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.
npx agentmods add instructions/myths-labs/muse/agents-mdgit clone --depth 1 https://github.com/myths-labs/museWrote 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/myths-labs/muse/agents-md)<a href="https://agentmods.dev/instructions/myths-labs/muse/agents-md"><img src="https://agentmods.dev/badge/instructions/myths-labs/muse/agents-md.svg" alt="Measured on agentmods" 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 | $0.29476 | $0.29476 |
| Opus 5 | $0.14738 | $0.14738 |
| Sonnet 5 | $0.05895 | $0.05895 |
| Haiku 4.5 | $0.02948 | $0.02948 |
Grade D, and why
muse AGENTS.md scanned grade D with 3 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 5d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
**Current State**: `<!-- L0: v2.22.0 | Governance System✅, TF-IDF Search✅, Benchmark✅, Memory Loss Prevention✅, Skill Marketplace✅, Web Dashboard✅, VS Code Extension✅, Online Dashboard✅, S043✅, 57skills, 9/9渠道已发, S040黑客松 Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Add to your `~/.claude/settings.json`: Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- [x] 页面含安装命令 (`curl` one-liner) How it starts
The opening of the file, as written. The whole thing — 2,213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Auto-generated from MUSE (The AI Coding Governance System) This file acts as a compatibility layer for tools expecting a single AGENTS.md file.
Core Constitution
🏛 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: When context ≥ 80%, immediately run
/bye - Verify Before Claiming Done: Run
verification-before-completionskill before saying "done" - End Sessions Properly: Always use
/byeto end conversations - Research-First Development: 🚨 When implementing unfamiliar technical patterns (e.g., SDK APIs, coordinate systems, rendering pipelines), MUST search the web first for proven solutions before writing code. Never reinvent what the community has already solved. Use
search_webto find official docs, GitHub issues, and Stack Overflow answers. 闭门造车推导公式 = 浪费时间 + 架构错误。
Skill-Driven Execution
- Speed Reference (know which skill to use):
Task Skill Git commit git-commitCode review code-reviewer-agentBuild errors build-error-resolverDebugging systematic-debuggingVerify completion verification-before-completionGEO/SEO optimization geo-seo→geo-audit/geo-citability/geo-schema/geo-report-pdf
Context Health Pre-Check
Every session start: estimate context usage. If ≥ 70%, suggest opening new conversation.
Defensive saving: every 10 interaction rounds silently update memory/CRASH_CONTEXT.md.
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.
- 5d ago First seen · 2,213 lines · 29,476 tokens per session scan D 4bda0e1a0085
muse AGENTS.md is an instructions file published in the GitHub repository myths-labs/muse (32 stars, last pushed 1mo ago), licensed MIT. It adds 29,476 tokens to every session, about $0.1474 per session on Opus 5. A static security scan graded it D with 3 findings (hidden instructions, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
project-brain copilot-instructions.md
Instructions for Ethan-YS/project-brain, covering on session start, single-workstream, multi-workstream, update behavior and project red lines.
mex CLAUDE.md
Claude Code instructions for mex-memory/mex, a project described as: Persistent project memory for AI coding agents. Structured scaffold + drift detection CLI.
mex AGENTS.md
AGENTS.md instructions for mex-memory/mex, a project described as: Persistent project memory for AI coding agents. Structured scaffold + drift detection CLI.
pluribus copilot-instructions.md
Instructions for caioribeiroclw-pixel/pluribus, covering project, stack, conventions, constraints and goals.
Iron-mem CLAUDE.md
Instructions for BMC-INC/Iron-mem, a project described as: Agent-native memory infrastructure for AI coding assistants. Governed session capture, LLM compression, hybrid retrieval (FTS + vector + RRF), temporal knowledge graph, content-addressed storage, compliance-grade classification. Single Rust binary, MCP server.…
ai-mind-map copilot-instructions.md
Copilot instructions for shdra06/ai-mind-map, covering ai mind map mcp — code memory engine (v1.4.0), 🚀 first thing to do in every conversation, quick lookup: "i need to..." → use this tool, ⚡ session lifecycle (always use these) and 🔍 find code (instead of grep/reading files).