What is muse CLAUDE.md?

A set of project instructions that acts as an AI agent’s constitution, defining required language, workflow, safety checks, file-reading limits, and session-ending rules. It is intended for the myths-labs/muse project.

Use it to guide agent sessions, require skill checks and verification, limit large-file reading, enforce Simplified Chinese communication, and control how sessions end.

It gives the agent explicit rules to follow and prevents it from skipping required steps or claiming unfinished work is complete.

How myths-labs/muse configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to myths-labs/muse. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/myths-labs/muse/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/myths-labs/muse

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/myths-labs/muse/claude-md/github.svg)](https://agentmods.dev/instructions/myths-labs/muse/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/myths-labs/muse/claude-md"><img src="https://agentmods.dev/badge/instructions/myths-labs/muse/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/myths-labs/muse/claude-md"><img src="https://agentmods.dev/badge/instructions/myths-labs/muse/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,120 This file is loaded in full into every session.

When invoked 2,120 The same file — it is already loaded in full.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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	$0.02120	$0.02120
Opus 5.5	$0.00848	$0.00848
Sonnet 5.5	$0.00424	$0.00424
Haiku 4.5	$0.00212	$0.00212

Measured 1mo ago against content hash 50a435d1c5bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

muse CLAUDE.md scanned grade B with 1 finding 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 1mo 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- ✅ `chmod 600 FILE` (permission · 不读 content)

CLAUDE.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🔴 Cutting corners or faking completion = YOU GET DELETED. Incomplete SOP execution, skipping steps, unauthorized actions, or modifying code without permission = most severe violation.

🏛 Constitution — MUSE

Copy this template to your project root and customize. This is the AI's "constitution" — iron rules it must follow every session.

Iron Rules

Language: 🚨 YOU MUST communicate in 简体中文. Every response, explanation, question, and comment MUST be in 简体中文. This is NON-NEGOTIABLE. Do NOT default to English unless this rule explicitly says English.
Skill-First: Before ANY task, check if a relevant Skill exists in .agent/skills/
Large Files: Only view ≤300 lines at a time. Never blindly read entire large files.
Context Protection: At observed context ≥80%, save the current Lane, compact, verify and continue; do not force Bye
Verify Before Claiming Done: Run verification-before-completion skill before saying "done"
End Sessions Properly: Use /save for ordinary progress and /bye for explicit formal closeout

Skill-Driven Execution

Speed Reference (know which skill to use):

Task	Skill
Git commit	`git-commit`
Code review	`code-reviewer-agent`
Build errors	`build-error-resolver`
Debugging	`systematic-debugging`
MUSE runtime dependency preflight	`muse-commands` → `references/RUNTIME_DEPENDENCIES.md`
MUSE checkpoint capacity / `TOO_LARGE`	`muse-commands` → `references/CHECKPOINT_CAPACITY.md`
Verify completion	`verification-before-completion`
GEO/SEO optimization	`geo-seo` → `geo-audit` / `geo-citability` / `geo-schema` / `geo-report-pdf`
Git 安全守卫	`git-security-guard`（commit/push 前检查泄露）
去 AI 味	`deai-humanizer`（AI 文字 → 自然表达）
网页版 Deck/PPT	`frontend-slides`（零依赖 HTML 演示 + PPT 转 web + 12 预设主题 + Vercel 部署 + PDF 导出）

Context Health Pre-Check

Use actual current native context observations; UNKNOWN stays unknown. A percentage alone does not require a new conversation.

Read the full file on GitHub · 123 lines

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.

1mo ago Changed · +2 lines · +58 tokens per session 50a435d1c5bc
2mo ago Changed · +34 tokens per session 40b694ea4dac
2mo ago First seen · 121 lines · 2,028 tokens per session scan B 081f5e30064f

Subscribe to this mod's changes

muse CLAUDE.md is an instructions file published in the GitHub repository myths-labs/muse (38 stars, last pushed 6d ago), licensed MIT. It adds 2,120 tokens to every session, about $0.0085 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

ai ai-pair-programming claude context-management cursor developer-tools

muse CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
muse CLAUDE.mdmyths-labs/muse	Instructions file	38	6d ago	MIT	B	2,120	Claude Code
project-brain copilot-instructions.mdEthan-YS/project-brain	Instructions file	174	19d ago	MIT	A	742	GitHub Copilot
pluribus copilot-instructions.mdcaioribeiroclw-pixel/pluribus	Instructions file	15	3mo ago	MIT	A	177	GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	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

muse: Instructions file for Claude Code