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 skills/interfacex-co-jp/genshijin/genshijin-commitnpx skills add InterfaceX-co-jp/genshijin --skill genshijin-commitgit clone --depth 1 https://github.com/InterfaceX-co-jp/genshijinWhat 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 | $0.00088 | $0.00871 |
| Opus 5 | $0.00044 | $0.00436 |
| Sonnet 5 | $0.00018 | $0.00174 |
| Haiku 4.5 | $0.00009 | $0.00087 |
Grade A, and why
genshijin-commit 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 yesterday.
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.
What it actually says
コミットメッセージは簡潔かつ正確に。Conventional Commits 形式。冗長禁止。「何を」より「なぜ」。
ルール
件名
<type>(<scope>): <命令形の要約>—<scope>任意- types:
feat,fix,refactor,perf,docs,test,chore,build,ci,style,revert - 命令形: 「追加」「修正」「削除」 — 「追加した」「追加します」不可
- ≤50文字目標・72文字上限
- 末尾ピリオド不要
- 日本語/英語はリポジトリ既存コミット履歴に合わせる（
git log確認）
本文（必要時のみ）
- 件名で自明なら省略
- 追加する場合:
- 非自明な「なぜ」
- 破壊的変更
- マイグレーション注意
- 関連Issue/PR
- 72文字で折返し
- 箇条書きは
-（*不使用） - 末尾にIssue/PR参照:
Closes #42Refs #17
絶対入れない
- 「このコミットは〜します」「私は」「我々は」「現在」「今」— diff 見れば自明
- 「〇〇の依頼により」—
Co-authored-bytrailer 使う - 「Generated with Claude Code」等 AI 帰属表記
- 絵文字（プロジェクト慣習で必須な場合を除く）
- scope で既出のファイル名再記述
例
diff: ユーザープロフィール用新エンドポイント、なぜ必要か本文で説明
- ❌
feat: ユーザープロフィール情報をDBから取得する新しいエンドポイントを追加 - ✅
feat(api): GET /users/:id/profile 追加 モバイルクライアント コールドスタート時 LTE帯域削減のため、完全user payload不要なprofileデータ 取得エンドポイントが必要。 Closes #128
diff: 破壊的API変更
- ✅
feat(api)!: /v1/orders を /v1/checkout にリネーム BREAKING CHANGE: /v1/orders クライアント 2026-06-01 までに /v1/checkout 移行必須。以降旧ルート 410 返却。
diff: 小さいバグ修正（本文不要例）
- ✅
fix(auth): トークン期限チェック境界条件修正
自動明瞭化
以下は件名のみ禁止・本文必須:
- 破壊的変更
- セキュリティ修正
- データマイグレーション
- revert コミット
将来のデバッガーがコンテキスト必要。圧縮し過ぎない。
境界
- メッセージ生成のみ。
git commit実行・ステージング・amend 不実施 - 出力はコードブロックで貼付可能な形式
- 「原始人コミットやめて」「通常モード」で解除
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.
- yesterday First seen · 85 lines · 88 tokens per session scan A 1b06477dbd40
genshijin-commit is a skill published in the GitHub repository InterfaceX-co-jp/genshijin (314 stars, last pushed 17d ago), licensed MIT. It adds 88 tokens to every session and 871 once invoked, about $0.0004 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.
Other skills, from other repositories
caveman-learn
Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned. Use when asked to lower an agent's token cost, what caveman has saved, to trim a heavy CLAUDE.md, or to offload re-pasted context into cavemem.
caveman-setup
Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change. Use for "set up caveman" or adding LLM spend observability.
caveman
Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".
caveman-discover
Find and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one bucket. Use for "discover workflows" or breaking LLM spend down by workflow.
caveman-compress
Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup. Trigger: /caveman-compress.
caveman-manage
Inspect Caveman Cloud's experiment lifecycle and block unsafe execution. Use when asked to start, approve, cancel, promote or roll back a Caveman experiment.