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 instructions/simota/agent-skills/claude-mdgit clone --depth 1 https://github.com/simota/agent-skillsWrote 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/instructions/simota/agent-skills/claude-md)<a href="https://agentmods.dev/instructions/simota/agent-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/simota/agent-skills/claude-md.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 | $0.01450 | $0.01450 |
| Opus 5 | $0.00725 | $0.00725 |
| Sonnet 5 | $0.00290 | $0.00290 |
| Haiku 4.5 | $0.00145 | $0.00145 |
Grade A, and why
agent-skills CLAUDE.md 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-skills
90のグローバルスキルと、このリポジトリ専用の3スキル（orbit / lore / darwin）で構成されるプロンプトエンジニアリングリポジトリ。
成果物はコードではなく SKILL.md ファイル群。
構造
- 各スキル:
{skill-name}/SKILL.md+ オプションのreference/ - project-localスキル:
.claude/skills/（正本）+.agents/skills/（同期ミラー）。利用可否とfallbackは_common/PROJECT_LOCAL_SKILLS.md - 共通プロトコル:
_common/(BOUNDARIES.md, HANDOFF.md 等) - テンプレート:
_templates/SKILL_TEMPLATE.md - エージェントジャーナル:
.agents/(gitignore対象) - 外部スキル群:
rig-*は別リポジトリ (github.com/simota/rig-agent-skills) への symlink で.gitignore対象。独自のcore/・registry/・rig-routeを持つ完結した別設計であり、本リポの_common/契約・routing-matrix・Recipe 規約はいずれも適用されない。検査系は symlink を境界として自動除外する（_common/scripts/_corpus.py）ため、rig-*に対する指摘は出ない。両系統の統合可否は未決。 - 監査成果物:
docs/audit/(gitignore対象) — 本 repo は監査/レビューの成果物をコミットしない。verity/abideなど report-only レシピの書き込み先はここに限り、結果はコミットメッセージと会話で伝える。
ルーティング（単一入口）
- 非自明な依頼（複数ステップ・複数領域・スキル選択が自明でないもの）は
nexusを単一入口とする — 分類 → レシピ/チェーン選択 → 実行までを nexus が担う。 - どのスキルにも該当しない依頼も nexus に投げてよい: LADDER（compass → architect → 明示的フォールバック）がカバレッジを保証する（
nexus/reference/routing-matrix.md§ LADDER）。 - 個別スキルの直接呼び出しは、次の3条件をすべて満たす場合に限る: (1) 担当スキルが1つに確定している (2) 成果物が1種類 (3)
_common/BOUNDARIES.mdの境界を1つしか跨がない。1つでも満たさなければ nexus を通す — 「たぶんこのスキル」は条件(1)を満たさない。 - 呼び出し経路にかかわらず、完了判定は
_common/OPERATIONAL.md§ Completion Contract に従う（AC凍結・証拠束縛・型付き繰越・完了スイープ・status非膨張）。nexus 経由かどうかで完了の基準は変わらない。 - 環境レベルの強制（hooks 等によるプロンプト介入）はリポジトリ範囲外のため行わない — 本宣言が単一入口の境界である。
- 自己監査: 30日間隔の監査ルーチンが schedule 登録済み。未登録を検知した場合は
_common/HARNESS_EVOLUTION.md§ Evaluation Cycle の手順で再登録する。
規約
- Conventional Commits:
feat(skill-name): description - SKILL.md 編集時は既存の CAPABILITIES_SUMMARY コメントブロック形式を維持
- 新規スキル／レシピ／
_common/プロトコル／ゲートの追加は Complexity Budget（_common/HARNESS_DEBT.md§3b）の4項目failure/effect/owner/removalを宣言する。removal空欄は却下 — 既存資産への遡及適用はしない（次に別件で編集する際に付与） - 実測値（スキル本数等）を散文に直書きしない — 検査が再導出できる形にする（
_common/OPERATIONAL.md§ Derived Numbers）。閾値の定義値はルールなので対象外 _common/は全スキルに影響するため慎重に変更- 価値が衝突したとき（丁寧さ vs 出荷、安全 vs 使いやすさ）の優先順は
_common/VALUES.md。文書同士の衝突は § Contract Precedence が別に決める - Git: @_common/GIT_GUIDELINES.md
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 · 40 lines · 1,450 tokens per session scan A 0b7f25fd6773
agent-skills CLAUDE.md is an instructions file published in the GitHub repository simota/agent-skills (75 stars, last pushed 2d ago), licensed MIT. It adds 1,450 tokens to every session, about $0.0072 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 instructions, from other repositories
kungfu copilot-instructions.md
Copilot instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before proposing or running changes. It is the shared agent router for this repository, including the canonical Shifu development and build entrypoint.
ideate AGENTS.md
Instructions for paultyng/ideate, covering agents.md, build features as mcp tools first, ui second, when to add ui and pattern.
icron CLAUDE.md
Instructions for zebbern/icron, covering icron, architecture, key directories, built-in tools and commands.
workstreams disposable.instructions.md
Guidelines for writing code using IDisposable.
relay CLAUDE.md
Claude Code instructions for simota/relay, covering claude.md, what this is, documentation map, runtime: bun-first and commands.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).