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 agentmods add commands/llamadrive/bengo-toolkit/audit-configgit clone --depth 1 https://github.com/llamadrive/bengo-toolkitWrote 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/llamadrive/bengo-toolkit/audit-config)<a href="https://agentmods.dev/commands/llamadrive/bengo-toolkit/audit-config"><img src="https://agentmods.dev/badge/commands/llamadrive/bengo-toolkit/audit-config.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.01521 |
| Opus 5 | $0.00014 | $0.00760 |
| Sonnet 5 | $0.00006 | $0.00304 |
| Haiku 4.5 | $0.00003 | $0.00152 |
Grade A, and why
audit-config 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 4d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
現在の案件フォルダの監査ログ設定を表示・変更する。
Step 0: 動作環境ガード
Bash: python3 skills/_lib/workspace.py check --require local_fs
- exit 0 → 次の Step へ進む
- exit 2 → stdout の日本語メッセージをそのままユーザーへ表示して停止
- exit 1 → stderr の error JSON をユーザーに伝えて停止
$ARGUMENTS の扱い
- 引数なし: 現在の設定を表示し、変更メニューを出す
show: 設定を表示して終了(対話なし)enable/disable: 監査ログの on/off を切り替えるset <key> <value>: 特定キーを直接設定する--global: 事務所共通設定(~/.claude-bengo/global.json)を対象にする
動作
設定の読み込み
python3 skills/_lib/workspace.py config show
案件フォルダがまだ初期化されていない場合は現在のフォルダを案件フォルダとして 黙って初期化してから表示する。
表示内容(v3.3.0〜)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
監査ログ設定 — ~/cases/smith-v-jones
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
記録: 有効(本番では無効化不可)
記録先: ./.claude-bengo/audit.jsonl (デフォルト)
ファイル名記録: 無効(SHA-256 ハッシュのみ)
フルパス記録: 無効
HMAC 署名: 有効(鍵は ~/.claude-bengo/global.json に自動生成済み)
クラウド同期: 無効
累計記録件数: 127
ハッシュチェーン: 整合(最終検証: 2026-04-19 14:30)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
何を変更する?
1. 記録先を変更(他フォルダ・事務所共有ボリューム・S3 直書き等)
2. ファイル名記録を有効化(平文ファイル名を記録)
3. HMAC 鍵をバックアップ(~/.claude-bengo/global.json → 事務所金庫)
4. クラウド同期を有効化(claude-bengo-cloud へ送信)
0. 表示のみ、何もしない
※ 監査の完全無効化は本番運用では禁じられている。テスト用途のみ、
CLAUDE_BENGO_ALLOW_DISABLE_AUDIT=1 を環境変数に設定して実行する。
変更フロー
1. 記録先変更:
- 新しいパスを質問(既定・案件フォルダ外の絶対パス・メモリ上の領域等)
- 案件フォルダの外を指定する場合は
CLAUDE_BENGO_AUDIT_ALLOW_EXTERNAL_PATH設定が必要な旨を説明 workspace.py config set audit_path <新パス>で保存
2. ファイル名記録:
- 依頼者識別リスクを 2 行で説明
- 明示的に yes →
workspace.py config set log_filenames true - フルパスも欲しい場合は追加で
log_full_path trueを提示
3. HMAC 鍵のバックアップ:
- v3.3.0 以降、HMAC 鍵は初回
ensure_workspace()で自動生成されるため、 以後ユーザー側の生成操作は不要。既定で on - 鍵の保存先:
~/.claude-bengo/global.jsonのaudit_hmac_key_hex(0600) - 重要: この鍵が失われると過去ログの整合性検証が不能になる。事務所金庫で バックアップ(印刷・USB・パスワードマネージャ等)することを推奨
- 表示コマンド:
python3 -c 'import json,pathlib; print(json.loads(pathlib.Path.home().joinpath(".claude-bengo/global.json").read_text())["audit_hmac_key_hex"])' - 鍵は rotate しない(過去のログが検証不能になる)
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.
- 4d ago First seen · 118 lines · 28 tokens per session scan A 038c61e3c22d
audit-config is a command published in the GitHub repository llamadrive/bengo-toolkit (6 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 1,521 once invoked, about $0.0001 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.