agentic-sop-to-work

Turn a process you do by hand into steps a program runs — and never let the AI make up facts, loop forever, or have the final say. 把你手動做的流程，變成程式一步步執行的流程——而且不讓 AI 編造事實、無限打轉，或替你做最後決定。

/plugin marketplace add s0912758806p/agentic-sop-to-work
/plugin install agentic-sop-kit@agentic-sop-to-work
/reload-plugins

🌐 English ・ 繁體中文

Follow the dot: 🟢 passed · 🔴 blocked · 🟠 retried or sent back, always with a limit · 🟣 handed to review.
跟著圓點走：🟢 通過 · 🔴 擋下 · 🟠 重試或退回（一定有上限） · 🟣 交給審查。

English

How it works — the five things the animation shows:

1. Check the plan first. run.py --plan reads the whole flow and refuses one with a dead end or an endless loop before anything runs.
2. Code runs every step. One step = one tool. If a tool fails or writes nothing, the run stops. To also verify what it wrote, attach a gate (cmd_gate · schema_gate · trace_gate · recompute_gate · residual_gate) — plain code, no AI grading itself.
3. Retries have limits. /sop-flow auto-fixes and re-runs a failed step up to 3 times (configurable), and stops early if it is going in circles. A review step can send work back, but only as many times as the flow declares.
4. The result is a DRAFT. Missing facts are marked 【待補】, never invented. Before a human signs off, second-opinion-honesty and alcoa-guard can check the draft.
5. Every code change is re-tested. In a project that uses the kit, a Stop hook runs the regression tests when Claude finishes, and blocks if something broke.

What's in the box — four plugins, pure Python standard library, every report is a DRAFT:

Install — the three lines at the top. Needs Python 3.8+ as python3. Check: /help lists /agentic-sop-kit:sop-flow. Settings when you enable the plugin: max_fix_retries · stall_window · keep_runs.

Compatibility — what CI actually runs on every PR, for all four plugins:

Go deeper — kit/README.md: the engine, gates, graph features, settings · kit/SOP.md: the method · CONTRIBUTING.md: tests, versioning, releases · MIGRATION.md: what v2.0 removes · CHANGELOG.md.

Update — /plugin marketplace update agentic-sop-to-work, then /reload-plugins. Each release is a git tag (vX.Y.Z for the kit, <plugin>-vX.Y.Z for the others) with a GitHub release.

繁體中文

怎麼運作 — 動畫裡的五件事：

1. 先檢查流程。 run.py --plan 讀完整張流程圖；有死路或無限迴圈，還沒開跑就拒絕。
2. 每一步都由程式執行。 一步＝一個工具。工具失敗或沒有產出，流程就停。要再驗證產出內容，就在那一步掛上閘門（cmd_gate · schema_gate · trace_gate · recompute_gate · residual_gate）——全是程式，不讓 AI 自己打分數。
3. 重試有上限。 /sop-flow 遇到失敗會自動修、重跑，最多 3 次（可調），原地打轉就提早停。審查步驟可以退件重做，但次數不能超過流程宣告的上限。
4. 產出只是草稿。 缺的事實標 【待補】，絕不編造。交給人核准之前，可以先用 second-opinion-honesty 和 alcoa-guard 檢查。
5. 每次改程式都重新測試。 在導入 kit 的專案裡，Claude 收工時 Stop hook 會自動跑回歸測試，壞了就擋下。

你會得到 — 四個 plugin，純 Python 標準庫，所有報告都是草稿：

安裝 — 最上面那三行。需要 Python 3.8+，且能用 python3 呼叫。確認：/help 看得到 /agentic-sop-kit:sop-flow。啟用 plugin 時可設定：max_fix_retries · stall_window · keep_runs。

相容性 — CI 每個 PR 對四個 plugin 實際跑的組合：

深入了解 — kit/README.md：引擎、閘門、圖狀流程、設定 · kit/SOP.md：方法論 · CONTRIBUTING.md：測試、版本、發版 · MIGRATION.md：v2.0 會移除什麼 · CHANGELOG.md。

更新 — /plugin marketplace update agentic-sop-to-work，再 /reload-plugins。每個版本都有 git tag（kit 是 vX.Y.Z，其他是 <plugin>-vX.Y.Z）和 GitHub release。

flowchart LR
    n0["draft<br/>draft@1"]
    n1["verdict<br/>verdict@1"]
    n2{{gate}}
    n3["accept<br/>accepted@1"]
    n0 --> n1
    n1 --> n2
    n2 -.->|"verdict == 'reject' (≤2)"| n0
    n2 -->|"default"| n3

License — MIT (LICENSE · NOTICE); keep the notice in copies, including single files. · 授權 MIT，副本（含單一檔案）需保留聲明。