alcoa-guard
Lint a record / dataset / kit run for ALCOA+ data integrity (attribution, contemporaneity, completeness, accuracy, consistency).…
Run the agentic-sop-kit workflow (extract→compute→report, or a declared topology) and report the DRAFT result. Works out-of-the-box (bundled demo) even before a project adopts the kit.
> /plugin marketplace add s0912758806p/agentic-sop-to-workHow it fires
How this command gets triggered: by you, by Claude, or both.
/sop-flowContext preview
What this command does when you run it.
Run the agentic-sop-kit workflow (extract→compute→report, or a declared topology) and report the DRAFT result. Works out-of-the-box (bundled demo) even before a project adopts the kit.
description: Run the agentic-sop-kit workflow (extract→compute→report, or a declared topology) and report the DRAFT result. Works out-of-the-box (bundled demo) even before a project adopts the kit.
執行 agentic-sop-kit 的編排流程並回報 DRAFT。**先判斷目前專案是否已導入 kit**:
跑該專案自己的、受 Stop-hook 閘門保護的流程: 1. 依賴檢查:`python3 agentic-sop-kit/check_deps.py`(缺項明確列出 → 請使用者補齊,勿硬跑)。 2. 跑流程:`python3 agentic-sop-kit/workflow/run.py`(可加 `--input <檔>` 換輸入)。$ARGUMENTS 3. 讀新產生的 `agentic-sop-kit/runs/<run_id>/report.md` 與 `run_manifest.json`,向使用者摘要。
直接跑 plugin 內附的範例 kit,輸出寫到專案的 `.agentic-sop-runs/`: 1. 依賴檢查:`python3 "${CLAUDE_PLUGIN_ROOT}/kit/check_deps.py"`。 2. 跑範例:`python3 "${CLAUDE_PLUGIN_ROOT}/kit/workflow/run.py" --out-base "$CLAUDE_PROJECT_DIR/.agentic-sop-runs"`(可加 `--input <檔>`)。$ARGUMENTS 3. 讀 `.agentic-sop-runs/<run_id>/report.md` 與 `run_manifest.json`,向使用者摘要。 4. 告訴使用者:要讓**這個專案**常駐 kit 並受 Stop-hook 回歸閘門保護,跑一次: `python3 "${CLAUDE_PLUGIN_ROOT}/kit/bootstrap.py" --project "$CLAUDE_PROJECT_DIR"`(加 `--with-claude-skills` 會順便產出對話可觸發的 runner skills)。
寫入衝突/無界環/孤邊)——**據實回報那幾行問題、請人修 `flow.json`,不要硬跑**。 要給人看圖用 `--graph`;跑完的狀態在 manifest 的 `topology` 與 `path_taken` 裡。
1. 讀 manifest 的 `failure{step,gate_type,message,artifact}` 分類:**輸入問題/生成層輸出**(schema/trace 等)→ 修輸入或重生該段,**用相同 `--run-id` 重跑**(引擎對同 run-id 計數、超過 `--max-fix-retries 3` 會自行拒跑=程式封頂);**工具碼/recompute/cmd bug** → 診斷並提修正建議、不盲跑、不偷改輸出,交人;**判斷/受控步驟** → 不自動修,交人。 2. `stalled:true`(原地打轉:`stall_reason` = idle/thrash)→ **STOP,回報卡住的 gate、重複的 `repeated_signature`、撞了 `stall_rounds` 圈**,不得佯稱成功、不得換 `--run-id` 規避。 3. `fix_exhausted:true` 或不可自動修 → **STOP,據實回報每次嘗試與原因**,不得佯稱成功。 4. `revisit_exhausted:true`(退回邊撞上界)或 `topology_invalid:true`(拓撲不合法,未執行即拒跑) → **STOP 交人**:回報 `back_edge`(哪條邊、上界多少)或那幾行拓撲問題。 **不得**為了讓它過關而調高 `max_revisits`、改寬 branch 條件、或改動 `reads`/`writes` 宣告——那是竄改閘門。 5. **永不為過關竄改輸出**(閘門查真相);最終一律 **DRAFT、需人核准**,永不自動歸檔。
Loop Engineering — make an agent's loop produce verifiable progress, stay honest, and stay bounded, by deterministic mechanism rather than vibes.
Lint a record / dataset / kit run for ALCOA+ data integrity (attribution, contemporaneity, completeness, accuracy, consistency).…
Lint a Claude Code plugin / marketplace against house invariants, or scaffold a new grammar-conformant plugin skeleton.
Get an independent adversarial SECOND OPINION on a finished DRAFT — check its claims against its evidence (no fabrication, no…