Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add s0912758806p/agentic-sop-to-work --skill agentic-sopgit clone --depth 1 https://github.com/s0912758806p/agentic-sop-to-workWrote 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/skills/s0912758806p/agentic-sop-to-work/agentic-sop)<a href="https://agentmods.dev/skills/s0912758806p/agentic-sop-to-work/agentic-sop"><img src="https://agentmods.dev/badge/skills/s0912758806p/agentic-sop-to-work/agentic-sop/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/skills/s0912758806p/agentic-sop-to-work/agentic-sop"><img src="https://agentmods.dev/badge/skills/s0912758806p/agentic-sop-to-work/agentic-sop.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 | $0.00127 | $0.02076 |
| Opus 5.5 | $0.00051 | $0.00830 |
| Sonnet 5.5 | $0.00025 | $0.00415 |
| Haiku 4.5 | $0.00013 | $0.00208 |
Grade A, and why
agentic-sop 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 1mo 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic SOP — 把人工流程做成可治理的 agent 工作流
何時用 / 不用
- 用：要把人工 SOP／手動流程自動化、建新 agent 工具、設計「拆解＋閘門」、或開新的 agent 工作流專案時。任何專案皆適用，尤其未來新項目。
- 不用：稽核既有工作流是否退化成 mega agent → 用
agentic-workflow-audit；執行既有 GMP 產生器 → 用該工具自己的 skill。
開場：先判斷輸入型態（intake 分流）
觸發後第一件事——看使用者怎麼來，別急著動工：
- 已有正式輸入（寫好的 spec／既有 requirement 或 runner skill／已填好的
templates/human_sop_template.md）→ 照原樣採用、不重寫，直接進下面的拆解。 - 只有自然語言需求/任務 → 先用
templates/human_sop_template.md起草一份 Human SOP：能由輸入得到的填上、未知的標【待補】（絕不臆造）；草稿好 STOP 給人看一眼（「這樣有抓到你的流程嗎？改／確認」）→ 確認後才續入拆解。 - 判不準 → 問一個澄清問題，別猜路。 草稿 SOP 也是 DRAFT（受「DRAFT＋人核准」約束）；本步只動生成層，不碰引擎/閘門。
核心模型（三段鏈，缺一不可）
Human SOP → 工具 Skill（SKILL.md） → Agentic Workflow（拓撲宣告 + 誠實閘門 + hook）。 中間的 Skill 環最易被忘：工具一改，SKILL.md 必須同次更新。每支工具實作同一條七階段迴圈： intake → 分類/前置檢查 → 確定性層(程式) → 生成層(Claude，只整理輸入) → 組裝 DRAFT → 閘門自評(≤2 次) → 覆核包 → 人核准 STOP。
拆解完，先畫拓撲（動手接線之前）
拆出節點之後、寫 flow.json 之前，先把圖講清楚——這一步只花幾分鐘，卻是後面所有閘門的地基：
- 節點：列出每個節點（＝一個工具的一步）。 節點不是 agent：把工具換成模型的節點常被叫做 agent，但一 skill 一工具不變； 一個節點裡塞了整條流程就是 mega agent，名字叫什麼都一樣。
- 邊：每條邊取一個名字——「誰把什麼交給誰」。交接的是具名產物，不是「整包 context 丟過去」。
接著給它型別（
schema_ref指向workflow/schemas/<tag>.json）：邊沒有型別，交接協定就是假的。 - 狀態欄位與 owner：列出流程要共用的欄位，每個欄位指定唯一一個 writer 節點；
讀取方宣告
reads。值不另外存——留在該節點的 artifact 裡（written_by就是produced_by）。 - 退回邊：哪一步的判定會把工作退回上游？那條邊宣告
back:true＋max_revisits:<N>。 沒有上界的環不准存在；退回的判定必須由確定性的欄位決定，不是由模型當場決定。 - 驗證：
python3 workflow/run.py --plan會把整張圖靜態判過（不可達節點、read-before-write、 寫入衝突、無界環、孤邊），不合法在跑之前就 exit 2；--graph畫出來給人看。
五題有任一題答不出來，就是還沒拆完——別急著寫 flow.json。 若流程本來就是一條直線、也沒有退回，那就照直線做：以上宣告全是選擇性的，不宣告即維持線性行為。
落地：導入 agentic-sop-kit（不要重造）
方法論已封裝成可攜套件，直接導入、別重寫：
- 一鍵導入：
python3 ~/.claude/agentic-sop-kit/bootstrap.py --project /path/to/project（複製 kit＋裝/sop-flow＋合併 Stop-hook）。canonical 在~/.claude/agentic-sop-kit/。 python3 agentic-sop-kit/check_deps.py驗依賴；workflow/run.py跑通範例。- 用
templates/human_sop_template.md寫 SOP（每步標工具）；依拆解規則把每個「步驟×工具」用templates/skill_template/建成skills/<name>/。 - 依上一節的拓撲在
workflow/flow.json接線（節點順序、schema_ref、reads/writes、退回邊）；--plan驗過再跑；裝commands/+hooks/。 詳見 kit 的SOP.md（方法論 canonical）與README.md（安裝）；圖示範流程見workflow/examples/graph.json。
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.
- 1mo ago Changed · +26 lines 11f448c72692
- 1mo ago First seen · 40 lines · 127 tokens per session scan A 48d3a1581f55
agentic-sop is a skill published in the GitHub repository s0912758806p/agentic-sop-to-work (211 stars, last pushed 1mo ago), licensed MIT. It adds 127 tokens to every session and 2,076 once invoked, about $0.0005 per session on Opus 5.5. 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 skills, from other repositories
state-management
Cache management, configuration best practices, and progressive disclosure patterns for efficient context window usage. Use when working with large responses, optimizing token costs, or managing plugin state across operations.
session-recap
Document Claude Code sessions by extracting knowledge into cross-referenced documentation. Triggers on "recap the session", "summarize the work", or after significant code changes.
kb-ingest
Ingest external sources into the knowledge bank through interactive study or quick filing. Two modes — Quick (summarize → file) and Study (theme-by-theme deep dive with online research and personal notes → multi-layer KB output → optional blog/slack synthesis). Triggers on "ingest this", "study this article", "add to…
kb-lint
Health-check the knowledge bank for orphan documents, stale content, broken WikiLinks, index drift, and missing frontmatter. Generates a severity-graded report. Use this skill whenever the user mentions lint, health check, KB maintenance, stale docs, broken links, orphan pages, missing references, knowledge bank…
x-bug2rag
A knowledge-capture tool that turns reusable bug explanations into a local RAG collection, meaning a searchable store of text that an agent can retrieve later. It records the trigger, incorrect implementation, correct implementation, and observable difference.
x-tech-design
A technical-design document workflow that turns an approved feature specification into a separate architecture and implementation plan. It records modules, protocols, data flow, constraints, and test references for later task breakdown.