Borrowing it
Nothing to install: this file belongs to YasuakiOmokawa/oura-mcp. 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/YasuakiOmokawa/oura-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/YasuakiOmokawa/oura-mcpWrote 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/yasuakiomokawa/oura-mcp/claude-md)<a href="https://agentmods.dev/instructions/yasuakiomokawa/oura-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/yasuakiomokawa/oura-mcp/claude-md/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/instructions/yasuakiomokawa/oura-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/yasuakiomokawa/oura-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00740 | $0.00740 |
| Opus 5.5 | $0.00296 | $0.00296 |
| Sonnet 5.5 | $0.00148 | $0.00148 |
| Haiku 4.5 | $0.00074 | $0.00074 |
Grade A, and why
oura-mcp 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 2mo 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.
What it actually says
oura-mcp プロジェクトルール
詳細ルールは .claude/rules/*.md に paths-scoped で分離。該当ファイルを編集する時に自動で読み込まれる。
| rule | 発火条件 |
|---|---|
no-class-syntax.md |
src/ test/ scripts/ の *.ts 編集時 |
mcp-sdk.md |
src/index.ts src/mcp/ 編集時 |
release.md |
.changeset/ CHANGELOG.md package.json 編集時 |
言語
コメント・ドキュメントは 英語 で書く。例外: CLAUDE.md と .claude/rules/*.md のみ日本語可（人間が読みやすさ優先）。changeset 本文も英語。
命名
- factory 関数:
create*（例:createAuthManager,createFileTokenStore） - ステートレス処理: 動詞ベース（例:
buildAuthorizeUrl,exchangeCode,refreshTokens） - 型: PascalCase の
type（interfaceではなくtype統一）
TypeScript 編集後のチェック
lint は biome (npm run lint:fix)。user global rule の yarn eslint は適用外（biome を使うため）。
ハマりどころメモ
bot 作成 PR は CI が走らない（GITHUB_TOKEN の anti-recursion）
changesets/action/peter-evans/create-pull-request等が GITHUB_TOKEN で作る PR にはpull_requestトリガーの ci.yml が fire しない- 回避策:
- 暫定: bot PR ブランチに空コミットを手動 push（
git commit --allow-empty -m "trigger ci" && git push） - 恒久: secrets に PAT を登録、action の env で
GITHUB_TOKEN: ${{ secrets.PAT }}を上書き
- 暫定: bot PR ブランチに空コミットを手動 push（
- 理由: GitHub の anti-recursion 仕様で default 無効、設定で変えられない。branch protection で必須 status checks が設定済みだと bot PR がマージできず詰まる
自分の PR を merge する時は --admin --squash
- main の branch protection は
required_approving_review_count: 1+enforce_admins: false - 自分の PR は self-approve 不可なので、
gh pr merge --auto --squashで予約してもmergeStateStatus: BLOCKEDで fire しない（auto-merge は admin bypass しない仕様） - 自分の PR は CI 通過を確認してから
gh pr merge --admin --squash <num>で merge する（admin bypass で要件無視） - bot PR の扱い:
- release PR（changesets/action）:
release.yml内でgithub-actions[bot]が auto-approve するため止まらない - Dependabot PR / その他: 手動で
gh pr review --approve <num>してから merge
- release PR（changesets/action）:
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.
- 2mo ago First seen · 41 lines · 740 tokens per session scan A 30f237fb4381
oura-mcp CLAUDE.md is an instructions file published in the GitHub repository YasuakiOmokawa/oura-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 740 tokens to every session, about $0.0030 per session on Opus 5.5. 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.
oura-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| oura-mcp CLAUDE.mdYasuakiOmokawa/oura-mcp | Instructions file | 1 | 2mo ago | MIT | A | 740 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |