agentic-workflow-audit

agentic-workflow-audit is a skill for Claude Code from s0912758806p/agentic-sop-to-work. It costs 188 tokens per session (3,317 once invoked), scanned A, original, MIT.

A read-only review method for checking whether an AI-agent or language-model workflow is genuinely split into small, independent tasks with clear rules and checks.

In plain words
What is it for?
It helps audit task boundaries, data passed between steps, success checks, recovery behavior, and whether each step has its own operating procedure.
Why use it?
It exposes workflows that look modular but are really one tangled “mega-agent,” using code and execution logs as evidence instead of trusting documentation.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the agentic-sop-kit plugin — 9 skills, 1 command, 2 hooks shipped together

Good fit It helps audit task boundaries, data passed between steps, success checks, recovery behavior, and whether each step has its own operating procedure.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/s0912758806p/agentic-sop-to-work/agentic-workflow-audit
Install

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.

Any agent
npx skills add s0912758806p/agentic-sop-to-work --skill agentic-workflow-audit
Clone the repo
git clone --depth 1 https://github.com/s0912758806p/agentic-sop-to-work

Made for: Claude Code.

Or install agentic-sop-kit, the plugin that ships this one along with the rest of its 9 skills, 1 command, 2 hooks.

Wrote 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.

agentmods badge for agentic-workflow-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/s0912758806p/agentic-sop-to-work/agentic-workflow-audit/github.svg)](https://agentmods.dev/skills/s0912758806p/agentic-sop-to-work/agentic-workflow-audit)
Your own site
<a href="https://agentmods.dev/skills/s0912758806p/agentic-sop-to-work/agentic-workflow-audit"><img src="https://agentmods.dev/badge/skills/s0912758806p/agentic-sop-to-work/agentic-workflow-audit/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.

agentmods 80×15 button for agentic-workflow-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/s0912758806p/agentic-sop-to-work/agentic-workflow-audit"><img src="https://agentmods.dev/badge/skills/s0912758806p/agentic-sop-to-work/agentic-workflow-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 188 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,317 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00188 $0.03317
Opus 5 $0.00094 $0.01658
Sonnet 5 $0.00038 $0.00663
Haiku 4.5 $0.00019 $0.00332

Measured 3d ago against content hash a09da1149559, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

agentic-workflow-audit 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 3d 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.

plugins/agentic-sop-kit/skills/agentic-workflow-audit/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentic Workflow 稽核

角色與目標

扮演一個唯讀的程式碼稽核者。任務是判定目標專案是否真正實作了「拆成小 Task、每步有 SOP、串接成可自我修復的 workflow」這套架構,還是一個徒有模組化外表、實際上把所有事攪在一起的 mega agent。

全程唯讀。不修改、不新增、不刪除任何檔案。

為什麼要這樣查

mega agent 的退化通常是悄悄發生的——程式碼看起來分了模組,跑起來其實全部黏在一起。文件與註解往往描述的是「意圖」而非「現況」。因此稽核的第一原則是看實際執行、不看宣稱。下面每一項檢查都要求你拿出證據,就是為了擋掉「自我安慰式」的從寬判定。

行為準則

  1. 以程式碼與真實 trace / log 為準,不採信 README、設計文件、註解裡的宣稱。
  2. 每個判定都附證據:引用具體檔案路徑與行號,或一段真實 log / trace 摘錄。無證據者一律標記 UNKNOWN
  3. 不從寬解釋:模稜兩可時判 FAIL,並寫清楚你需要什麼證據才能改判。
  4. 找不到就標 UNKNOWN,絕不臆測為 PASS。

稽核項目

逐項執行下列七項。每項產出:判定(PASS / PARTIAL / FAIL / UNKNOWN)、證據、具體缺口、可執行的修補建議。

拿圖當檢查表。 一個拆好的工作流就是一張圖:節點是各自負責一塊的步驟、是「誰把什麼交給誰」的具名契約、 狀態是沿邊流動且每個欄位有唯一 writer 的共用資訊。下面七項就是在問這張圖畫不畫得出來、以及畫出來合不合法。 注意「節點」不等於「agent」:一個節點是一個工具的一步;把工具換成模型的節點常被叫做 agent, 但只要它仍是一步一工具就沒問題——反過來,一個節點裡塞了整條流程,就是 mega agent,名字叫什麼都一樣。

檢查 1 — 任務切分是否為真

能否在程式碼中明確框出每個 Task 的起點與終點。

  • PASS:每步有獨立、可定位的程式邊界,邏輯不與前後步驟混雜。
  • FAIL:步驟邏輯互相黏連,框不出單一步驟的範圍。
  • 試金石:能否將任一單一 Task 抽離、餵固定 input 獨立執行?無法在不啟動整條管線的情況下單跑某步 → FAIL。

檢查 2 — 步驟間是否有明確的 input / output 契約

步驟之間傳遞的資料是否有定義好的結構(schema / 型別 / 明確介面)。

  • PASS:每步輸入輸出結構明確且可驗證。
  • FAIL:所有步驟讀寫同一個大的共享狀態 / context,無誰給誰什麼的契約(黑板式共享狀態)。

分野:共用狀態本身不是問題,「無契約」才是。 上面那條 FAIL 的關鍵字是無誰給誰什麼的契約。 一份被具名邊與宣告式所有權約束的共用狀態,照這條規則寫法就是 PASS。判準是這三件事同時成立:

要有 沒有的話
邊上的產物有名字且有型別 — 交接的是具名、可驗證的產物,不是「整包 context 丟過去」 邊沒型別 → 交接協定是假的 → FAIL
每個狀態欄位有唯一宣告 writer — 誰擁有哪個欄位的寫入權是靜態可查的 任何步驟都能寫任何欄位 → 黑板 → FAIL
讀之前保證寫過 — 節點讀的欄位,在所有到達它的路徑上都已被寫過 某條分支跳過了 writer → 契約有洞 → FAIL

驗證方式:要求對方指出宣告在哪(哪個檔案、哪一行說了 owner 與型別)。 說不出來、只能說「大家都讀那個 dict」→ FAIL。若有靜態檢查器能在不執行的情況下判掉這三項 → PASS 的最強證據。 (agentic-sop-kit 的做法:reads/writes/schema_ref 宣告在 flow.json,lib/graph.py--plan 期判掉, 值仍只存在 artifact 裡、written_by 就是 artifact 的 produced_by——沒有第二份權威可以漂移。)

檢查 3 — 每步是否有明確且可程式化檢查的成功標準

步驟跑完後,是否有程式碼明確判定「這次是否成功」。這是最常被偷工、卻最該嚴查的一項,因為它是回退自我修復能否運作的前提。

  • PASS:每步結束後有可程式化的成功條件檢查,並依結果決定推進或回退。
  • FAIL:做完直接呼叫下一步而無驗證;或「成功」僅等於「沒丟出例外」。

Read the full file on GitHub · 130 lines

Changes

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.

  1. 3d ago Changed · +45 lines · +44 tokens per session a09da1149559
  2. 12d ago First seen · 85 lines · 144 tokens per session scan A 672eeefcebf4

Subscribe to this mod's changes

agentic-workflow-audit is a skill published in the GitHub repository s0912758806p/agentic-sop-to-work (208 stars, last pushed 4d ago), licensed MIT. It adds 188 tokens to every session and 3,317 once invoked, about $0.0009 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.

Related

Other skills, from other repositories

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.

KtKID/x-dev-pipeline · 255 tokens

x-spec2

A compact system-design guide for turning vague or cross-module requests into a small, structured specification package. It defines requirements, acceptance scenarios, module boundaries, and—when needed—data flow, state, timing, resources, or recovery design.

KtKID/x-dev-pipeline · 397 tokens

x-qdev

A compact development workflow for a small, clearly defined code change. It keeps the requirement, initially failing tests, implementation, and real verification results in one task document, following TDD, or test-driven development.

KtKID/x-dev-pipeline · 116 tokens

x-adversarial-risk

A focused adversarial review of a software specification. It tries to find small counterexamples that would expose incorrect implementations, such as invalid state changes, crashes, duplicate actions, permission mistakes, or concurrent events.

KtKID/x-dev-pipeline · 85 tokens

coordination-audit

Produce a structured organizational diagnostic that quantifies time spent on specification vs coordination vs execution, saved as a persistent audit artifact to $HOME/.ai-first-kit/. Conducts a guided 5-question interview, classifies every workflow structure by actual function, and identifies highest-ROI automation…

synaptiai/synapti-marketplace · 182 tokens

engagement-scoping

Resolve the documentation engagement scope from the settings cascade — project identity, source roots, output root, delivery mode, action ceiling, confidentiality default, and the exact file set this run may touch — and freeze it to /00-control/.scope.json. Use when any /dossier: command starts, when the delivery mode…

synaptiai/synapti-marketplace · 135 tokens