed static adapter ID
--expires-in <value> — Lifetime in seconds (300-2592000)
--field <value> default: "value" — Credential payload field
--operation <value> required — Comma-separated allowlisted operations
--provider <value> required — Provider ID
--purpose <value> required — Non-secret human-readable purpose
--vault-entry <value> required — Vault entry UUID
Shellsift
sift capabilities describe

Describe safe metadata for one Vault capability

Arguments
id required — Capability metadata ID
Shellsift
sift capabilities execute

Execute one typed operation through a Vault capability handle

Flags
--approval <value> — Governed approval UUID when required
--handle <value> required — Opaque vcap_ capability handle
--idempotency-key <value> — Stable 8-128 character key for safe retries
--input <value> default: "{}" — Typed operation input JSON object
--operation <value> required — Allowlisted operation
Shellsift
sift capabilities list

List safe metadata for Vault capability handles

Shellsift
sift capabilities revoke

Revoke a Vault capability

Arguments
id required — Capability metadata ID

代碼

代碼工具。

13 個指令
Shellsift
sift code blame

查看檔案嘅 Git blame

Arguments
file required — Relative file path
Flags
--root <value> default: "." — Repository root path
Shellsift
sift code memory confirm

確認一個代碼記憶候選,並提供可審計嘅理由

Arguments
id required — Memory ID
Flags
--reason <value> required — Audit reason
Shellsift
sift code memory delete

刪除已儲存嘅代碼庫資訊

Arguments
id required — Memory ID
Flags
-y, --yes — Skip confirmation
Shellsift
sift code memory detect-stale

偵測可能過時嘅代碼記憶,並將佢哋標示為 needs_review (絕不刪除)

Flags
--limit <value> — Maximum memories to scan
--repo <value> — Repository ID
Shellsift
sift code memory edit

直接編輯代碼記憶;舊內容會保留喺審計紀錄度

Arguments
id required — Memory ID
Flags
--confidence <value> — Confidence 0-1
--fact <value> required — Updated fact
--reason <value> required — Audit reason
Shellsift
sift code memory events

列出某個代碼記憶嘅所有只可附加嘅管理同沿革事件

Arguments
id required — Memory ID
Flags
--limit <value> — Maximum number of events
Shellsift
sift code memory get

顯示單一代碼記憶,包括其來源、證據同生命周期

Arguments
id required — Memory ID
Shellsift
sift code memory list

列出已儲存嘅代碼庫資訊

Flags
--include-inactive — Include rejected and superseded lineage memories
--lifecycle <unreviewed|confirmed|rejected|superseded|needs_review> — Filter by lifecycle state
--limit <value> — Maximum number of results
--repo <value> — Repository ID
Shellsift
sift code memory needs-review

因應潛在嘅過時或矛盾,將代碼記憶標示為 needs_review (絕不刪除)

Arguments
id required — Memory ID
Flags
--reason <value> required — Audit reason
--signal <value> repeatable — Staleness signal (repeatable)
Shellsift
sift code memory reject

拒絕一個代碼記憶,並提供可審計嘅理由 (屬軟性拒絕;絕不刪除)

Arguments
id required — Memory ID
Flags
--reason <value> required — Audit reason
Shellsift
sift code memory search

搜尋已儲存嘅代碼庫資料

Arguments
query required — Search query
Flags
--category <architecture|integration|convention|entrypoint|gotcha|ownership> — Filter by category
--include-inactive — Include rejected and superseded lineage memories
--lifecycle <unreviewed|confirmed|rejected|superseded|needs_review> — Filter by lifecycle state
--limit <value> — Maximum number of results
--repo <value> — Repository ID
Shellsift
sift code memory store

儲存代碼庫資料

Flags
--agent <value> — Authoring agent (marks memory as agent-authored)
--category <architecture|integration|convention|entrypoint|gotcha|ownership> required — Fact category
--commit <value> — Source commit SHA
--confidence <value> — Confidence 0-1
--evidence-chunk <value> repeatable — Historical indexed chunk ID supporting the fact
--fact <value> required — Fact to store (1-2 sentences)
--file <value> — Related file path
--path <value> repeatable — Additional related path (repeatable)
--reason <value> — Capture reason (required with --agent)
--repo <value> — Repository ID
--work-item <value> — Related agent work item ID
Shellsift
sift code memory supersede

用新事實取代一個代碼記憶;舊記憶會作為沿革保留

Arguments
id required — Memory ID to supersede
Flags
--category <architecture|integration|convention|entrypoint|gotcha|ownership> — Fact category (defaults to previous)
--commit <value> — Source commit SHA
--confidence <value> — Confidence 0-1
--evidence-chunk <value> repeatable — Evidence chunk ID (repeatable)
--fact <value> required — Replacement fact
--file <value> — Related file path
--path <value> repeatable — Additional related path (repeatable)
--reason <value> required — Audit reason

Codex

Codex 自動化輔助工具。

1 個指令
Shellsift
sift codex daily-review collect

收集唯讀嘅 Siftable 同埋本地 git 上下文,用嚟做 Codex 每日工作回顧

Flags
--calendar-days <value> default: 7 — Calendar lookahead days
--limit <value> default: 20 — Maximum records per source
--skip-git — Skip local git summary

情境

1 個指令
Shellsift
sift context current

解釋目前嘅 principal、擁有者、項目同本機 checkout 情境

Flags
--workspace-root <value> — Absolute local checkout root to describe (never sent as a workspace tenant ID)

Crm

6 個指令
Shellsift
sift crm import apply

淨係套用現有 CRM 匯入計劃入面已批准嘅操作;重複執行安全無誤

Arguments
planId required — Durable CRM import plan UUID
Flags
--yes — Confirm canonical CRM writes without prompting
Shellsift
sift crm import approve

批准現有 CRM 匯入計劃入面所有或者揀出嚟等緊處理嘅操作

Arguments
planId required — Durable CRM import plan UUID
Flags
--operation-id <value> repeatable — Stable operation ID to approve; repeat to approve a subset
--reason <value> required — Human approval reason recorded on the plan
--yes — Confirm the approval without prompting
Shellsift
sift crm import get

用固定嘅計劃 ID,繼續同檢查一個持久嘅 CRM 匯入計劃

Arguments
planId required — Durable CRM import plan UUID
Shellsift
sift crm import plan

用 CSV、TSV、XLS 或者 XLSX 建立或重用一個持久嘅 CRM 匯入計劃,而唔使寫入正式嘅 CRM 紀錄

Arguments
file required — Local CSV, TSV, XLS, or XLSX source (8 MiB maximum)
Flags
--mapping-mode <manual|workspace_auto> default: "manual" — Manual mapping or approved workspace mapping profile
--provider <generic|salesforce> default: "generic" — Source provider mapping
Shellsift
sift crm organizations convert

解釋 CRM 組織同工作空間之間嘅受規管邊界

Arguments
id required — CRM organization ID
Shellsift
sift crm organizations list

只列出 CRM 組織;協作工作空間會被排除在外

Flags
--limit <value> default: 100 — Maximum number of CRM results
--search <value> — Optional fuzzy search query

數據集

結構化數據集。

43 個指令
Shellsift
sift datasets add

新增紀錄到數據集

Arguments
id required — Dataset ID
Flags
--idempotency-key <value> required — Caller-owned stable key for replaying this exact dataset mutation
--record <value> repeatable — Record as JSON object, e.g. '{"name":"Alice","age":"30"}'
--records <value> — Multiple records as JSON array
Shellsift
sift datasets aggregate

用分組指標(數量、平均值、總和、最小值、最大值、中位數、標準差、百分位數、比例)嚟聚合數據集紀錄

Arguments
id required — Dataset ID
Flags
--filters <value> — JSON array of filters
--group-by <value> — Comma-separated field names to group by
--having <value> — JSON array of having clauses [{metric, operator, value}]
--limit <value> default: 100 — Max rows
--metrics <value> — JSON array of metrics [{operation, field, as}]
--sorts <value> — JSON array of sorts
Shellsift
sift datasets analyze

為數據集生成有根據嘅自然語言分析

Arguments
id required — Dataset ID
Flags
--filters <value> — JSON array of filters
--focus-fields <value> — Comma-separated field names to focus analysis on
--max-insights <value> default: 5 — Max insights to generate
--mode <descriptive|operational> — Analysis mode
--signal-limit <value> — Max decision signals to return
Shellsift
sift datasets apply-diff

套用儲存咗嘅數據集 diff 計劃

Arguments
plan required — Path to a local diff plan or persisted diff plan ID
Flags
--yes — Confirm applying the saved diff plan without prompting
Shellsift
sift datasets archive

封存數據集,但唔會刪除佢嘅實體表

Arguments
id required — Dataset ID
Flags
-y, --yes — Confirm dataset archival without prompting
Shellsift
sift datasets bucket

將數字或日期欄位分做唔同範圍,並計算每個範圍嘅聚合指標

Arguments
id required — Dataset ID
Flags
--boundaries <value> — Comma-separated boundary values (omit for auto-bucketing)
--bucket-count <value> — Number of auto-buckets (default: 5)
--field <value> required — Field to bucket
--filters <value> — JSON array of filters
--metrics <value> — JSON array of metrics
Shellsift
sift datasets cleanup

針對有生命週期標籤嘅臨時數據集,計劃或執行清理

Flags
--dry-run — Return a deterministic cleanup plan without deleting datasets
--lifecycle <value> — Lifecycle kind to clean, e.g. scratch, benchmark, research-run
--limit <value> default: 100 — Maximum lifecycle datasets to inspect
--now <value> — Deterministic timestamp for tests and scheduled cleanup
--older-than <value> — Only include datasets older than this duration, e.g. 12h, 7d
--orphaned — Include stale dataset notes that no longer have a backing dataset row
--tag <value> — Lifecycle tag to clean, e.g. benchmark
-y, --yes — Confirm deletion when applying cleanup with --no-dry-run
Shellsift
sift datasets compare

並排比較分類欄位入面唔同部分嘅指標

Arguments
id required — Dataset ID
Flags
--filters <value> — JSON array of filters
--limit <value> default: 10 — Max segment values to compare
--metrics <value> — JSON array of metrics
--segment-field <value> required — Categorical field to segment by
--segment-values <value> — Comma-separated segment values (auto-discovers if omitted)
Shellsift
sift datasets compute

根據數據集或者之前嘅衍生結果,計算出衍生欄位

Arguments
id — Dataset ID
Flags
--computed-fields <value> required — JSON array of computed fields, e.g. '[{"as":"spread","expression":"right.Close-left.Close"}]'
--filters <value> — JSON array of filters
--limit <value> default: 50 — Maximum rows
--order-by <value> — JSON array of order clauses
--select <value> — Comma-separated fields to include
--sorts <value> — JSON array of output sorts
--source-result <value> — Inline JSON for a prior derived result
--source-result-file <value> — Path to a JSON file containing a prior derived result
Shellsift
sift datasets contract

顯示 agent 睇得明嘅數據集 schema 同功能合約

Arguments
id required — Dataset ID
Flags
--resolve <value> — Comma-separated semantic field references to resolve
--template <value> — Validate contract against a built-in template
Shellsift
sift datasets create

建立數據集

Flags
--description <value> — Dataset description
--fields <value> — Field definitions as JSON array, e.g. '[{"name":"age","type":"number"}]'
--idempotency-key <value> required — Caller-owned stable key for replaying this exact dataset mutation
--lifecycle <value> — Lifecycle kind for generated datasets, e.g. scratch, benchmark, research-run
--metadata <value> — Dataset metadata as JSON object
--note-id <value> — Link to an existing note
--run-id <value> — Lifecycle run identifier
--scratch — Shortcut for --lifecycle scratch --tags scratch
--tags <value> — Comma-separated lifecycle tags
--title <value> required — Dataset title
--ttl <value> — Lifecycle TTL duration, e.g. 12h, 7d, 30d
Shellsift
sift datasets dedupe

喺唔改動數據嘅情況下,透過 key 搵出重複嘅資料集紀錄

Arguments
id required — Dataset ID
Flags
--key <value> required — Field name used to group duplicates
--limit <value> default: 500 — Maximum records to scan in one bounded pass
Shellsift
sift datasets delete

永久刪除資料集同埋佢嘅實體表

Arguments
id required — Dataset ID
Flags
-y, --yes — Confirm dataset deletion without prompting
Shellsift
sift datasets delete-record

喺資料集刪除一條紀錄

Arguments
id required — Dataset ID
record-id required — Record ID
Flags
--idempotency-key <value> required — Caller-owned stable key for replaying this exact dataset mutation
-y, --yes — Skip confirmation
Shellsift
sift datasets diff

預覽 CSV、JSON 或 JSONL 檔案嘅資料集行數變更

Arguments
id required — Dataset ID
Flags
--batch-size <value> default: 100 — Records per backend batch
--from-file <value> required — Path to CSV, JSON, or JSONL rows to compare
--persist — Persist the diff plan in Siftable for later review/apply
--save-plan <value> — Write an applyable diff plan JSON file
--template <sources|people|events|claims|evidence_sources|evidence_source_fragments|evidence_claims|evidence_people|evidence_organizations|evidence_places|evidence_artifacts|evidence_events|evidence_relationships|evidence_contradictions> — Built-in template name
--upsert-by <value> — Field name used to match existing rows
Shellsift
sift datasets diff-plans list

列出已儲存嘅資料集差異計劃

Flags
--dataset-id <value> — Filter by dataset ID
--limit <value> default: 50 — Maximum plans to return
--status <draft|validated|applied|rejected|expired> — Filter by plan status
Shellsift
sift datasets diff-plans show

顯示已儲存嘅資料集差異計劃

Arguments
id required — Diff plan ID
Shellsift
sift datasets export

將特定範圍嘅資料集紀錄匯出成 CSV、JSON、JSONL 或 Markdown

Arguments
id required — Dataset ID
Flags
--filters <value> — JSON array of filters
--format <csv|json|jsonl|markdown> default: "csv" — Export format
--limit <value> default: 500 — Max rows to export
-o, --output <value> — Output file path (writes to stdout if omitted)
--sorts <value> — JSON array of sorts
Shellsift
sift datasets facets

顯示資料集欄位嘅特定範圍分面摘要

Arguments
id required — Dataset ID
Flags
--fields <value> — Comma-separated field names to facet
--limit <value> default: 20 — Maximum values per facet
Shellsift
sift datasets formula-plan

計算公式欄位,並預覽可供審核嘅資料集更新

Arguments
id required — Dataset ID
Flags
--computed-fields <value> required — JSON array of computed fields, e.g. '[{"as":"score","expression":"confidence * reliability"}]'
--filters <value> — JSON array of filters for compute source
--limit <value> default: 100 — Maximum rows to compute and plan
--order-by <value> — JSON array of order clauses
--save-plan <value> — Write an applyable diff plan JSON file
--select <value> — Comma-separated fields to include in compute source
--sorts <value> — JSON array of output sorts
--target-fields <value> — Comma-separated computed field names to write; defaults to every computed field alias
--template <sources|people|events|claims> — Built-in template name for validation
--upsert-by <value> required — Field used to match rows for update
Shellsift
sift datasets get

獲取資料集詳情同埋 schema

Arguments
id required — Dataset ID
Shellsift
sift datasets impact

解釋數據集公式、圖表、視圖、品質同埋實體化嘅影響

Arguments
id required — Dataset ID
Flags
--from-plan <value> — Persisted diff plan ID to inspect
--operation <value> — Committed dataset operation ID to inspect
Shellsift
sift datasets import

將 CSV、JSON 或者 JSONL 嘅資料行匯入去新或者現有嘅數據集

Arguments
file required — Path to CSV, JSON, or JSONL file
Flags
--batch-size <value> default: 100 — Records per backend batch
--dataset-id <value> — Import into existing dataset instead of creating a new one
--description <value> — Dataset description
--dry-run — Validate and plan the import without writing
--lifecycle <value> — Lifecycle kind for generated datasets, e.g. scratch, benchmark, research-run
--metadata <value> — Dataset metadata as JSON object when creating a new dataset
--run-id <value> — Lifecycle run identifier
--scratch — Shortcut for --lifecycle scratch --tags scratch
--tags <value> — Comma-separated lifecycle tags
--template <sources|people|events|claims|evidence_sources|evidence_source_fragments|evidence_claims|evidence_people|evidence_organizations|evidence_places|evidence_artifacts|evidence_events|evidence_relationships|evidence_contradictions> — Built-in template name
--title <value> — Dataset title (defaults to filename)
--ttl <value> — Lifecycle TTL duration, e.g. 12h, 7d, 30d
--upsert-by <value> — Field name used to update matching rows instead of creating duplicates
--yes — Confirm mutating imports without prompting
Shellsift
sift datasets inspect-file

檢查本地 CSV、TSV、XLS 或者 XLSX 檔案嘅結構,而唔使建立或者修改數據集

Arguments
file required — Path to a local CSV, TSV, XLS, or XLSX file
Flags
--delimiter <value> — Single-byte delimiter override for CSV/TSV
--format <csv|tsv|xls|xlsx> — Format override when the extension is absent or wrong
--header-row <value> — Zero-based header row index within the sheet grid
--max-bytes <value> — Refuse files larger than this many bytes
--max-cols <value> — Maximum columns returned per sheet
--max-rows <value> — Maximum data rows returned per sheet
--max-sheets <value> — Maximum sheets returned
--sheet <value> — Inspect only this sheet; the full sheet inventory is still reported
Shellsift
sift datasets join

用 left.Close 同 right.Close 呢類別名範圍欄位,將數據集連接返自己

Arguments
id required — Dataset ID
Flags
--join-keys <value> required — JSON array of join keys, e.g. '[{"leftField":"Date","rightField":"Date"}]'
--join-type <inner|left|right> default: "inner" — Join type
--left-alias <value> default: "left" — Left alias
--left-filters <value> — JSON array of left-side filters
--limit <value> default: 50 — Maximum joined rows
--right-alias <value> default: "right" — Right alias
--right-filters <value> — JSON array of right-side filters
--select <value> — Comma-separated alias-scoped fields to return
--sorts <value> — JSON array of sorts
Shellsift
sift datasets list

列出數據集

Flags
--limit <value> default: 50 — Maximum number of results
Shellsift
sift datasets lookup

透過精確鍵值配對嚟查找數據集紀錄

Arguments
id required — Dataset ID
Flags
--key <value> required — Field name to match
--limit <value> default: 25 — Maximum matching records
--value <value> required — Exact value to match
Shellsift
sift datasets materialize

將衍生結果實體化做一個新嘅臨時數據集

Flags
--description <value> — Dataset description
--idempotency-key <value> required — Caller-owned stable key for replaying this exact dataset mutation
--source-result <value> — Inline JSON for a derived result
--source-result-file <value> — Path to a JSON file containing a derived result
--title <value> required — Title of the new dataset
Shellsift
sift datasets pivot

根據分組數據集指標建立樞紐分析式摘要

Arguments
id required — Dataset ID
Flags
--cols <value> required — Column field
--filters <value> — JSON array of filters
--limit <value> default: 500 — Maximum grouped cells to request
--metrics <value> — JSON metrics array; defaults to count
--rows <value> required — Row field
Shellsift
sift datasets plot

驗證同埋標準化嚟自衍生結果嘅輕量化圖表數據

Flags
--chart-type <line|bar|scatter> required — Chart type
--series-field <value> — Optional series field
--source-result <value> — Inline JSON for a derived result
--source-result-file <value> — Path to a JSON file containing a derived result
--x-field <value> required — X-axis field
--y-fields <value> required — Comma-separated Y-axis fields
Shellsift
sift datasets profile

顯示數據集嘅受限分析資訊

Arguments
id required — Dataset ID
Flags
--sample-limit <value> default: 10 — Number of sample rows to include
Shellsift
sift datasets quality

用結構化嘅缺失值指標同重複值記錄,去檢查數據集嘅質素

Arguments
id required — Dataset ID
Flags
--fields <value> — Comma-separated field names to check
--repeat-threshold <value> default: 3 — Minimum occurrences for a repeated value to be reported
Shellsift
sift datasets query

查詢數據集入面嘅紀錄

Arguments
id required — Dataset ID
Flags
--cursor <value> — Pagination cursor from previous query
--filters <value> — Filter conditions as JSON array, e.g. '[{"field":"status","value":"active"}]'
--include-deleted — Include soft-deleted records
--limit <value> default: 25 — Maximum number of records
--sorts <value> — Sort spec as JSON array, e.g. '[{"field":"name","direction":"asc"}]'
Shellsift
sift datasets rank

根據排序或者加權數字公式幫數據集紀錄排名

Arguments
id required — Dataset ID
Flags
--filters <value> — JSON array of filters
--formula <value> — JSON formula object {weights: [{field, weight}]}
--limit <value> default: 25 — Max rows
--sorts <value> — JSON array of sorts
Shellsift
sift datasets reconcile

根據 key 比較兩個數據集,唔會改動任何一邊

Arguments
left required — Left dataset ID
right required — Right dataset ID
Flags
--left-key <value> required — Left dataset key field
--limit <value> default: 500 — Maximum rows to scan from each dataset
--right-key <value> — Right dataset key field; defaults to --left-key
Shellsift
sift datasets schema

修改數據集 schema(新增、更新或者刪除欄位)

Arguments
id required — Dataset ID
Flags
--field <value> — Field definition as JSON, e.g. '{"name":"email","type":"text"}'
--field-id <value> — Field ID (required for update/delete)
--idempotency-key <value> required — Caller-owned stable key for replaying this exact dataset mutation
--operation <add_field|update_field|delete_field> required — Schema operation
Shellsift
sift datasets search

喺指定嘅文字欄位入面搜尋數據集紀錄

Arguments
id required — Dataset ID
query required — Search text
Flags
--fields <value> — Comma-separated fields to search; defaults to profile columns
--filters <value> — JSON array of base filters applied to every field search
--limit <value> default: 25 — Maximum merged records
--per-field-limit <value> default: 25 — Maximum records to request per searched field
Shellsift
sift datasets summarize

攞數據集摘要(行數、欄位、樣本行)

Arguments
id required — Dataset ID
Shellsift
sift datasets templates list

列出內置數據集範本

Shellsift
sift datasets templates show

顯示內置數據集範本嘅 schema

Arguments
template required — Template name
Shellsift
sift datasets timeseries

用 lag、pct_change、rolling windows、drawdown、volatility 同 correlation 嚟分析數據集時間序列

Arguments
id required — Dataset ID
Flags
--date-field <value> required — Date field name
--filters <value> — JSON array of filters
--limit <value> default: 100 — Maximum output rows
--metrics <value> — JSON array of metric definitions
--order-direction <asc|desc> default: "asc" — Time ordering
--pivot — Emit explicit pivoted output
--segment-field <value> — Optional segment field
--segment-values <value> — Comma-separated segment values
--transforms <value> — JSON array of transform definitions
Shellsift
sift datasets update-record

更新數據集入面嘅紀錄

Arguments
id required — Dataset ID
record-id required — Record ID
Flags
--fields <value> required — Field updates as JSON object, e.g. '{"status":"done"}'
--idempotency-key <value> required — Caller-owned stable key for replaying this exact dataset mutation
Shellsift
sift datasets validate

用內置範本嚟驗證數據集

Arguments
id required — Dataset ID
Flags
--template <sources|people|events|claims|evidence_sources|evidence_source_fragments|evidence_claims|evidence_people|evidence_organizations|evidence_places|evidence_artifacts|evidence_events|evidence_relationships|evidence_contradictions> required — Built-in template name

文件

上傳文件。

1 個指令
Shellsift
sift documents upload

將文件(PDF、Markdown 或者純文字)上傳做筆記

Arguments
file required — Path to file
Flags
--project <value> — Project ID
--title <value> — Note title (defaults to filename)
--type <note|concept|meeting|reference|daily|dataset> — Note type

環境

宣告式環境合約同埋受管治嘅 Vault 套件實體化。

11 個指令
Shellsift
sift env check

為本機或 CI 使用驗證環境合約

Flags
--checkout-root <value> — Exact Git checkout root containing .sift/environment.yaml
--ci — Fail non-zero when contract, example, Git, or checkout safety findings exist
Shellsift
sift env diff

顯示環境合約嘅變動,但不包括實際值

Flags
--checkout-root <value> — Exact Git checkout root containing .sift/environment.yaml
Shellsift
sift env endpoint enroll

登記一個公開端點身份,而唔授予 Vault 存取權限

Flags
--dedicated — Endpoint is a dedicated runner
--endpoint-class <interactive_desktop|remote_vm|noninteractive_runner|shared_host|ci_runner|production_host|multi_tenant> required — Explicit endpoint policy class
--kill-switch — Runner has an enforced kill switch
--owner <value> default: "personal" — personal or workspace:<uuid>
--storage-tier <hardware_host_bound|systemd_managed|convenience_keyring|none> required — Actual endpoint key storage tier; convenience_keyring is not hardware-backed
Shellsift
sift env example

產生一個確定性、只包含名稱同佔位符嘅範例

Flags
--checkout-root <value> — Exact Git checkout root containing .sift/environment.yaml
--write — Write the deterministic output to .env.example instead of displaying it
Shellsift
sift env import apply

原子化咁套用一個經過審核嘅 dotenv 匯入計劃

Flags
--checkout-root <value> — Checkout used only to reject Sift-managed source files
--owner <value> — Exact Vault owner: personal or workspace:<tenant-id>
--plan-file <value> required — Reviewed value-free plan artifact
--source <value> required — Same explicit dotenv source used to create the plan
Shellsift
sift env import plan

為一個指明嘅 dotenv 來源,建立一個冇值、限定擁有者範圍嘅計劃

Flags
--checkout-root <value> — Checkout used only to reject Sift-managed source files
--decision <value> repeatable — Explicit per-index decision: INDEX:keep-existing|overwrite|skip|rename=NAME
--owner <value> — Exact Vault owner: personal or workspace:<tenant-id>
--plan-file <value> required — New local value-free plan artifact to create
--project <value> — Exact owner-scoped project UUID
--source <value> required — Explicit dotenv source file
Shellsift
sift env pull

將一個受管治嘅 Vault 套件,拉入一個由 Sift 管理嘅開發環境檔案

Flags
--approval-timeout <value> default: 600
--checkout-root <value> — Checkout containing .sift/environment.yaml
--destination <value> — Exact relative destination when the manifest declares more than one bundle
--endpoint-class <development|production|ci|shared_host|policy_ineligible> required — Explicit endpoint policy class; managed pulls accept development only
--owner <value> — Exact Vault owner: personal or workspace:<tenant-id>
--purpose <value> required
--replace — Replace a changed Sift-managed file using its exact observed precondition
Shellsift
sift env push apply

原子化咁套用一個經過審核嘅 dotenv 匯出計劃

Flags
--checkout-root <value> — Checkout used only to reject Sift-managed source files
--owner <value> — Exact Vault owner: personal or workspace:<tenant-id>
--plan-file <value> required — Reviewed value-free plan artifact
--source <value> required — Same explicit dotenv source used to create the plan
Shellsift
sift env push plan

為一個指明嘅 dotenv 來源,建立一個冇值、限定擁有者範圍嘅匯出計劃

Flags
--checkout-root <value> — Checkout used only to reject Sift-managed source files
--decision <value> repeatable — Explicit per-index decision: INDEX:keep-existing|overwrite|skip|rename=NAME
--owner <value> — Exact Vault owner: personal or workspace:<tenant-id>
--plan-file <value> required — New local value-free plan artifact to create
--project <value> — Exact owner-scoped project UUID
--source <value> required — Explicit dotenv source file
Shellsift
sift env rm

移除一個由 Sift 管理嘅本地環境檔案

Flags
--checkout-root <value> — Exact Git checkout root containing .sift/environment.yaml
--destination <value> — Exact relative destination when the manifest declares more than one bundle
--yes required — Confirm removal of the exact recognized managed file
Shellsift
sift env status

報告冇值嘅本地環境狀態

Flags
--checkout-root <value> — Exact Git checkout root containing .sift/environment.yaml

事件

由時間線事實支持嘅研究事件。

3 個指令
Shellsift
sift events attach-person

將參與者加落去現有嘅研究事件入面

Arguments
event required — Existing temporal fact ID
person required — Person UUID to attach
Flags
--role <value> default: "subject" — Participant role
--yes — Confirm participant attachment without prompting
Shellsift
sift events create

建立一個有參與者嘅研究事件時間線事實

Flags
--body <value> — Event notes/body
--confidence <low|medium|high> — Confidence level
--entity <value> repeatable — Participant/entity as type:uuid or type:uuid:role; repeatable
--org <value> repeatable — Organization UUID participant; repeatable
--person <value> repeatable — Person UUID participant; repeatable
--precision <millisecond|minute|hour|day|month|year|decade|century|millennium|mega_year|era> default: "year" — Temporal precision
--source <value> repeatable — Source entity as type:uuid or type:uuid:role; repeatable
--source-label <value> — Source/provenance label
--source-note <value> — Source/provenance note
--source-url <value> — Source/provenance URL
--timestamp <value> — ISO timestamp
--title <value> required — Event title
--visibility <org_public|private|restricted> — Timeline visibility
--year <value> — Historical year CE
--year-end <value> — Historical end year CE
Shellsift
sift events list

列出研究事件時間線嘅事實資料

Flags
--cursor <value> — Pagination cursor
--end <value> — End boundary
--entity <value> — Filter by entity ref type:uuid
--limit <value> default: 50 — Maximum events
--order <asc|desc> default: "asc" — Sort order
--person <value> — Filter by person UUID
--q <value> — Text search query
--start <value> — Start boundary

證據

Evidence Graph 設定同埋證明工作流編排。

11 個指令
Shellsift
sift evidence diff apply

套用已審核嘅 Evidence Graph 差異計劃

Arguments
id required — Persisted diff plan ID
Flags
--yes — Confirm applying the reviewed diff plan without prompting
Shellsift
sift evidence diff impact

解釋已儲存差異計劃對 Evidence Graph 嘅影響

Arguments
id required — Persisted diff plan ID, or local when using --from-file
Flags
--from-file <value> — Local diff plan JSON file to explain without API access
Shellsift
sift evidence diff list

列出已儲存嘅 Evidence Graph 差異計劃

Flags
--dataset-id <value> — Filter by evidence dataset ID
--limit <value> default: 50 — Maximum plans to return
--project <value> — Filter locally by Evidence Graph project ID when present on plans
--status <draft|validated|applied|rejected|expired> — Filter by plan status
Shellsift
sift evidence diff show

顯示 Evidence Graph 差異計劃同埋具備領域知識嘅摘要

Arguments
id required — Persisted diff plan ID
Shellsift
sift evidence extract

建立唔使套用嘅 Agent 工作,用嚟提取 Evidence Graph 候選資料

Flags
--agent <value> default: "researcher" — Assigned agent alias
--context <value> — Additional input context JSON object
--context-file <value> — Additional input context JSON file
--dry-run — Preview work item payload without writing
--no-apply — Keep extraction in proposed/diff-first mode
--pack <company-origin|family-history|investigation|compliance-evidence|account-history|codebase-history> default: "company-origin" — Evidence workflow pack
--project <value> — Project ID
--source-dataset <value> required — Evidence sources dataset ID
--targets <value> — Comma-separated extraction targets
--yes — Confirm work item creation without prompting
Shellsift
sift evidence init

建立 Evidence Graph 項目同埋以數據集為基礎嘅工作表

Arguments
name required — Evidence Graph project name
Flags
--dry-run — Preview project/dataset creation without writing
--pack <company-origin|family-history|investigation|compliance-evidence|account-history|codebase-history> default: "company-origin" — Evidence workflow pack
--yes — Confirm creation without prompting
Shellsift
sift evidence plan

喺寫入受信任狀態之前,先計劃 Evidence Graph 工作流

Arguments
goal required — Evidence Graph goal
Flags
--pack <company-origin|family-history|investigation|compliance-evidence|account-history|codebase-history> default: "company-origin" — Evidence workflow pack
--project <value> — Existing project ID
--source-dataset <value> — Existing evidence sources dataset ID
Shellsift
sift evidence project

試行 Evidence Graph 時間線同埋關係投影

Flags
--dry-run — Preview projection without writing
--from-file <value> — Local diff plan JSON file to project from without API access
--from-plan <value> — Persisted diff plan ID to project from
--pack <company-origin|family-history|investigation|compliance-evidence|account-history|codebase-history> default: "company-origin" — Evidence workflow pack
--project <value> — Evidence Graph project ID
Shellsift
sift evidence proof report

由數據集支援嘅證據包生成 Evidence Graph 證明報告

Flags
--format <json|markdown> default: "markdown" — Report format
--from-file <value> required — Evidence packet JSON file to report on
--project <value> — Evidence Graph project ID for report metadata
Shellsift
sift evidence sources import

將 Evidence Graph 來源分類帳嘅資料行匯入數據集支援嘅來源表

Arguments
file required — Path to CSV, JSON, or JSONL source ledger rows
Flags
--batch-size <value> default: 100 — Records per backend batch
--dataset-id <value> — Evidence sources dataset ID
--dry-run — Validate and plan source import without writing
--upsert-by <value> default: "source_id" — Field name used to update matching source rows
--yes — Confirm mutating imports without prompting
Shellsift
sift evidence verify

驗證 Evidence Graph 嘅出處、評論、投影同埋引用不變量

Flags
--from-file <value> required — Evidence packet JSON file to verify
--project <value> — Evidence Graph project ID for report metadata

Grants

4 commands
Shellsift
sift grants adapters

List reviewed local execution adapters and honest containment tiers

Shellsift
sift grants request

Request a human-approved grant for a pre-registered trusted local runner

Flags
--adapter <value> required
--audience <value> required
--credential-field <value> required
--cwd <value>
--executable <value> required — Resolved reviewed executable path
--executable-digest <value> required
--issuer <value> required
--operation <value> required
--purpose <value> required
--runner-fingerprint <value> required
--runner-public-key <value> required — PEM public-key file from the trusted local runner
--scope <value> required — Provider scope JSON with string values
--vault-entry <value> required
Shellsift
sift grants run

Request approval, redeem in memory, and run exactly one reviewed child process

Flags
--adapter <github_gh|github_publish_pr|terraform_apply> required
--approval-timeout <value> default: 600
--audience <value> required
--body-file <value> — PR body file for github_publish_pr
--credential-field <value> required
--cwd <value>
--issuer <value> required
--operation <value> required
--purpose <value> required
--scope <value> required
--vault-entry <value> required
Shellsift
sift grants status

Inspect safe status for an ephemeral local execution grant

Arguments
id required

圖譜

實體圖搜尋同鄰近節點。

5 個指令
Shellsift
sift graph between

解釋兩個實體之間嘅有界圖路徑

Arguments
source required — Source entity reference as type:uuid
target required — Target entity reference as type:uuid
Flags
--depth <value> default: 4 — Maximum path depth, backend clamps to 1-5
--frontier-limit <value> default: 500 — Maximum links to inspect per path expansion, backend clamps to 1-1000
Shellsift
sift graph explain

解釋兩個實體之間嘅有界圖路徑

Arguments
source required — Source entity reference as type:uuid
target required — Target entity reference as type:uuid
Flags
--depth <value> default: 4 — Maximum path depth, backend clamps to 1-5
--frontier-limit <value> default: 500 — Maximum links to inspect per path expansion, backend clamps to 1-1000
Shellsift
sift graph neighbors

顯示某個實體喺圖入面嘅鄰近節點

Arguments
entity required — Entity reference as type:uuid
Flags
--depth <value> default: 1 — Graph depth, backend clamps to 1-3
--limit <value> default: 80 — Maximum graph items, backend clamps to 1-200
Shellsift
sift graph preview

預覽單個圖譜實體

Arguments
entity required — Entity reference as type:uuid
Shellsift
sift graph search

搜尋可用嚟連結嘅圖譜實體

Arguments
query required — Search query
Flags
--limit <value> default: 20 — Maximum results
--types <value> — Comma-separated entity types

筆記

知識庫筆記。

7 個指令
Shellsift
sift notes bulk-delete

預覽或者批量刪除筆記

Flags
--archived — Filter by archived state
--confirm — Execute deletion instead of preview
--ids <value> — Comma-separated note IDs
--title-contains <value> — Title substring filter
--title-equals <value> — Exact title filter
--title-starts-with <value> — Title prefix filter
--type <note|concept|meeting|reference|daily|dataset>
Shellsift
sift notes create

建立筆記

Flags
--content <value> — Note content (markdown)
--metadata <value> — Note metadata as JSON
--metadata-file <value> — Read note metadata JSON from a file
--project <value> — Project ID
--title <value> required — Note title
--type <note|concept|meeting|reference|daily|dataset> — Note type
Shellsift
sift notes delete

刪除筆記

Arguments
id required — Note ID
Flags
-y, --yes — Skip confirmation
Shellsift
sift notes get

獲取筆記完整內容

Arguments
id required — Note ID
Shellsift
sift notes list

列出筆記

Flags
--archived — Filter by archived state
--limit <value> — Maximum number of results
--project <value> — Filter by project ID
--title-contains <value> — Title substring filter
--title-equals <value> — Exact title filter
--title-starts-with <value> — Title prefix filter
--type <note|concept|meeting|reference|daily|dataset> — Filter by note type
Shellsift
sift notes search

搜尋筆記

Arguments
query required — Search query
Flags
--limit <value> — Maximum number of results
--project <value> — Filter by project ID
Shellsift
sift notes update

更新筆記

Arguments
id required — Note ID
Flags
--content <value> — Note content (markdown)
--metadata <value> — Replace note metadata with this JSON object
--metadata-file <value> — Read replacement note metadata JSON from a file
--title <value> — Note title
--type <note|concept|meeting|reference|daily|dataset> — Note type

組織

組織同埋公司。

5 個指令
Shellsift
sift organizations bulk-delete

預覽或批量刪除組織

Flags
--confirm — Execute deletion instead of preview
--contains <value> — Name substring filter
--equals <value> — Exact name filter
--ids <value> — Comma-separated organization IDs
--relationship <value> — Filter by relationship status
--starts-with <value> — Name prefix filter
--type <value> — Filter by organization type
Shellsift
sift organizations create

建立組織

Flags
--domain <value> — Domain (e.g. acme.com)
--industry <value> — Industry
--linkedin-url <value> — LinkedIn page URL
--location <value> — Location
--name <value> required — Organization name
--notes <value> — Notes
--relationship-status <value> — Relationship status (e.g. prospect, customer, partner, vendor)
--type <value> — Organization type (e.g. company, nonprofit, government, school)
--website <value> — Website URL
Shellsift
sift organizations delete

刪除組織

Arguments
id required — Organization ID
Flags
-y, --yes — Skip confirmation
Shellsift
sift organizations search

搜尋組織

Arguments
query — Optional fuzzy search query
Flags
--contains <value> — Name substring filter
--equals <value> — Exact name filter
--limit <value> — Maximum number of results
--relationship <value> — Filter by relationship status
--starts-with <value> — Name prefix filter
--type <value> — Filter by organization type
Shellsift
sift organizations update

更新組織

Arguments
id required — Organization ID
Flags
--domain <value> — Domain (e.g. acme.com)
--industry <value> — Industry
--linkedin-url <value> — LinkedIn page URL
--location <value> — Location
--name <value> — Organization name
--notes <value> — Notes
--relationship-status <value> — Relationship status
--type <value> — Organization type
--website <value> — Website URL

人脈

人物同聯絡人。

15 個指令
Shellsift
sift people bulk-delete

預覽或者批量刪除聯絡人

Flags
--confirm — Execute deletion instead of preview
--contains <value> — Name substring filter
--equals <value> — Exact name filter
--has-no-email — Only contacts without an email
--ids <value> — Comma-separated person IDs
--relationship <value> — Filter by relationshipToUser
--starts-with <value> — Name prefix filter
Shellsift
sift people context add

新增一個關乎擁有者嘅個人或工作關係

Arguments
personId required — Person ID
Flags
--basis <value> — Why this relationship is recorded
--confidence <value> — Evidence confidence from 0 to 1
--context <personal|work> required — Relationship context
--primary — Make this the primary relationship in its context
--relationship <value> required — Relationship type, e.g. friend, client, mentor
Shellsift
sift people context list

列出現時擁有者點樣認識一個人

Arguments
personId required — Person ID
Shellsift
sift people context remove

移除一個關乎擁有者嘅關係脈絡

Arguments
personId required — Person ID
relationshipId required — Context relationship ID
Flags
--dry-run — Show what would be removed without writing
-y, --yes — Remove without prompting
Shellsift
sift people create

建立聯絡人

Flags
--birth-year <value> — Birth year
--birthday <value> — Birthday (YYYY-MM-DD)
--company <value> — Company name (auto-links to organization if exists)
--context <personal|work> repeatable — How you know this person; repeat for both contexts
--email <value> — Email address
--estimated-age <value> — Estimated age
--job-title <value> — Job title
--linkedin-url <value> — LinkedIn profile URL
--location <value> — Location
--mbti <value> — MBTI type (e.g. INTJ, ENFP)
--name <value> required — Full name
--notes <value> — Notes about this person
--phone <value> — Phone number
--relationship <value> — Relationship to user (e.g. friend, colleague, client, mentor)
--website <value> — Personal website
Shellsift
sift people delete

刪除聯絡人

Arguments
id required — Person ID
Flags
-y, --yes — Skip confirmation
Shellsift
sift people enrich

用可重放安全嘅方式執行,研究關於一個人嘅公開資料

Arguments
id required — Person ID
Flags
--dataset <value> — Optional dataset ID for a reviewable reconciliation plan
--dataset-upsert-by <value> — Preferred dataset identity field
--idempotency-key <value> required — Stable 8-128 character key for exact retries
--mode <standard|ultra> default: "standard" — Research depth
Shellsift
sift people get

獲取個人檔案,包括特徵同關係

Arguments
id required — Person ID
Shellsift
sift people graph

顯示以人為中心嘅關係圖

Arguments
id required — Person ID
Flags
--depth <value> default: 2 — Relationship graph depth
--include-inactive — Include inactive relationship edges
Shellsift
sift people kinship

解釋兩個人之間嘅親屬關係或者關係距離

Arguments
egoPersonId required — Ego/source person ID
targetPersonId required — Target person ID
Flags
--max-depth <value> default: 6 — Maximum relationship depth
Shellsift
sift people list

列出聯絡人

Flags
--category <family|romantic|professional|social> — Relationship category
--contains <value> — Name substring filter
--context <all|personal|work> default: "all" — Relationship context
--equals <value> — Exact name filter
--has-no-email — Only contacts without an email
--limit <value> — Maximum number of results
--relationship <value> — Filter by relationshipToUser
--starts-with <value> — Name prefix filter
Shellsift
sift people relate

建立或者更新兩個人之間嘅關係

Arguments
personAId required — First person ID
personBId required — Second person ID
Flags
--dry-run — Preview the relationship payload without writing
--notes <value> — Relationship notes
--type <value> required — Relationship type, e.g. colleague, sibling, spouse, collaborator
-y, --yes — Apply without prompting
Shellsift
sift people search

搜尋聯絡人

Arguments
query required — Search query
Flags
--contains <value> — Name substring filter
--equals <value> — Exact name filter
--has-no-email — Only contacts without an email
--limit <value> — Maximum number of results
--relationship <value> — Filter by relationshipToUser
--starts-with <value> — Name prefix filter
Shellsift
sift people timeline

列出同某人有關嘅時間線紀錄

Arguments
id required — Person ID
Flags
--limit <value> default: 50 — Maximum facts to return
--order <asc|desc> default: "asc" — Sort order
--role <value> — Filter by entity role, comma-separated
Shellsift
sift people update

更新聯絡人

Arguments
id required — Person ID
Flags
--birth-year <value> — Birth year
--birthday <value> — Birthday (YYYY-MM-DD)
--company <value> — Company name
--email <value> — Email address
--estimated-age <value> — Estimated age
--job-title <value> — Job title
--linkedin-url <value> — LinkedIn profile URL
--location <value> — Location
--mbti <value> — MBTI type (e.g. INTJ, ENFP)
--name <value> — Full name
--notes <value> — Notes about this person
--phone <value> — Phone number
--relationship <value> — Relationship to user
--website <value> — Personal website

項目

項目管理。

7 個指令
Shellsift
sift projects archive

封存項目

Arguments
id required — Project ID
Flags
-y, --yes — Skip confirmation
Shellsift
sift projects context

獲取項目背景資訊(任務、筆記、訊號)

Arguments
id required — Project ID
Shellsift
sift projects create

建立項目

Flags
--emoji <value> — Single emoji
--name <value> required — Project name
--status <planning|active|on_hold|blocked|completed> — Project status
--summary <value> — Project summary
Shellsift
sift projects list

列出項目

Flags
--include-archived — Include archived projects
--status <planning|active|on_hold|blocked|completed> — Filter by status
Shellsift
sift projects planning

獲取項目嘅標準 CSN 計劃快照

Arguments
id required — Project ID
Shellsift
sift projects planning-recompute

重新計算項目嘅標準 CSN 計劃快照

Arguments
id required — Project ID
Shellsift
sift projects update

更新項目

Arguments
id required — Project ID
Flags
--emoji <value> — Single emoji
--name <value> — Project name
--status <planning|active|on_hold|blocked|completed> — Project status
--summary <value> — Project summary

食譜

內置嘅研究工作流食譜。

2 個指令
Shellsift
sift recipes list

列出內置嘅研究工作流食譜

Shellsift
sift recipes show

顯示內置嘅研究工作流食譜

Arguments
id required — Recipe ID

Relationships

79 commands
Shellsift
sift relationships actions dry-run

Preview a relationship action on the server without committing it

Arguments
id required — Relationship action ID
entity — Relationship entity as opportunity:<uuid> or prospect:<uuid>
Flags
--entity <value> — Target as prospect:uuid or opportunity:uuid
--idempotency-key <value> required — Stable 8-128 character key for reproducible server-side previews
--input <value> — Action input JSON object
--input-file <value> — Path to action input JSON
Shellsift
sift relationships actions list

List registered relationship actions and their commitment policies

Flags
--approval-policy <value> — Filter by approval policy
--commitment <value> — Filter by commitment class
--limit <value> — Maximum results
Shellsift
sift relationships actions run

Run any canonical relationship action with replay-safe caller identity

Arguments
id required — Canonical action ID from relationships actions list
entity — Relationship entity as opportunity:<uuid> or prospect:<uuid>
Flags
--entity <value> — Target as prospect:uuid or opportunity:uuid
--expected-version <value> — Current collaboration version
--idempotency-key <value> required — Stable 8-128 character key for exact retries
--input <value> — Action input JSON object
--input-file <value> — Path to an action input JSON file
--yes — Confirm action execution
Shellsift
sift relationships actions show

Show one registered relationship action

Arguments
id required — Relationship action ID
Shellsift
sift relationships brief

Compose an exact, evidence-grounded relationship brief

Arguments
subject required — Subject as prospect:uuid or opportunity:uuid
Flags
--lens <value> default: "relationship" — Relationship lens identifier
Shellsift
sift relationships composer approver-edit

建立一個具名嘅審批者修訂版本,並重新開啟指導審閱

Arguments
id required — Composer session UUID
Flags
--body <value> required
--expected-version <value> required
--reason <value> required
--subject <value> required
--yes — Confirm the attributed edit
Shellsift
sift relationships composer bind-sender

將一個明確、有效嘅已連接電郵帳戶,綁定到一份永久草稿

Arguments
id required — Composer session UUID
Flags
--expected-version <value> required — Current optimistic session version
--sender <value> required — Connected email account UUID
Shellsift
sift relationships composer confirm

確認已綁定嘅簡報,並建立第一個永久草稿修訂版本

Arguments
id required — Composer session UUID
Flags
--expected-version <value> required — Current optimistic session version
--yes — Confirm brief and create draft
Shellsift
sift relationships composer create

建立或繼續一個由關係簡報到草稿嘅永久作業階段

Arguments
subject required — Subject as prospect:uuid or opportunity:uuid
Flags
--file <value> required — JSON file with source, recommendation, brief, and ranked evidence
Shellsift
sift relationships composer dispatch

保留原有審批、即刻傳送,或排程一個受管治嘅關係訊息

Arguments
id required — Composer session UUID
Flags
--at <value> — ISO-8601 time required for send_later
--choice <approve_only|send_now|send_later> required — Dispatch outcome
--expected-version <value> required — Current optimistic session version
--idempotency-key <value> required — Stable retry key for this exact choice and time
--yes — Confirm this governed dispatch choice
Shellsift
sift relationships composer evaluate

評估現時嘅永久草稿,並附加錨定喺片語上嘅指導發現

Arguments
id required — Composer session UUID
Flags
--expected-version <value> required — Current optimistic session version
Shellsift
sift relationships composer finding-action

解釋、預覽、接受、拒絕或還原一個可歸屬嘅指導發現

Arguments
id required — Composer session UUID
finding required — Coaching finding UUID
Flags
--action <explain|preview|accept|reject|undo> required
--expected-version <value> required — Current optimistic session version
--yes — Confirm a mutating coaching decision
Shellsift
sift relationships composer history

按記錄順序,顯示只能附加嘅指導同草稿決策紀錄

Arguments
id required — Composer session UUID
Shellsift
sift relationships composer request-approval

針對特定嘅 composer 審閱請求或繼續審批;審批過程只會喺瀏覽器進行

Arguments
id required — Composer session UUID
Flags
--expected-version <value> required — Current optimistic session version
--idempotency-key <value> required — Stable approval-request retry key
--yes — Confirm the approval request
Shellsift
sift relationships composer request-changes

將一份特定嘅審閱退返俾作者,而且唔會改動訊息內容

Arguments
id required — Composer session UUID
Flags
--expected-version <value> required
--reason <value> required
--yes — Confirm the review interruption
Shellsift
sift relationships composer resolve-identity

解決或轉交一條已審閱訊息嘅內嵌「可能重複」關卡

Arguments
id required — Composer session UUID
Flags
--candidate <value> required — Candidate person UUID
--decision <same_person|different_people|route_to_owner> required
--expected-version <value> required
--yes — Confirm the identity decision
Shellsift
sift relationships composer review

將一份已完成指導嘅耐久草稿,交俾受監管嘅審閱程序

Arguments
id required — Composer session UUID
Flags
--approver-user-id <value> — Optional active internal workspace member who will approve the exact message
--expected-version <value> required — Current optimistic session version
--yes — Confirm the transition to review
Shellsift
sift relationships composer save-draft

儲存關係草稿嘅一個新耐久修訂版

Arguments
id required — Composer session UUID
Flags
--file <value> required — JSON file with expectedVersion, subject, and bodyText
Shellsift
sift relationships composer show

顯示一個耐久嘅關係 composer 會話

Arguments
id required — Composer session UUID
Shellsift
sift relationships composer update

喺建立草稿之前,更新已綁定嘅意圖同已排序嘅證據

Arguments
id required — Composer session UUID
Flags
--file <value> required — JSON file with expectedVersion, brief, and evidence
Shellsift
sift relationships contact-plan inspect

檢查一個標準嘅個人聯絡計劃,而且唔會改動佢嘅來源生命週期

Arguments
person required — Canonical person UUID
Flags
--from <value> — Inclusive ISO-8601 inspection window start
--limit <value> default: 100 — Maximum projected items
--timezone <value> — IANA display timezone
--to <value> — Inclusive ISO-8601 inspection window end
Shellsift
sift relationships diagnoses create

建立一個不可變、有證據基礎嘅關係診斷快照

Flags
--file <value> required — Diagnosis JSON file
--yes — Confirm immutable diagnosis creation
Shellsift
sift relationships diagnoses list

列出所有不可變嘅關係診斷快照

Flags
--limit <value>
--subject-id <value>
--subject-type <prospect|opportunity>
Shellsift
sift relationships email-accounts list

列出可供關係草稿同受監管傳送使用嘅寄件人帳戶

Shellsift
sift relationships generated-assets draft

根據已批准嘅外展資源建立一份私人通訊提案;呢個動作唔會傳送

Arguments
id required — Generated outreach/follow-up asset UUID
Flags
--file <value> required — Exact senderAccountId, destination, optional edits, and idempotency JSON file
--yes — Confirm proposal creation
Shellsift
sift relationships generated-assets generate

根據已批准嘅精確劇本同源資源版本,產生一份有根據嘅資源

Flags
--file <value> required — Generation request JSON file
--yes — Confirm immutable asset generation
Shellsift
sift relationships generated-assets list

列出已產生嘅關係資源,包括清單同最新嘅產物審閱

Flags
--limit <value>
--subject-id <value>
--subject-type <prospect|opportunity>
Shellsift
sift relationships generated-assets review

將一個人手審批決定附加到已產生嘅產物上

Arguments
id required — Generated asset UUID
Flags
--decision <approved|rejected|needs_changes> required
--reason <value> required
--yes — Confirm append-only review
Shellsift
sift relationships generated-assets review-history

列出一份已產生資源嘅只能附加審閱紀錄

Arguments
id required — Generated asset UUID
Shellsift
sift relationships generated-assets show

顯示一份已產生嘅資源、佢嘅精確清單,同埋最新嘅產物審批

Arguments
id required — Generated asset UUID
Shellsift
sift relationships generated-assets usage-list

列出一份已產生資源嘅只能附加使用紀錄同結果連結

Arguments
id required — Generated asset UUID
Shellsift
sift relationships generated-assets usage-record

將一個匯出、內部共享或結果連結嘅紀錄附加到一份已產生嘅資源上

Arguments
id required — Generated asset UUID
Flags
--idempotency-key <value> required — Stable 8-128 character retry key
--kind <exported|shared_internally|outcome_linked> required
--outcome <value> — Stable outcome reference; required for outcome_linked
--yes — Confirm append-only usage record
Shellsift
sift relationships handoffs list

List immutable relationship outcome receipts in the onboarding queue

Flags
--limit <value> default: 100 — Maximum receipts
Shellsift
sift relationships handoffs show

Show one immutable relationship outcome handoff receipt

Arguments
id required — Outcome handoff receipt UUID
Shellsift
sift relationships meetings brief create

用已批准嘅人脈證據編寫附有引用來源嘅會議簡報

Flags
--input <value> — Exact meeting brief input JSON
--input-file <value> — Path to exact meeting brief input JSON
Shellsift
sift relationships meetings brief show

重組精確嘅輸入,以讀取目前附有引用來源嘅會議簡報

Flags
--input <value> — Exact owner, subject, approved asset, and optional meeting JSON
--input-file <value> — Path to exact meeting brief input JSON
Shellsift
sift relationships meetings evidence capture

擷取經同意授權嘅逐字稿證據,或者明確聲明嘅手寫筆記

Flags
--idempotency-key <value> required — Caller-owned stable key for exact retries
--input <value> — Exact meeting evidence input JSON
--input-file <value> — Path to exact meeting evidence input JSON
--yes — Confirm canonical evidence capture
Shellsift
sift relationships meetings evidence show

檢視單一標準會議證據事件同佢嘅來源定位器

Arguments
id required — Relationship meeting evidence event UUID
Shellsift
sift relationships meetings proposals apply

重新檢查前提條件後,一次過完整套用一個已批准嘅會議提案

Arguments
id required — Approved meeting proposal UUID
Flags
--expected-proposal-digest <value> required — Exact reviewed proposal digest
--yes — Confirm the persistent internal relationship-state change
Shellsift
sift relationships meetings proposals create

為一個已登記嘅人脈操作建立不可變且附有證據引用嘅提案

Flags
--idempotency-key <value> required — Caller-owned stable key for exact retries
--input <value> — Exact meeting proposal input JSON
--input-file <value> — Path to exact meeting proposal input JSON
--yes — Confirm immutable proposal creation
Shellsift
sift relationships meetings proposals list

列出由會議產生嘅人脈提案同埋佢哋嘅審核生命週期

Flags
--status <pending|approved|rejected|committed|failed|stale> — Filter by lifecycle status
--subject-id <value> — Filter by subject UUID
--subject-kind <prospect|opportunity> — Filter by subject kind
Shellsift
sift relationships meetings proposals review

為一個未經修改嘅會議提案附加具署名嘅批准或拒絕

Arguments
id required — Meeting proposal UUID
Flags
--input <value> — Exact decision, reason, and expectedProposalDigest JSON
--input-file <value> — Path to exact proposal review input JSON
--yes — Confirm attributable proposal review
Shellsift
sift relationships meetings proposals show

檢視由會議產生嘅人脈提案、證據、差異同埋復原計劃

Arguments
id required — Meeting proposal UUID
Shellsift
sift relationships outcomes describe

描述運行時嘅人脈成果合約同埋安全邊界

Shellsift
sift relationships outcomes inspect

喺 Answer/C0 模式下檢視已宣告嘅人脈成果,而唔會作持久儲存

Flags
--input <value> — Exact InspectRelationshipOutcomeInput JSON
--input-file <value> — Path to exact inspection input JSON
Shellsift
sift relationships outcomes interventions

顯示快照中單一有界且可審核嘅干預批次

Arguments
snapshotId required — Relationship-outcome snapshot ID
Shellsift
sift relationships outcomes list

列出人脈成果快照,並配合有界嘅游標分頁

Flags
--cursor <value> — Opaque cursor from the previous page
--limit <value> default: 50 — Maximum snapshots to return
--projection <sales_forecast|onboarding_handoff> — Filter by projection
--scope-anchor-id <value> — Filter by declared scope anchor ID
--scope-anchor-kind <value> — Filter by declared scope anchor kind
Shellsift
sift relationships outcomes records

列出精確嘅快照記錄,並配合有界嘅游標分頁

Arguments
snapshotId required — Relationship-outcome snapshot ID
Flags
--cursor <value> — Opaque cursor from the previous page
--limit <value> default: 50 — Maximum records to return
--posture <value> — Filter by the declared record posture
--risk <value> — Filter by low, moderate, high, or unknown operational risk
Shellsift
sift relationships outcomes review

記錄一次冪等嘅快照審核,而唔會執行任何建議嘅已登記操作

Arguments
snapshotId required — Relationship-outcome snapshot ID
Flags
--dry-run — Validate authority and selected interventions without recording a review
--idempotency-key <value> required — Caller-owned stable key for this exact review
--input <value> — Exact ReviewRelationshipOutcomeSnapshotInput JSON (idempotency is injected)
--input-file <value> — Path to exact snapshot review input JSON
--yes — Confirm append-only review recording
Shellsift
sift relationships outcomes run

建立或模擬運行一個 C2 人脈成果快照,而且絕對唔會執行建議嘅操作

Flags
--dry-run — Validate and project without persisting a snapshot
--idempotency-key <value> required — Caller-owned stable key for this exact snapshot request
--input <value> — Exact CreateRelationshipOutcomeSnapshotInput JSON (idempotency is injected)
--input-file <value> — Path to exact snapshot input JSON
--yes — Confirm C2 snapshot persistence
Shellsift
sift relationships outcomes show

顯示一個不可變嘅人脈成果快照

Arguments
snapshotId required — Relationship-outcome snapshot ID
Shellsift
sift relationships playbook-recommendations create

記錄一項具實質影響嘅建議,並附帶至少三個可行嘅方案

Flags
--file <value> required — Recommendation JSON file
--yes — Confirm immutable recommendation creation
Shellsift
sift relationships playbook-recommendations list

列出已記錄嘅人脈指南建議同埋其他替代方案

Flags
--limit <value>
--subject-id <value>
--subject-type <prospect|opportunity>
Shellsift
sift relationships playbooks create

基於運行時合約嘅 JSON,建立一個不可變且未經批准嘅人脈指南版本

Flags
--file <value> required — Playbook version JSON file
--yes — Confirm immutable version creation
Shellsift
sift relationships playbooks list

列出不可變關係 playbook 嘅版本同最新嘅批核決定

Flags
--limit <value> — Maximum versions
--stable-key <value> — Filter by stable playbook key
Shellsift
sift relationships playbooks review

為 playbook 版本附加人手批核決定

Arguments
id required — Playbook version UUID
Flags
--decision <approved|rejected|needs_changes> required
--reason <value> required — Attributable review reason
--yes — Confirm append-only review
Shellsift
sift relationships playbooks show

顯示一個指定嘅不可變關係 playbook 版本同佢最新嘅批核

Arguments
id required — Playbook version UUID
Shellsift
sift relationships proposals get

Inspect one relationship action proposal and its evidence

Arguments
id required — Proposal ID
Shellsift
sift relationships proposals list

List pending and historical relationship action proposals

Flags
--enrollment <value> — Filter by enrollment ID
--limit <value> — Maximum results
--sequence <value> — Filter by sequence ID
--status <value> — Filter by proposal status
Shellsift
sift relationships proposals request-approval

Request short-lived human approval for a proposal; cannot approve or consume it

Arguments
id required — Proposal ID
Flags
--idempotency-key <value> required — Stable 8-128 character key for safe retries
--purpose <value> — Non-secret reason shown to the human approver
Shellsift
sift relationships queues list

List relationship team queues in the active workspace

Shellsift
sift relationships recommendations execute

Execute an accepted, current recommendation through the canonical action runtime

Arguments
id required — Recommendation UUID
Flags
--yes — Confirm canonical action execution
Shellsift
sift relationships recommendations list

List immutable relationship recommendation snapshots

Flags
--lens <value> — Relationship lens identifier
--limit <value> default: 50 — Maximum recommendations
--subject <value> — Filter by prospect:uuid or opportunity:uuid
Shellsift
sift relationships recommendations review

Append an ordinary review decision to a relationship recommendation

Arguments
id required — Recommendation UUID
Flags
--decision <accepted|dismissed|snoozed|needs_information> required — Review decision
--reason <value> — Review reason
--snoozed-until <value> — Offset-aware ISO date-time, required for snoozed
--yes — Confirm the append-only review
Shellsift
sift relationships recommendations show

Show a relationship recommendation with its exact citations and gates

Arguments
id required — Recommendation UUID
Shellsift
sift relationships sequences create

Create a supervised relationship sequence from a JSON definition

Flags
--definition <value> — Sequence definition JSON object
--definition-file <value> — Path to sequence definition JSON
--idempotency-key <value> required — Stable 8-128 character key for safe retries
Shellsift
sift relationships sequences dry-run

Preview a supervised sequence on the server without committing it

Arguments
id required — Sequence ID
Flags
--idempotency-key <value> required — Stable 8-128 character key for reproducible server-side previews
--input <value> — Dry-run input JSON object
--input-file <value> — Path to dry-run input JSON
Shellsift
sift relationships sequences enroll

Enroll a relationship target in a supervised sequence

Arguments
id required — Sequence ID
Flags
--idempotency-key <value> required — Stable 8-128 character key for safe retries
--input <value> — Enrollment input JSON object
--input-file <value> — Path to enrollment input JSON
Shellsift
sift relationships sequences get

Show one supervised relationship sequence

Arguments
id required — Sequence ID
Shellsift
sift relationships sequences list

List supervised relationship sequences

Flags
--limit <value> — Maximum results
--status <value> — Filter by sequence status
Shellsift
sift relationships sequences pause

Pause a supervised relationship sequence

Arguments
id required — Sequence ID
Flags
--idempotency-key <value> required — Stable 8-128 character key for safe retries
--reason <value> — Non-secret pause reason
Shellsift
sift relationships sequences resume

Resume a supervised relationship sequence

Arguments
id required — Sequence ID
Flags
--idempotency-key <value> required — Stable 8-128 character key for safe retries
Shellsift
sift relationships sequences runs

List execution evidence for a supervised relationship sequence

Arguments
id required — Sequence ID
Flags
--limit <value> — Maximum results
--status <value> — Filter by run status
Shellsift
sift relationships sequences update

Update a supervised relationship sequence from a JSON definition

Arguments
id required — Sequence ID
Flags
--definition <value> — Sequence update JSON object
--definition-file <value> — Path to sequence update JSON
--idempotency-key <value> required — Stable 8-128 character key for safe retries
Shellsift
sift relationships show

Show the current relationship collaboration snapshot

Arguments
entity required — Relationship entity as opportunity:<uuid> or prospect:<uuid>
Shellsift
sift relationships source-assets create

建立一個不可變、未批核嘅 grounded source-asset 版本

Flags
--file <value> required — Source-asset version JSON file
--yes — Confirm immutable version creation
Shellsift
sift relationships source-assets list

列出不可變嘅 grounded source-asset 版本同埋最新嘅批核決定

Flags
--limit <value> — Maximum versions
--stable-key <value> — Filter by stable source-asset key
Shellsift
sift relationships source-assets review

為 source-asset 版本附加人手批核決定

Arguments
id required — Source-asset version UUID
Flags
--decision <approved|rejected|needs_changes> required
--reason <value> required
--yes — Confirm append-only review
Shellsift
sift relationships source-assets show

顯示一個指定嘅不可變 source-asset 版本同埋佢最新嘅審閱

Arguments
id required — Source-asset version UUID

研究

研究工作流嘅計劃同編排。

4 個指令
Shellsift
sift research init

建立研究項目同埋標準數據集

Arguments
name required — Research project name
Flags
--dry-run — Preview project/dataset creation without writing
--template <historical-research> default: "historical-research" — Research template
--yes — Confirm creation without prompting
Shellsift
sift research plan

喺寫入數據之前,先計劃好確定性嘅研究工作流

Arguments
goal required — Research goal
Flags
--project <value> — Existing project ID
--source-dataset <value> — Existing sources dataset ID
Shellsift
sift research run

為研究方案建立確定性嘅 agent 工作

Arguments
recipe required — Research run recipe
Flags
--agent <value> default: "researcher" — Assigned agent alias
--context <value> — Additional input context JSON object
--context-file <value> — Additional input context JSON file
--dry-run — Preview work item payload without writing
--project <value> — Project ID
--source-dataset <value> — Source dataset ID
--yes — Confirm work item creation without prompting
Shellsift
sift research status

檢查研究項目嘅 context 同埋 CLI 準備狀況

Arguments
project — Project ID

技能

可以安裝嘅 Siftable skillpack。

2 個指令
Shellsift
sift skills install

將 Siftable skillpack 安裝到本地嘅 skills 目錄

Arguments
id required — Skillpack ID
Flags
--force — Replace an existing installed skill
--target <value> default: "skills" — Installed skills directory
-y, --yes — Confirm replacing an existing skill
Shellsift
sift skills list

列出可以安裝嘅 Siftable skillpack

任務

人類計劃任務。

11 個指令
Shellsift
sift tasks bulk-delete

預覽或者批量刪除任務

Flags
--confirm — Execute deletion instead of preview
--done — Filter by completed state
--ids <value> — Comma-separated task IDs
--phase <draft|open|in_flight|review|blocked|done|cancelled>
--title-contains <value> — Title substring filter
--title-equals <value> — Exact title filter
--title-starts-with <value> — Title prefix filter
--when <now|today|soon|later>
Shellsift
sift tasks complete

將任務標記為已完成

Arguments
id required — Task ID
Shellsift
sift tasks coupling-create

喺同一個項目入面嘅任務之間建立 CSN coupling edge

Arguments
id required — Source task ID
target required — Target task ID
Flags
--note <value> — Optional note
--strength <value> — Coupling strength (0-1)
--type <info|resource> required — Coupling type
Shellsift
sift tasks coupling-delete

喺任務度刪除 CSN coupling edge

Arguments
id required — Task ID
edgeId required — Coupling edge ID
Flags
-y, --yes — Skip confirmation
Shellsift
sift tasks coupling-list

列出任務嘅 CSN 耦合邊緣

Arguments
id required — Task ID
Shellsift
sift tasks create

建立人類計劃任務

Flags
--acceptance-criteria <value> — Acceptance criteria (semicolon-separated text, e.g. "tests pass; docs updated")
--description <value> — Task description
--due <value> — Due date (ISO 8601)
--effort <trivial|small|medium|large|epic|unknown> — Effort estimate
--phase <draft|open|in_flight|review|blocked|done|cancelled> — Lifecycle phase
--priority <do_now|schedule|delegate|someday> — Priority level
--project <value> — Project ID
--scope <value> — Scope boundaries (JSON object with include/exclude arrays)
--title <value> required — Task title
Shellsift
sift tasks delete

刪除任務

Arguments
id required — Task ID
Flags
-y, --yes — Skip confirmation
Shellsift
sift tasks get

獲取人類計劃任務詳情

Arguments
id required — Task ID
Shellsift
sift tasks list

列出人類計劃任務

Flags
--cursor <value> — Continuation cursor from a previous page
--effort <trivial|small|medium|large|epic|unknown> — Filter by effort
--limit <value> default: 25 — Maximum number of results
--phase <draft|open|in_flight|review|blocked|done|cancelled> — Filter by phase
--project <value> — Filter by project ID
--status <inbox|next_action|in_progress|waiting_for|completed|archived> — Filter by status
--title-contains <value> — Title substring filter
--title-equals <value> — Exact title filter
--title-starts-with <value> — Title prefix filter
Shellsift
sift tasks planning-update

更新任務嘅 CSN 計劃欄位

Arguments
id required — Task ID
Flags
--cynefin-confidence <value> — Cynefin confidence (0-1)
--cynefin-domain <clear|complicated|complex|chaotic|aporetic> — Cynefin domain
--cynefin-rationale <value> — Why this domain fits
--cynefin-source <user|assistant|classifier> — Source of the planning classification
--duration-model <value> — Duration model JSON, e.g. {"kind":"point","days":2}
--reversibility <value> — Reversibility score (0-1)
Shellsift
sift tasks update

更新人類計劃任務

Arguments
id required — Task ID
Flags
--acceptance-criteria <value> — Acceptance criteria (semicolon-separated text, e.g. "tests pass; docs updated")
--blocked-reason <value> — Reason task is blocked
--description <value> — Task description
--due <value> — Due date (ISO 8601)
--effort <trivial|small|medium|large|epic|unknown> — Effort estimate
--phase <draft|open|in_flight|review|blocked|done|cancelled> — Lifecycle phase
--priority <do_now|schedule|delegate|someday> — Priority level
--project <value> — Project ID
--scope <value> — Scope boundaries (JSON object with include/exclude arrays)
--status <inbox|next_action|in_progress|waiting_for|completed|archived> — Task status
--title <value> — Task title

時間線

時間線事實同敘述。

4 個指令
Shellsift
sift timeline create

建立用戶編寫嘅時間線事實

Flags
--body <value> — Fact body or notes
--confidence <low|medium|high> — Confidence level
--entity <value> repeatable — Participant/entity as type:uuid or type:uuid:role; repeatable
--fact-type <value> default: "event" — Fact type
--precision <millisecond|minute|hour|day|month|year|decade|century|millennium|mega_year|era> default: "year" — Temporal precision
--source-label <value> — Source/provenance label
--source-note <value> — Source/provenance note
--source-url <value> — Source/provenance URL
--timestamp <value> — ISO timestamp
--title <value> required — Fact title
--visibility <org_public|private|restricted> — Timeline visibility
--year <value> — Historical year CE
--year-end <value> — Historical end year CE
Shellsift
sift timeline delete

撤回時間線事實

Arguments
id required — Timeline fact ID
Flags
--yes — Confirm retraction without prompting
Shellsift
sift timeline list

用範圍過濾器列出時間線事實

Flags
--cursor <value> — Pagination cursor
--end <value> — End boundary, ISO timestamp or supported historical boundary
--entity <value> — Entity filter as type:uuid
--entity-role <value> — Comma-separated entity roles
--fact-types <value> — Comma-separated fact types
--limit <value> default: 50 — Maximum items to return
--order <asc|desc> default: "asc" — Sort order
--q <value> — Text search query
--source-types <value> — Comma-separated source types
--start <value> — Start boundary, ISO timestamp or supported historical boundary
Shellsift
sift timeline narrative

為時間線事實生成敘述摘要或者解釋

Flags
--action <summarize|changed_since|led_to|what_next|cross_object> default: "summarize" — Narrative action
--entity <value> — Entity scope as type:uuid
--entity-roles <value> — Comma-separated entity roles
--fact-type <value> — Fact type filter
--limit <value> default: 60 — Maximum timeline facts to include
--participant <value> — Participant filter as type:uuid
--prompt <value> — Question or custom narrative prompt
--q <value> — Text query filter
--related-entity <value> — Related entity as type:uuid
--source-type <value> — Source type filter

保險庫

秘密保險庫。

15 個指令
Shellsift
sift vault audit

List Vault audit events (requires vault:audit:read)

Flags
--limit <value> — Maximum number of results
--owner <value> — Exact Vault owner: personal or workspace:<tenant-id>
Shellsift
sift vault create

儲存新嘅加密秘密

Flags
--category <value> — Category
--description <value> — Description
--name <value> required — Secret name
--owner <value> — Exact Vault owner: personal or workspace:<tenant-id>
--payload <value> required — JSON payload to encrypt
--slug <value> — Machine-friendly identifier
--tags <value> — Comma-separated tags
--type <env_var|credential|oauth_token|ssh_key|certificate|note> — Entry type
--url <value> — Associated URL
Shellsift
sift vault leases clean

清理一個本地 lease artifact,並標示返佢係已確認、失敗,定係不可知嘅狀態。

Arguments
id required
Flags
--checkout-root <value> — Git checkout used to prove runtime separation
--owner <value> — Exact Vault owner: personal or workspace:<tenant-id>
Shellsift
sift vault leases list

列出不含數值嘅環境 lease 同清理 metadata

Flags
--owner <value> — Exact Vault owner: personal or workspace:<tenant-id>
Shellsift
sift vault leases revoke

撤銷 lease 未來嘅使用權,移除存在嘅本地 artifact,並證明已清理。

Arguments
id required
Flags
--checkout-root <value> — Git checkout used to prove runtime separation
--owner <value> — Exact Vault owner: personal or workspace:<tenant-id>
Shellsift
sift vault leases status

檢查一個不含數值嘅環境 lease 嘅生命週期

Arguments
id required
Flags
--owner <value> — Exact Vault owner: personal or workspace:<tenant-id>
Shellsift
sift vault list

列出保險庫紀錄(只限 metadata)

Flags
--category <value> — Filter by category
--limit <value> — Maximum number of results
--owner <value> — Exact Vault owner: personal or workspace:<tenant-id>
--type <env_var|credential|oauth_token|ssh_key|certificate|note> — Filter by entry type
Shellsift
sift vault materialize environment

將一個指定嘅、受管嘅 Vault bundle 拉取到由 Sift 管理嘅開發環境檔案入面

Flags
--approval-timeout <value> default: 600
--checkout-root <value> — Checkout containing .sift/environment.yaml
--destination <value> — Exact relative destination when the manifest declares more than one bundle
--endpoint-class <development|production|ci|shared_host|policy_ineligible> required — Explicit endpoint policy class; managed pulls accept development only
--owner <value> — Exact Vault owner: personal or workspace:<tenant-id>
--purpose <value> required
--replace — Replace a changed Sift-managed file using its exact observed precondition
Shellsift
sift vault materialize request

Request human approval for one destination-bound Vault materialization

Flags
--destination <value> required
--entry <value> required
--expected-digest <value>
--field <value> required
--materializer-digest <value> required
--mode <0400|0600> default: "0600"
--nonce <value> required
--overwrite
--owner <value> — Exact Vault owner: personal or workspace:<tenant-id>
--purpose <value> required
--runner-fingerprint <value> required
--runner-public-key <value> required
--tracked-exception
--workspace-root <value> — Absolute local workspace root containing the destination
Shellsift
sift vault materialize revoke

撤銷一個處理中、鎖定咗目的地嘅 Vault materialization

Arguments
id required — Materialization ID
Flags
--legacy-context — Use the Personal/v0 identity of a request created with the deprecated path-shaped --workspace alias
--owner <value> — Exact Vault owner: personal or workspace:<tenant-id>
Shellsift
sift vault materialize run

Request approval, wait, and materialize one Vault field at the exact approved path

Flags
--approval-timeout <value> default: 600
--destination <value> required — Destination path; relative paths resolve inside --workspace-root before approval
--entry <value> required
--field <value> required
--mode <0400|0600> default: "0600"
--overwrite
--owner <value> — Exact Vault owner: personal or workspace:<tenant-id>
--purpose <value> required
--tracked-exception
--workspace-root <value> — Absolute local workspace root containing the destination
Shellsift
sift vault materialize status

Inspect safe status for a destination-bound Vault materialization

Arguments
id required
Flags
--legacy-context — Use the Personal/v0 identity of a request created with the deprecated path-shaped --workspace alias
--owner <value> — Exact Vault owner: personal or workspace:<tenant-id>
Shellsift
sift vault search

搜尋保險庫項目

Arguments
query required — Search query
Flags
--limit <value> — Maximum number of results
--owner <value> — Exact Vault owner: personal or workspace:<tenant-id>
Shellsift
sift vault update

更新保險庫項目嘅元數據

Arguments
id required — Vault entry ID
Flags
--category <value> — Category
--description <value> — Description
--name <value> — Entry name
--owner <value> — Exact Vault owner: personal or workspace:<tenant-id>
--tags <value> — Comma-separated tags
--url <value> — Associated URL
Shellsift
sift vault use lease

喺 Git worktree 以外建立一個指定嘅、短時效環境 bundle artifact

Flags
--approval-timeout <value> default: 600
--checkout-root <value> — Checkout containing .sift/environment.yaml
--consumer <value> required — Bound consumer identifier; not a command allowlist
--consumer-pid <value> — Optional already-running consumer process lifetime
--destination <value> — Manifest destination used only to select one exact bundle
--endpoint-class <development|production|ci|shared_host> required
--holder <value> — Bound holder identifier; defaults to the local runner fingerprint
--owner <value> — Exact Vault owner: personal or workspace:<tenant-id>
--purpose <value> required
--ttl <value> default: 300

工作

執行代理工作隊列。

25 個指令
Shellsift
sift work block

將工作項目標示為受阻

Arguments
id required — Work item ID
Flags
--artifacts <value> — Artifact refs JSON array
--claim-token <value> — Claim token returned by work claim (required for lease-owned transitions)
--lease <value> — Lease seconds
--memory-decision <value> — Durable code-memory decision JSON (required on agent complete/review): {"decision":"store"|"skip","rationale":"...","fact"?,"category"?,"repositoryId"?,"filePath"?,"paths"?,"evidenceChunkIds"?,"sourceCommit"?,"confidence"?}
--owner <value> — Claim owner identity (required for lease-owned transitions)
--reason <value> — Block or failure reason
--summary <value> — Result summary
--verification-results <value> — Verification evidence JSON array: [{"command","exitCode","output"?}]
Shellsift
sift work cancel

取消工作項目

Arguments
id required — Work item ID
Flags
--artifacts <value> — Artifact refs JSON array
--claim-token <value> — Claim token returned by work claim (required for lease-owned transitions)
--lease <value> — Lease seconds
--memory-decision <value> — Durable code-memory decision JSON (required on agent complete/review): {"decision":"store"|"skip","rationale":"...","fact"?,"category"?,"repositoryId"?,"filePath"?,"paths"?,"evidenceChunkIds"?,"sourceCommit"?,"confidence"?}
--owner <value> — Claim owner identity (required for lease-owned transitions)
--reason <value> — Block or failure reason
--summary <value> — Result summary
--verification-results <value> — Verification evidence JSON array: [{"command","exitCode","output"?}]
Shellsift
sift work claim

領取下一個可用嘅可執行代理工作項目

Arguments
id — Optional specific work item ID
Flags
--agent <value> — Agent alias to claim for
--lease <value> default: 1800 — Lease seconds
--owner <value> required — Claim owner identity
Shellsift
sift work complete

核准並完成可執行代理工作項目

Arguments
id required — Work item ID
Flags
--artifacts <value> — Artifact refs JSON array
--claim-token <value> — Claim token returned by work claim (required for lease-owned transitions)
--lease <value> — Lease seconds
--memory-decision <value> — Durable code-memory decision JSON (required on agent complete/review): {"decision":"store"|"skip","rationale":"...","fact"?,"category"?,"repositoryId"?,"filePath"?,"paths"?,"evidenceChunkIds"?,"sourceCommit"?,"confidence"?}
--owner <value> — Claim owner identity (required for lease-owned transitions)
--reason <value> — Block or failure reason
--summary <value> — Result summary
--verification-results <value> — Verification evidence JSON array: [{"command","exitCode","output"?}]
Shellsift
sift work contract check

確定性地驗證一個 Work Contract V1 檔案或已擷取嘅工作項目

Arguments
id — Work item ID to fetch and validate
Flags
--file <value> — Path to a Work Contract V1 JSON file
Shellsift
sift work create

建立可執行代理工作項目

Flags
--acceptance-criteria <value> — Acceptance criteria JSON array or semicolon-separated text
--agent <value> — Assigned agent alias
--allow-deploy — Allow deployment in the authored contract
--allow-migrate — Allow migrations in the authored contract
--allow-network — Allow network access in the authored contract
--allow-vault — Allow audited Vault access in the authored contract
--allowed-actions <value> — Allowed actions JSON object
--capture-applicability <conversational_capture_required|non_conversational|unclassified> — Prospective capture applicability; this does not determine study eligibility
--capture-receipt <value> repeatable — Finalized capture receipt UUID to bind atomically; repeat for multi-surface handoffs
--context <value> — Input context JSON object
--contract <value> — Complete Work Contract V1 JSON
--contract-file <value> — Path to a complete Work Contract V1 JSON file
--depends-on <value> — Dependency JSON array: [{"workItemId":"<uuid>","requiredGate"?:"done"|"commands_passed"}]
--dry-run — Preview the normalized payload and contract without creating work
--exclude-scope <value> repeatable — Excluded workspace-relative write scope; repeat for multiple paths
--profile <coding|read-only|read_only> — Author a complete Work Contract V1 using the coding or read-only profile
--project <value> — Linked project ID
--prompt <value> — Agent prompt or instructions
--rank <value> default: 0 — Queue rank
--scope <value> repeatable — Included workspace-relative write scope; repeat for multiple paths
--task <value> — Parent human planning task ID
--title <value> required — Executable work item title
--verify <value> — Verification commands separated by semicolons
--write-scope <value> — Write scope JSON object
Shellsift
sift work dependencies get

Get authoritative dependencies and claimability for a work item

Arguments
id required — Work item UUID
Shellsift
sift work dependencies set

Atomically replace the authoritative dependencies for a work item

Arguments
id required — Work item UUID
Flags
--depends-on <value> required — Dependency JSON array; pass [] to clear dependencies
Shellsift
sift work dependency-policy get

Get a project default work-dependency gate

Flags
--project <value> required — Project UUID
Shellsift
sift work dependency-policy set

Set a project default work-dependency gate

Flags
--gate <done|commands_passed> required — Default gate for dependencies that omit requiredGate
--project <value> required — Project UUID
Shellsift
sift work edit

C2: Revise queued, unclaimed work while preserving its UUID and dependency edges. Do not use after claim or execution; wait for a queued unclaimed state or create follow-up work. Example: raise queue rank or refine acceptance criteria while the item is queued and unclaimed. Counterexample: do not change status, dependencies, or an active worker lease with this capability. Execution-contract edits supersede the active verification plan and reset verification evidence; queue-rank-only edits do not. The same Idempotency-Key and payload replays the original receipt; a different payload with that key is rejected.

Arguments
id required — Work item ID
Flags
--acceptance-criteria <value> — Replacement acceptance criteria JSON array
--allowed-actions <value> — Replacement allowed actions JSON object
--context <value> — Replacement input context JSON object
--contract <value> — Replacement Work Contract V1 JSON
--contract-file <value> — Path to replacement Work Contract V1 JSON
--dry-run — Show normalized diff and proof consequences without mutating
--expected-revision <value> required — Observed work item revision
--idempotency-key <value> required — Stable retry key for this exact edit
--patch <value> — Editable fields as one JSON object
--patch-file <value> — Path to an editable-fields JSON object
--prompt <value> — Replacement prompt; use --patch for null
--rank <value> — Replacement queue rank
--reason <value> required — Auditable reason for the revision
--title <value> — Replacement title
--verify <value> — Replacement verification commands as JSON array or semicolon-separated text
--write-scope <value> — Replacement write scope JSON object
Shellsift
sift work fail

將工作項目標記做失敗

Arguments
id required — Work item ID
Flags
--artifacts <value> — Artifact refs JSON array
--claim-token <value> — Claim token returned by work claim (required for lease-owned transitions)
--lease <value> — Lease seconds
--memory-decision <value> — Durable code-memory decision JSON (required on agent complete/review): {"decision":"store"|"skip","rationale":"...","fact"?,"category"?,"repositoryId"?,"filePath"?,"paths"?,"evidenceChunkIds"?,"sourceCommit"?,"confidence"?}
--owner <value> — Claim owner identity (required for lease-owned transitions)
--reason <value> — Block or failure reason
--summary <value> — Result summary
--verification-results <value> — Verification evidence JSON array: [{"command","exitCode","output"?}]
Shellsift
sift work get

攞執行代理工作項目嘅詳情

Arguments
id required — Work item ID
Shellsift
sift work heartbeat

延長工作項目租約

Arguments
id required — Work item ID
Flags
--artifacts <value> — Artifact refs JSON array
--claim-token <value> — Claim token returned by work claim (required for lease-owned transitions)
--lease <value> — Lease seconds
--memory-decision <value> — Durable code-memory decision JSON (required on agent complete/review): {"decision":"store"|"skip","rationale":"...","fact"?,"category"?,"repositoryId"?,"filePath"?,"paths"?,"evidenceChunkIds"?,"sourceCommit"?,"confidence"?}
--owner <value> — Claim owner identity (required for lease-owned transitions)
--reason <value> — Block or failure reason
--summary <value> — Result summary
--verification-results <value> — Verification evidence JSON array: [{"command","exitCode","output"?}]
Shellsift
sift work list

列出執行代理工作項目

Flags
--agent <value> — Filter by assigned agent alias
--limit <value> — Maximum results
--project <value> — Filter by project ID
--status <value> — Filter by status
--task <value> — Filter by parent human planning task ID
Shellsift
sift work release

將攞咗嘅工作項目放返入隊列

Arguments
id required — Work item ID
Flags
--artifacts <value> — Artifact refs JSON array
--claim-token <value> — Claim token returned by work claim (required for lease-owned transitions)
--lease <value> — Lease seconds
--memory-decision <value> — Durable code-memory decision JSON (required on agent complete/review): {"decision":"store"|"skip","rationale":"...","fact"?,"category"?,"repositoryId"?,"filePath"?,"paths"?,"evidenceChunkIds"?,"sourceCommit"?,"confidence"?}
--owner <value> — Claim owner identity (required for lease-owned transitions)
--reason <value> — Block or failure reason
--summary <value> — Result summary
--verification-results <value> — Verification evidence JSON array: [{"command","exitCode","output"?}]
Shellsift
sift work requeue

Return blocked work to the queue for a fresh claim

Arguments
id required — Work item ID
Flags
--artifacts <value> — Artifact refs JSON array
--claim-token <value> — Claim token returned by work claim (required for lease-owned transitions)
--lease <value> — Lease seconds
--memory-decision <value> — Durable code-memory decision JSON (required on agent complete/review): {"decision":"store"|"skip","rationale":"...","fact"?,"category"?,"repositoryId"?,"filePath"?,"paths"?,"evidenceChunkIds"?,"sourceCommit"?,"confidence"?}
--owner <value> — Claim owner identity (required for lease-owned transitions)
--reason <value> — Block or failure reason
--summary <value> — Result summary
--verification-results <value> — Verification evidence JSON array: [{"command","exitCode","output"?}]
Shellsift
sift work review

將執行代理工作標記做需要人工審核

Arguments
id required — Work item ID
Flags
--artifacts <value> — Artifact refs JSON array
--claim-token <value> — Claim token returned by work claim (required for lease-owned transitions)
--lease <value> — Lease seconds
--memory-decision <value> — Durable code-memory decision JSON (required on agent complete/review): {"decision":"store"|"skip","rationale":"...","fact"?,"category"?,"repositoryId"?,"filePath"?,"paths"?,"evidenceChunkIds"?,"sourceCommit"?,"confidence"?}
--owner <value> — Claim owner identity (required for lease-owned transitions)
--reason <value> — Block or failure reason
--summary <value> — Result summary
--verification-results <value> — Verification evidence JSON array: [{"command","exitCode","output"?}]
Shellsift
sift work revisions

List immutable, attributable work-item revision receipts and field diffs

Arguments
id required — Work item ID
Flags
--limit <value> default: 50 — Maximum revisions to return
Shellsift
sift work start

將工作項目標記做執行中

Arguments
id required — Work item ID
Flags
--artifacts <value> — Artifact refs JSON array
--claim-token <value> — Claim token returned by work claim (required for lease-owned transitions)
--lease <value> — Lease seconds
--memory-decision <value> — Durable code-memory decision JSON (required on agent complete/review): {"decision":"store"|"skip","rationale":"...","fact"?,"category"?,"repositoryId"?,"filePath"?,"paths"?,"evidenceChunkIds"?,"sourceCommit"?,"confidence"?}
--owner <value> — Claim owner identity (required for lease-owned transitions)
--reason <value> — Block or failure reason
--summary <value> — Result summary
--verification-results <value> — Verification evidence JSON array: [{"command","exitCode","output"?}]
Shellsift
sift work verification evidence

Submit externally executed evidence for an exact plan version and step ID

Arguments
id required — Work item ID
Flags
--artifacts <value> — Artifact reference JSON array for larger logs
--attempt <value> required — Caller-stable attempt identity
--claim-owner <value> — Active lease owner for workspace-service evidence
--claim-token <value> — Opaque active lease token for workspace-service evidence
--environment <value> required — Execution environment label
--exit-code <value> — Process exit code when applicable
--outcome <passed|failed|error> required — Attempt outcome
--output <value> — Bounded output excerpt; secrets are redacted by the API
--plan-version <value> required — Active verification plan version
--provenance <value> — Evidence provenance JSON object
--ran-at <value> — RFC3339 execution timestamp
--step <value> required — Stable verification step UUID
Shellsift
sift work verification history

List immutable verification-plan history and coverage

Arguments
id required — Work item ID
Shellsift
sift work verification plan

Show the active versioned verification plan and coverage

Arguments
id required — Work item ID
Shellsift
sift work verification revise

Create an audited active verification-plan revision

Arguments
id required — Work item ID
Flags
--expected-version <value> required — Observed active plan version
--provenance <value> — Revision provenance JSON object
--reason <value> required — Audited revision reason
--steps <value> — Verification step JSON array
--steps-file <value> — Path to a verification step JSON array
--yes — Confirm activation without prompting
Shellsift
sift work verify

Deprecated compatibility command. Hosted LLM verification is retired; use verification-command evidence.

Arguments
id required — Work item ID
Flags
--history — List historical verifier runs recorded before retirement
--model <value> — Deprecated; ignored because hosted verification is retired
--reps <value> — Deprecated; ignored because hosted verification is retired

Worker

喺本地執行工作嘅 runner。

2 個指令
Shellsift
sift worker dispatch

為啱啱好兩個 AWS agent worker 建立一個零開支、表面中立嘅計劃

Flags
--max-runtime-minutes <value> default: 120 — Per-worker runtime ceiling
--source-sha <value> — Reviewed 40-character source Git SHA; defaults to a clean current HEAD
--surface <cli|t3|codex|claude-code|mcp> default: "cli" — Calling control surface; does not change dispatch identity
--work-item <value> required; repeatable — Queued Sift work-item UUID; repeat exactly twice
Shellsift
sift worker run

領取可執行工作,執行本地 worker 指令,同埋回報需要審核嘅產出

Flags
--agent <value> required — Agent alias to claim work for
--command <value> required — Local command to run for the claimed work item
--cwd <value> — Fallback working directory for the local command
--lease <value> default: 1800 — Lease seconds
--owner <value> required — Worker owner fingerprint

Workspaces

3 個指令
Shellsift
sift workspaces current

顯示目前揀選嘅個人或協作 workspace

Shellsift
sift workspaces list

列出已認證用戶可用嘅協作 workspace

Shellsift
sift workspaces use

揀選一個協作 workspace 嚟進行探索,或者揀「個人」嚟清除設定

Arguments
id required — Workspace ID, or "personal"

互動式 Copilot

sift interactive 指令會啟動一個終端機 copilot,可以同你傾偈、執行工具、改 code、開平行 agent 分支、計劃工作,仲可以畫圖 — 全部喺終端機搞掂,直接操作你嘅檔案系統同 Siftable 工作圖譜。

Terminal
$ sift interactive

要求同啟動

  • 需要安裝 Bun。 sift interactive 會重新執行 Bun;如果未裝,佢會顯示 curl -fsSL https://bun.sh/install | bash
  • 需要身份驗證 — 可以用 --tokenSIFT_TOKEN 或者 sift auth login
  • 「大腦」會喺進程內運行 — 唔使另外啟動 daemon。
  • 寫入範圍只限於工作區根目錄 (workspace root) — 即係你啟動目錄入面最近嗰個有 .git 嘅資料夾。呢個係 /status 報告嘅範圍,亦係原生寫入路徑強制執行嘅邊界。

介面

The composer is a full readline-capable text area. Enter submits; Shift+Enter / Ctrl+J insert a newline; submitting while the agent is busy queues your message. !command runs via bash -lc into the transcript (a bare !cd <path> changes the session directory; output clipped to ~4000 chars). Large or structured pastes become a collapsed chip; pasted images are validated, normalized, and attached. ? on an empty composer shows hotkeys.

斜線指令

輸入 / 就可以打開指令選單。隱藏指令仲係可以輸入,但唔會喺選單度出現。

CommandGroupDescription
/help, /hotkeys, /statusSessionCommand list, keyboard shortcuts, and current model/scope/queue status
/cwd [path]SessionShow or change the working directory (recomputes the workspace root)
/copy [last|all|explorer]SessionCopy the latest reply, whole transcript, or latest explorer report to the clipboard
/clear, /quitSessionReset the transcript; exit
/threads [clear], /compactSessionManage the persisted thread; force a context compaction (requires context compaction enabled)
/model [id] [effort]ModelOpen the model picker or select a model and reasoning effort directly
/codex [login|on|use|off|logout|status]ModelControl the Codex (ChatGPT) engine; default subcommand is status
/key <provider> <key>, /key vault <provider>ModelStore a provider API key, or hydrate it from Siftable Vault
/loginModelSiftable device-code login from inside the TUI
/explorerModelConfigure the repo Explorer (context-gathering backend)
/skills [name]SkillsList discovered skills, or print one skill's body
/branchesBranchesOpen the parallel-agent branches hub
/spawn <title> [--rw <globs>|--rw-any|--ro]BranchesStart a child agent branch in its own git worktree with an access mode
/merge, /rebase, /sendback, /rejectBranchesLand, replay, resume, or reject a child branch
/workWorkOpen the work-queue hub (board of agents and items by status)
/plan [objective | work [--apply] [--after SRC:DST] [--limit N] | view]WorkPlan from an objective, or compute a precedence DAG over the agent work queue as a Mermaid graph
/handoff <title> [--agent ..] [--files ..] [--acceptance ..] [--verify ..]WorkCreate a Siftable work item from the current context
/proof <claim>, /remember <fact> --category <..>WorkGather code/test evidence; store durable code memory
/crew [list|show|new|run], /collabCrewsManage and run multi-agent crews; show in-process collaboration sessions
/mermaid [request|file.mmd|source], /viewDiagramsRender Mermaid (NL request, file, or source) in the terminal; open the pannable viewer
/theme, /sounds [on|off]AppearanceOpen the appearance picker; toggle UI sounds

模型同引擎

The model picker (/model) is two-stage: choose a model, then a reasoning effort (saved to ~/.siftable/prefs.json). The catalog includes GPT-5.6 Sol, Terra, and Luna (ChatGPT plan via the Codex engine — /codex login / /codex on select Sol by default), Claude Opus 4.8 (OpenRouter or direct Anthropic with ANTHROPIC_API_KEY), Claude Sonnet 4.6 / Haiku 4.5, Gemini 3.x Flash / Flash-Lite, GPT-5.4 mini / nano, and Morph v3 Large (apply-only). Codex drives the OpenAI codex app-server sidecar (ChatGPT device-code login). All other providers route through the bundled OpenFunction agent via <PROVIDER>_API_KEY. /key vault <provider> hydrates a key from Siftable Vault behind an approval prompt; the secret is never printed or written to disk.

Repo Explorer

/explorer configures repository context gathering before a turn. Modes: auto, off, deterministic, scout, fanout, warpgrep. Pick a scout model and budget (cheap/normal/deep). warpgrep needs MORPH_API_KEY (auto-hydrated from Vault when available). Settings persist in prefs.json.

技能

系統會喺 <root>/{.sift,.claude,.codex,.agents}/skills~/.claude|.codex|.agents/skills~/.config/sift/skills 同埋套件內置嘅路徑搵 SKILL.md 技能(優先次序:項目 > 用戶 > 內置)。Agent 可以透過工具調用技能,系統提示詞入面最多會列出大約 50 個技能。

鍵盤快捷鍵

覆蓋層會優先接收鍵盤輸入,所以快捷鍵係跟唔同模式而定。

  • Enter submit (queues if busy) · Shift+Enter/Ctrl+J newline · Tab complete a lone /foo · ↑/↓ prompt history
  • Esc abort turn → clear draft → deselect · Ctrl+C abort → clear → deselect → quit (never copies) · Ctrl+D quit on empty draft
  • Cmd/Super+A select all · Cmd+C/Ctrl+Shift+C copy selection or latest reply · Ctrl+O Explorer diagnostics · ? hotkeys
  • Approval gate: y/Enter allow once · a always · b bypass-all · n/Esc deny

原生加速

影響效能嘅關鍵路徑 (好似係 context 壓縮、長對話記憶、檔案系統掃描、合併編排、圖像處理) 都係經 Bun FFI 載入原生 Zig 模組嚟行,每個模組都有同步嘅 TypeScript fallback。個 package 內置咗 macOS (Apple Silicon)Linux (x64) 嘅預建庫;其他平台會用 fallback。設定 SIFT_NO_NATIVE=1 可以強制用 fallback,而 SIFT_CONTEXT_COMPACTION=1 就可以啟用即時 context-token 計量器,仲有對話持久化同恢復功能。

外觀同音效

/theme 提供 10 款配色方案(預設係 "sieve" — 炭灰色底配暖琥珀色),設定會儲存喺 ~/.siftable/appearance.json/sounds 可以開關 UI 音效(預設係關閉),設定會儲存喺 ~/.siftable/sounds.json,亦可以用 SIFT_SOUNDS 嚟覆蓋。

The copilot is read-only by default; write/edit tools are scoped to the workspace root and gated by a four-way approval prompt (allow once / always / bypass-all / deny). With nothing listening, requests deny. Auto-approve environment overrides are always scrubbed at launch.

完整指南,包括晒所有斜線指令、快捷鍵、環境變數同埋設定檔:GitHub 上嘅 docs/interactive.md

Give your agent a workspace.