Borrowing it
Nothing to install: this file belongs to kazuph/yunomi. 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/kazuph/yunomi/main/CLAUDE.mdgit clone --depth 1 https://github.com/kazuph/yunomiWrote 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/kazuph/yunomi/claude-md)<a href="https://agentmods.dev/instructions/kazuph/yunomi/claude-md"><img src="https://agentmods.dev/badge/instructions/kazuph/yunomi/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/kazuph/yunomi/claude-md"><img src="https://agentmods.dev/badge/instructions/kazuph/yunomi/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 | $0.02577 | $0.02577 |
| Opus 5.5 | $0.01031 | $0.01031 |
| Sonnet 5.5 | $0.00515 | $0.00515 |
| Haiku 4.5 | $0.00258 | $0.00258 |
Grade A, and why
yunomi CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
yunomi プロジェクト固有ルール
開発・テスト時のサーバー起動
yunomiを起動する前に通知経路を実行時に取得・検証する。IKESU_PANE_ID または ikesu pane current で ikesu を先に確かめ、次に Herdr、次に検証済みtmux adapterを評価する。
PANE_ID="$(printenv IKESU_PANE_ID || true)"
if [ -z "$PANE_ID" ] && command -v ikesu >/dev/null 2>&1; then
if PANE_ID="$(ikesu pane current 2>/dev/null | jq -er '.result.pane.pane_id')"; then :; else PANE_ID=""; fi
fi
if [ -n "$PANE_ID" ]; then
ikesu pane get "$PANE_ID" >/dev/null 2>&1 || exit 1
YUNOMI_ROUTE=ikesu
else
PANE_ID="$(printenv HERDR_PANE_ID || true)"
if [ -z "$PANE_ID" ] && command -v herdr >/dev/null 2>&1; then
if PANE_ID="$(herdr pane current 2>/dev/null | jq -er '.result.pane.pane_id')"; then :; else PANE_ID=""; fi
fi
if [ -n "$PANE_ID" ]; then
herdr pane get "$PANE_ID" >/dev/null 2>&1 || exit 1
YUNOMI_ROUTE=herdr
elif [ -n "$(printenv TMUX || true)" ] && [ -n "$(printenv TMUX_PANE || true)" ] && [ -n "$(printenv YUNOMI_NOTIFY_CMD || true)" ]; then
TMUX_PANE_ID="$(printenv TMUX_PANE)"
test "$(tmux display-message -p -t "$TMUX_PANE_ID" '#{pane_id}')" = "$TMUX_PANE_ID" || exit 1
YUNOMI_ROUTE=tmux
else
echo "no proven yunomi notification route" >&2
exit 1
fi
fi
- ikesu経路では
--loop --notify-ikesu-pane "$PANE_ID"を必ず指定する。Codexはikesu run --label yunomi --cwd /absolute/path/to/repo -- npx yunomi REPORT.md --loop --notify-ikesu-pane "$PANE_ID"、Claude Codeは同じyunomi引数でrun_in_background: trueを使う。Codexはジョブ終了後にikesu log <job>を読む。Claude Codeは起動したBashバックグラウンドタスクの出力を読む。 - ikesuは
ikesu agent prompt、部屋指定時はikesu send <pane> <text> --room R。古い版向け代替送信はしない。--notify-roomは実際に送るHerdr/ikesu全側の対応を起動前に確認する。 - 引数なしの
IKESU_PANE_IDはikesuのみを選び、漏れたHerdr/tmux環境を無視する。明示引数があればikesu環境を追加せず、従来のHerdr/tmux環境規則を保つ。YUNOMI_NOTIFY_CMDは全経路に優先し1回だけ実行する。 - Herdr経路の書込み可能レビューは、自分で確認する場合もユーザーにレビューさせる場合も、必ず
--loop --notify-pane "$PANE_ID"を付ける。 - 純tmux経路は、事前検証済みの
YUNOMI_NOTIFY_CMDが設定されている場合だけ--loopで起動する。yunomi shareはread-only例外。 - Claude CodeはBashツールの
run_in_background: trueで起動し、exitを検知する。 - Herdr経路で
--notify-paneが無い起動、通知経路を実行時に証明できない起動、記憶やfocused paneから通知先を推測する起動は禁止。 - 通知先を証明できない場合は、yunomiを起動せずfail closedで報告する。
--notify-paneはHerdr pane専用。tmuxの%paneを渡さず、その場でrawtmux send-keysfallbackを作らない。Herdrが使えない純tmux環境は、安全なキュー配送と到達性を事前検証済みのYUNOMI_NOTIFY_CMDがある場合だけ--loopで起動し、それ以外はfail closedにする。- ユーザーが「開いて」と明示した場合は、最終ビルドを使うサーバーの
healthzと対象UIを確認してから、macOSのopen http://127.0.0.1:<port>/で操作可能な画面を開き、ユーザーの確認が終わるまでサーバーを維持する。スクリーンショットだけを開いて代用してはいけない。明示依頼がない自動起動では、yunomi自身のブラウザ起動を使ってよい。
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.
- 2d ago Changed · +16 lines · +521 tokens per session af4b947061b6
- 1mo ago Changed · -1 lines · -21 tokens per session f011622110c6
- 1mo ago First seen · 124 lines · 2,077 tokens per session scan A aafbbbffc3ee
yunomi CLAUDE.md is an instructions file published in the GitHub repository kazuph/yunomi (21 stars, last pushed 2d ago), licensed MIT. It adds 2,577 tokens to every session, about $0.0103 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 2026-08-30.
Other instructions, from other repositories
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.