Borrowing it
Nothing to install: this file belongs to suisya-systems/claude-org-ja. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/suisya-systems/claude-org-ja/main/.claude/skills/skill-audit/SKILL.mdgit clone --depth 1 https://github.com/suisya-systems/claude-org-jaWrote 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/suisya-systems/claude-org-ja/skill-audit)<a href="https://agentmods.dev/skills/suisya-systems/claude-org-ja/skill-audit"><img src="https://agentmods.dev/badge/skills/suisya-systems/claude-org-ja/skill-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.
<a href="https://agentmods.dev/skills/suisya-systems/claude-org-ja/skill-audit"><img src="https://agentmods.dev/badge/skills/suisya-systems/claude-org-ja/skill-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 52 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 69 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- medium Agent Snooping · line 52 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 69 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00123 | $0.04351 |
| Opus 5 | $0.00062 | $0.02176 |
| Sonnet 5 | $0.00025 | $0.00870 |
| Haiku 4.5 | $0.00012 | $0.00435 |
Grade A, and why
skill-audit scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Enumerates other installed skillslowAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
work_skill_count=$(find .claude/skills -maxdepth 2 -name SKILL.md \ Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
skill-audit: skill 棚卸し
skill 数の増加に伴って org-delegate の work-skill 検索にノイズが増えるのを防ぐため、
定期的ではなく 状態ベースで棚卸しを行う。
skill 数増加そのものよりも「検索面のノイズ」が本丸。 本スキルは 3 つの観点（廃止 / 重複統合 / owner 明記）を機械的にチェックし、 変更提案を窓口 Claude にまとめて送る。自動で skill を削除・変更することはしない。
輸送層（transport）両系 — 既定
broker/ opt-inrenga: 本ファイル（および各スキル）の peer message・pane 操作はmcp__org-broker__*で書いてあり、ORG_TRANSPORT無設定＝既定brokerではそのまま従えばよい。ORG_TRANSPORT=renga（opt-in、切戻し可）では MCP サーバー名がrenga-peersになり、完全修飾名がmcp__org-broker__*→mcp__renga-peers__*に機械置換される（引数形・セマンティクスは同一なので操作の論理は変わらない）。輸送依存で手順が変わる差は次の 3 点:
- 受信モデル（既定 = push 一次 =
claude/channel/ pull フォールバック）: 既定 broker は push 一次に設計されている（runtime push-first 0.1.24+、設計 SoT は transport-labdocs/design/broker-native-roles.md§9）: 各ペイン同居の channel sidecar（server:org-broker-channel）が broker キューを ~1 秒間隔で claim→push し、notifications/claude/channelで本文を idle セッションへ注入する（「受けたら即応答」契機が生まれる）。ワーカー ack（to_id="worker-{task_id}"）・retro gate ack（to_id="dispatcher"）・ディスパッチャー handover 経路のsend_message/check_messages/send_keys/inspect_paneは同じツール名（mcp__org-broker__*）で動く。pull はフォールバック層: sidecar 不在 / unhealthy（heartbeat timeout でdelivery_mode=PULL）/ channel 非対応ペイン（codex pull-peer）/ claude.ai login 不在時は、各役割が自身の cadence で能動的にcheck_messagesする（役割別 cadence: worker=ターン境界 / 完了後 bounded/loop・dispatcher=/loop 3m・secretary=ターン冒頭。「ナッジを見たらcheck_messages」prose は撤回せずこの fallback cadence として読む）。ORG_TRANSPORT=renga（opt-in）では、ワーカー報告・ディスパッチャー応答が<channel source="renga-peers" …>として in-band で push される（renga の in-band push と broker push 一次は同じ即応契機）。契約面は Surface 8 + push-primary amendment で push 一次が ratified 済み（2026-06-15、S3。pull は fallback として retain・renga 不変）。- spawn 儀式（既定 = folder-trust 承認 + dev-channel sidecar 承認の 2 段）: 子ペイン起動時、既定 broker は
--mcp-config <broker>を注入し Claude Code の folder-trust プロンプトをsend_keys(enter=true)で機械承認するのに加えて、push 一次のため channel sidecar を--dangerously-load-development-channels server:org-broker-channelで load し dev-channel 承認プロンプト（spawn-flow 3-3b）をsend_keys(enter=true)で機械承認する（folder-trust + dev-channel の 2 段承認。詳細は.dispatcher/references/spawn-flow.md3-2 / 3-3b、設計は broker-native-roles.md §9.5）。ORG_TRANSPORT=renga（opt-in）では--dangerously-load-development-channels server:renga-peersを注入し「Load development channel?」を Enter 承認する 1 段。注: attention watcher は transport 非依存の CLI ペインであり、folder-trust / dev-channel いずれの 2 段承認の対象外（spawn 儀式の反転に巻き込まない）。- エラー分岐（既定 = broker 拡張コード込み）: 既定 broker は shared codes（
pane_not_found/last_pane/invalid-params、Surface 6）に加え broker 固有[token_invalid]/[session_invalid]/[tool_not_authorized]/[no_backend]（= adapter_unavailable）/[nudge_failed]/[peer_not_found]/[name_taken]/[unknown_tool]を返しうる（未知コードは default-branch で escalate）。ORG_TRANSPORT=renga時は broker 固有コードは発生せず shared codes + renga 固有コードのみ。契約面の正本は
docs/contracts/backend-interface-contract.mdSurface 8（broker auth & delivery、ratified 2026-06-14）+ 末尾「Ratified amendment (2026-06-15): push-primary delivery」（S3。broker push 一次が既定の契約、pull は structural fallback として retain）、設計 SoT は transport-labdocs/design/broker-native-roles.md§9（push 一次）/docs/design/ja-migration-plan.md§5・§8。opt-inrengaは削除せず常時有効な fallback として維持する（切戻しの安全装置）。broker 実走（dogfood）は Epic #6 Issue G スコープであり、本ファイルの既定運用経路ではない（既定の二フレーム注記（Refs #604）: ここでの「既定broker」はコード既定フレーム —tools/transport.py: DEFAULT_TRANSPORTが runtime 0.1.28 (Epic #586) でbrokerにフリップ済みで、ja 生成器・transport.resolve()はこのコードフレームで render するため生成面はこう表示する。別に運用既定フレームがあり、broker 実走 dogfood が Epic #6 Issue G まで未活性のため運用上の既定経路はrenga。両フレームは指す対象（コード定数 vs 運用経路）が異なり矛盾しない。総説は rootCLAUDE.md「輸送層（transport）両系」節。）
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 168 lines · 123 tokens per session scan A 95f4d1b0690e
skill-audit is a skill published in the GitHub repository suisya-systems/claude-org-ja (5 stars, last pushed 4d ago), licensed MIT. It adds 123 tokens to every session and 4,351 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
takt
A workflow engine that runs a task through a sequence of steps defined in a YAML file, using separate coding agents for the work.
takt
A workflow engine for coordinating multiple coding agents. It reads a YAML workflow, a text configuration format, and moves agents through its defined steps and rules.
company-product-context
Compiles comprehensive company product context from PDF documents, web research, and industry knowledge.
codebase-context-extractor
This skill provides a comprehensive context extraction system for large codebases. It intelligently analyzes code structure, dependencies, and relationships to extract relevant context for understanding, debugging, or modifying code.
skill-creator
Generates Anthropic Skills with complete workflow including GitHub PR creation and local download verification.
Research Synthesis Workflow
A step-by-step guide to synthesizing research from multiple sources into a coherent summary.