Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add s0912758806p/agentic-sop-to-work/plugin install agentic-sop-kitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/s0912758806p/agentic-sop-to-work/sop-flow)<a href="https://agentmods.dev/commands/s0912758806p/agentic-sop-to-work/sop-flow"><img src="https://agentmods.dev/badge/commands/s0912758806p/agentic-sop-to-work/sop-flow/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/s0912758806p/agentic-sop-to-work/sop-flow"><img src="https://agentmods.dev/badge/commands/s0912758806p/agentic-sop-to-work/sop-flow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00045 | $0.01288 |
| Opus 5 | $0.00023 | $0.00644 |
| Sonnet 5 | $0.00009 | $0.00258 |
| Haiku 4.5 | $0.00005 | $0.00129 |
Grade A, and why
sop-flow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
執行 agentic-sop-kit 的編排流程並回報 DRAFT。先判斷目前專案是否已導入 kit:
情況 A — 專案已導入($CLAUDE_PROJECT_DIR/agentic-sop-kit/ 存在)
跑該專案自己的、受 Stop-hook 閘門保護的流程:
- 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)。 - 跑流程:
python3 agentic-sop-kit/workflow/run.py(可加--input <檔>換輸入)。$ARGUMENTS - 讀新產生的
agentic-sop-kit/runs/<run_id>/report.md與run_manifest.json,向使用者摘要。
情況 B — 尚未導入(開箱即用 demo,免 bootstrap)
直接跑 plugin 內附的範例 kit,輸出寫到專案的 .agentic-sop-runs/:
- 依賴檢查:
python3 "${CLAUDE_PLUGIN_ROOT}/kit/check_deps.py"。 - 跑範例:
python3 "${CLAUDE_PLUGIN_ROOT}/kit/workflow/run.py" --out-base "$CLAUDE_PROJECT_DIR/.agentic-sop-runs"(可加--input <檔>)。$ARGUMENTS - 讀
.agentic-sop-runs/<run_id>/report.md與run_manifest.json,向使用者摘要。 - 告訴使用者:要讓這個專案常駐 kit 並受 Stop-hook 回歸閘門保護,跑一次:
python3 "${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)。
兩種情況都適用
- 先靜態驗證拓撲:跑之前先加
--plan。exit 2 表示拓撲不合法(不可達節點/read-before-write/ 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。 - 產出一律是 DRAFT → 提醒需人覆核、永不自動歸檔進受控系統。
- 任一步
"state":"FAILED"→ 封頂自動修復(fix-loop,最多 3 次),再不行才交人:- 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。 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。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。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。- 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。
- 讀 manifest 的
- 事實只來自輸入與工具輸出;缺值標【待補】,絕不臆造。
- 回歸閘門現附帶健康監測:覆蓋縮水會讓
verify回 3(硬擋、接 Stop-hook);變慢/flaky 只 advisory 印出、不擋。刻意降覆蓋用verify.py --rebaseline。 - 迴圈狀態有界:
regression_log由verify自動輪替(保底不傷健康趨勢);舊 run 目錄用run.py --prune(人授權)清理。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago Changed · +6 lines · +5 tokens per session caf2a7fd1283
- 11d ago First seen · 31 lines · 40 tokens per session scan A c4dfecd47bed
sop-flow is a command published in the GitHub repository s0912758806p/agentic-sop-to-work (206 stars, last pushed 2d ago), licensed MIT. It adds 45 tokens to every session and 1,288 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
gh-security-review
Use to perform a dedicated security review of current branch changes before pushing.
gh-release
Create a new release for the marketplace or a specific plugin.
flow
Universal workflow entry point. Use /flow for skill-driven GitHub development. Verbs: start, commit, pr, review, address, merge, resolve, release, status, learn, setup, explain, debug, design, brainstorm, issue.
ledger-research
Launch parallel evidence collection across all active research pillars.
ledger-spec
Generate constrained PRD and architecture documents where every section cites decisions.
quick-research
Quick research with source verification (lighter than /deep-research).