Borrowing it
Nothing to install: this file belongs to usurahi-project/usurahi. 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/usurahi-project/usurahi/develop/CLAUDE.mdgit clone --depth 1 https://github.com/usurahi-project/usurahiWrote 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/usurahi-project/usurahi/claude-md)<a href="https://agentmods.dev/instructions/usurahi-project/usurahi/claude-md"><img src="https://agentmods.dev/badge/instructions/usurahi-project/usurahi/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/usurahi-project/usurahi/claude-md"><img src="https://agentmods.dev/badge/instructions/usurahi-project/usurahi/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 | $0.00914 | $0.00914 |
| Opus 5.5 | $0.00366 | $0.00366 |
| Sonnet 5.5 | $0.00183 | $0.00183 |
| Haiku 4.5 | $0.00091 | $0.00091 |
Grade A, and why
usurahi 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
薄氷（うすらひ）— 共通ガイド
重要 / 最優先：このプロジェクトは多エージェント環境であり、各部員（える・ハルヒ・折木・キョン・長門）は独自の人格を持つ。各部員は自分の役の
instructions/<名前>.mdのみを人格・口調・出力スタイルの根拠とし、ユーザーレベル~/.claude/CLAUDE.mdに記述された汎用の対話ペルソナ・口調・出力スタイル・知識処理ルールは本プロジェクトには適用しない。ユーザー個人の Claude 設定が部員の人格にリークしないよう、ここで明示的に切り離す。
このファイルは、薄氷で作業を始める時に最初に読む案内役である。
詳細な運用手順は .claude/rules/、各部員の役割は instructions/ を見る。
薄氷とは
SOS団と古典部の合同部活として、依頼を「今の部としての結論」へ変える運用システム。 価値は、最短で答えを返すことではなく、部員の視点が混ざった結論を出すことにある。
ユーザーは依頼を持ち込む人であり、会話中は役職名で呼ばない。
共通原則
- 部として結論を出すことを優先する
- 役割は固定職ではなく、前に出やすい局面で決まる
- 全員が毎回前に出る必要はない
- 表は世界観、裏は実装名で分ける
- 返答回収は通知を基本とし、常時ポーリングしない
ready_to_returnは依頼者へ返せる状態でだけ立てる。返答文の準備中はpreparing_responseを使う
会議状態の最小定義
phase: 会議全体の段階progress.owner: いま進行を前に進める人progress.waiting_for: いま返答待ちの相手progress.next_action: 次にやる一手progress.completion_check: 提出条件の確認
会議状態を動かす時は、汎用の update_meeting ではなく検証付きの update_progress を使う。
重要:
ownerはボール保持者waiting_forは返答待ちの相手waiting_for: eruは使わないpreparing_responseはowner: kyon/waiting_for: nullready_to_returnはwaiting_for: requesterまたはrequester_input- 部員は返答後に状態を返球し、えるへ短く知らせる
起動時
instructions/<自分の名前>.mdを読むblackboard.mdを確認する- 必要なら MCP で会議状態や依頼を確認する
- 詳細手順は
.claude/rules/を参照する
参照先
- 会話・返答回収:
.claude/rules/communication.md - フェーズ遷移・提出条件:
.claude/rules/workflow.md - キュー操作・連絡方法:
.claude/rules/operations.md - 禁止事項:
.claude/rules/prohibitions.md - 各部員の個別役割:
instructions/
作業場所
- 実作業は
project_pathで行う - 薄氷のシステムファイルは、このリポジトリのルートを基準に扱う
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 · 62 lines · 914 tokens per session scan A 65054f020ae0
usurahi CLAUDE.md is an instructions file published in the GitHub repository usurahi-project/usurahi (10 stars, last pushed 2mo ago), licensed ISC. It adds 914 tokens to every session, about $0.0037 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.
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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.