What is usurahi CLAUDE.md?

A project instruction file for an AI coding team working on usurahi, a system that turns requests into shared decisions among multiple named agents. It defines their roles, meeting states, workflow, and communication rules.

Use it as the starting guide when an agent joins the project, updates meeting progress, coordinates the team, or prepares a decision for the requester.

It gives every agent the same project-specific operating rules and prevents inconsistent handling of ownership, waiting states, and final responses.

usurahi CLAUDE.md — Instructions file for Claude Code by usurahi-project: A project instruction file for an AI coding team…

Install

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.

agentmods

npx agentmods add instructions/usurahi-project/usurahi/claude-md

Clone the repo

git clone --depth 1 https://github.com/usurahi-project/usurahi

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/usurahi-project/usurahi/claude-md.svg)](https://agentmods.dev/instructions/usurahi-project/usurahi/claude-md)

Your own site

<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="Measured on agentmods" height="20"></a>

Per session 914 This file is loaded in full into every session.

When invoked 914 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00457	$0.00457
Sonnet 5	$0.00183	$0.00183
Haiku 4.5	$0.00091	$0.00091

Measured 6d ago against content hash 65054f020ae0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 6d 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.

CLAUDE.md · 62 lines

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: null
ready_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

Changes

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.

6d ago First seen · 62 lines · 914 tokens per session scan A 65054f020ae0

Subscribe to this mod's changes

usurahi CLAUDE.md is an instructions file published in the GitHub repository usurahi-project/usurahi (10 stars, last pushed 13d ago), licensed ISC. It adds 914 tokens to every session, about $0.0046 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 2026-08-31.

Building agents Multi-Agent claude-code mcp obsidian tmux workflow

usurahi CLAUDE.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

薄氷（うすらひ）— 共通ガイド

薄氷とは

共通原則

会議状態の最小定義

起動時

参照先

作業場所

What this file has done since we first saw it

Other instructions, from other repositories

vnx-orchestration CLAUDE.md

WorkFlowX CLAUDE.md

WorkFlowX AGENTS.md

phd-deepread-workflow CLAUDE.md

agentcrew-dev-skills AGENTS.md

markdown-agent-vault-ru AGENTS.md