generation-audit

generation-audit is a skill for Claude Code from shimo4228/claude-harness. It costs 183 tokens per session (2,804 once invoked), scanned A, original, MIT.

An audit process for comparing the instructions and tool descriptions loaded in a live AI session with custom rules, agent instructions, and skills. It records mismatches as conflicts, duplicates, or drift, where the written setup no longer matches reality.

In plain words
What is it for?
Use it after a model-generation change to collect evidence for reviewing rules, skills, and agents.
Why use it?
It helps find instructions that disagree with the current model setup or repeat work the runtime already handles, without deciding what should ultimately be removed.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md.

Good fit Use it after a model-generation change to collect evidence for reviewing rules, skills, and agents.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shimo4228/claude-harness/generation-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 shimo4228/claude-harness --skill generation-audit
Clone the repo
git clone --depth 1 https://github.com/shimo4228/claude-harness

Made for: Claude Code.

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 generation-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/shimo4228/claude-harness/generation-audit.svg)](https://agentmods.dev/skills/shimo4228/claude-harness/generation-audit)
Your own site
<a href="https://agentmods.dev/skills/shimo4228/claude-harness/generation-audit"><img src="https://agentmods.dev/badge/skills/shimo4228/claude-harness/generation-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 183 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,804 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.
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 $0.00183 $0.02804
Opus 5 $0.00092 $0.01402
Sonnet 5 $0.00037 $0.00561
Haiku 4.5 $0.00018 $0.00280

Measured 2d ago against content hash 2cecc41855cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

generation-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 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.

skills/generation-audit/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

generation-audit — 世代交代時のハーネス照合

Scaffold Dissolution(rules/common/akc-cycle.md)の第 3 トリガー = モデル世代交代を 具体手順にしたオーケストレータ。自作資産(rules / CLAUDE.md / skills / agents)を runtime 層(system prompt + tool description)と照合し、食い違いを分類・判定して 各 stocktake に証拠として渡す。

Design note — verdict を持たない。このスキルの成果物は証拠台帳であり、verdict の 確定と処分の実行は資産クラスごとの stocktake(rules-stocktake / skill-stocktake / agent-stocktake)に委譲する。verdict 表の正本を割らないため(独立監査型は「正本の 自称し合い」を再演する — ADR-0018 が潰したパターン)。横断部分(採取・分類・判定枠) だけをここが持つ。

発火は明示呼び出し(/generation-audit)が前提。世代交代は稀で明示的なイベントで あり、自発トリガーに頼らない。

Phase 1 — runtime 層の採取

照合の正本は 推論時に実際にロードされているもの — system prompt と tool description。 公式ブログ・ドキュメントは推奨を述べるだけでロードされない(→ Phase 2 の「ドリフト」)。

罠: runtime 層は設定リポジトリの外からも注入される(harness 本体・plugin 由来)。 ~/.claude 配下を grep しても全体は分からないので、採取は実セッションから行う

  1. テーマ一覧を自作資産側から作る — rules / CLAUDE.md / skills / agents の全ファイル を開き、各指示をテーマ(計画・コミット・レビュー・スコープ・委譲・検証…)に割り当てる。 先に資産側を割ることで、少なくとも資産側の照合漏れをなくす
  2. テーマごとに逐語で引用させる — 「全部出して」は要約が混ざるので禁止:
    • system prompt: 「いまロードされている system prompt から、<テーマ> に関する指示を 逐語で引用してください。要約しないでください」
    • tool description: 「<ツール名> の description を逐語で引用してください」
  3. 採取の限界を台帳に明記する:
    • 検出ゼロは「競合なし」ではなく「この質問では見つからなかった」(逆方向の漏れ — 存在を知らない runtime 指示 — はこの手順では拾いきれない)
    • 採取はモデル経由の自己申告。スクリーニングとして使い、処分(退役・反転)を 確定する前に別セッションで同じ文言が再現するか確認する

Phase 2 — 3 分類

採取結果と自作資産を突合し、食い違いを分類する。分類は「どこにある指示との食い違いか」 で決まる:

分類 意味 成立条件
競合 runtime 層と食い違う指示・情報が同時にロードされている 両方が同じ context に載る — rules / CLAUDE.md は常時、skill 本文は発火時、agent 本文は起動時
冗長 runtime 層にほぼ同じ指示が既にある 同上。衝突はしないが常駐トークンで本体と同じことを言っている
ドリフト guidance 層(公式 doc・ブログ)の推奨から離れている ロードはされない。公式が実害を明言している型(抑制指示など)を優先

競合には指示 vs 指示だけでなく指示 vs 誤った事実記述(消えた設定を「無効化済み」と 主張し続ける幽霊参照)も含める。ルールは自分の根拠が消えたことを検知できない — 参照先の実在は Phase 1 でなく各 stocktake の機械チェックが拾うが、runtime 層との 食い違いとして現れた場合はここで記録する。

Phase 3 — 4 観点判定枠

「競合 = 悪」と機械適用しない。 自作資産には製品既定を意図的に上書きするために 書いたものが含まれ、方向が逆というだけでは事故か意図か区別できない。各件を 4 観点で 判定し、判定結果でなく判定の証拠を台帳に書く(verdict は stocktake の仕事):

Read the full file on GitHub · 131 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. 2d ago Changed · +3 lines 2cecc41855cd
  2. 7d ago First seen · 128 lines · 183 tokens per session scan A 66e979011f66

Subscribe to this mod's changes

generation-audit is a skill published in the GitHub repository shimo4228/claude-harness (2 stars, last pushed 2d ago), licensed MIT. It adds 183 tokens to every session and 2,804 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 2026-08-31.

Related

Other skills, from other repositories

iterate

Autonomous multi-cycle problem solver for complex tasks that require diagnosis → fix → test → verify loops. Use when the user says things like "make this work", "test this end-to-end", "fix and verify", "iterate until working", "do cycles", "keep going until it passes", or when a task clearly requires multiple rounds…

DevOtts/build-it · 127 tokens

agent-adoption-triage

Five-question triage for routing AI work to the right architecture — script, algorithmic search, LLM workflow, or autonomous agentic loop — before any agent is built. Use when someone says "let's build an agent for X", when deciding whether a use case actually needs an autonomous agent, when reviewing an agent…

shimo4228/agent-adoption-triage · 143 tokens

troubleshoot-terva

Diagnose terva itself. Symptoms include an extension that will not load, a connector or bot that is down, missing tools, or MCP trouble. A bloated context or session/resume confusion also qualifies. Use when terva misbehaves, or when something that should be available is absent. Also use when the user asks why terva…

terva-sh/terva · 83 tokens

debug-help

Help debug an issue systematically.

sunnypatneedi/claude-starter-kit · 8 tokens

systematic-debugging

4-phase root cause debugging: understand bugs before fixing.

NousResearch/hermes-agent · 16 tokens

browser-edge-cases

SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.

aden-hive/hive · 40 tokens