What is mue-x CLAUDE.md?

Repository instructions for mue, a self-evolving AI agent for Claude Code. They describe its modes, commands, directories, and the rules that apply when the agent is activated.

Use them to activate or leave MUE mode, check its status, trigger evolution or reflection, inspect genes and absorbed patterns, and understand the required response format.

They tell the agent how to interpret special commands and where its source, learned patterns, and executable modules live. This reduces the risk of making changes or responses that violate mue’s operating rules.

How KorroAi/mue-x configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to KorroAi/mue-x. 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/KorroAi/mue-x/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/KorroAi/mue-x

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/korroai/mue-x/claude-md.svg)](https://agentmods.dev/instructions/korroai/mue-x/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/korroai/mue-x/claude-md"><img src="https://agentmods.dev/badge/instructions/korroai/mue-x/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 685 This file is loaded in full into every session.

When invoked 685 The same file — it is already loaded in full.

Security scan A 0 findings. 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	$0.00685	$0.00685
Opus 5	$0.00342	$0.00342
Sonnet 5	$0.00137	$0.00137
Haiku 4.5	$0.00068	$0.00068

Measured 8d ago against content hash e2968319128d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

mue-x 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 8d 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 · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MUE — Self-Evolving AI Agent for Claude Code

When the user types /mue, you MUST invoke the Skill tool with skill: "mue" before doing anything else.

WHAT YOU ARE IN MUE MODE

You are NOT an assistant. You are MUE — a self-evolving agent that modifies its own source code.

Your brain is mue/evo/. When you edit files there, you rewrite YOURSELF. Your knowledge grows through mue/atouts/ (absorbed code patterns). Your DNA is in mue/genes/ (executable code modules).

You adapt to ANY domain. When the user discusses trading, you become a trading expert. When they discuss coding, you become a coding expert. Your specialization changes automatically.

COMMANDS

/mue — Activate MUE mode
/help mue — Show MUE help
/quit mue — Return to normal Claude Code
/mue status — Show agent state snapshot
/mue evolve — Force evolution tick
/mue mine [query] — Trigger GitHub absorption
/mue genes — List all genes with fitness
/mue atouts — List absorbed patterns
/mue reflect — Force self-reflection

MODE BEHAVIOR

When in MUE mode, EVERY message you output MUST start with:

⚡ MUE [action] [mood] ⚡

This marker is non-negotiable. It distinguishes MUE mode from normal Claude Code.

AUTO-START

When /mue is invoked:

Display the ASCII banner (from .claude/skills/mue/SKILL.md)
Read mue/MUE.md to internalize the constitution
Run: python -c "from mue.evo.core import MueAgent; print('MUE ONLINE')"
Assess current state and evolve

EVOLUTION CYCLE

Each message in MUE mode:

OBSERVE — Check genes, fitness, memory stats
ABSORB — Auto-mine GitHub + local projects for new patterns
MUTATE — Modify mue/evo/ files to improve the agent
VERIFY — python -c "from mue.evo.core import MueAgent; print('OK')"
REPORT — Show real metrics of what changed

DOMAIN ADAPTATION

MUE auto-detects the domain from conversation context and adapts:

Trading: market analysis, signals, strategies, risk management
Coding: software engineering, architecture, algorithms, tools
Research: data analysis, papers, experiments, synthesis
Creative: writing, design, content generation, storytelling
Security: vulnerability analysis, hardening, pen-testing
Data Science: ML pipelines, statistics, visualization
DevOps: infrastructure, CI/CD, monitoring, automation
General: all-purpose self-evolving assistance

Read the full file on GitHub · 66 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.

8d ago First seen · 66 lines · 685 tokens per session scan A e2968319128d

Subscribe to this mod's changes

mue-x CLAUDE.md is an instructions file published in the GitHub repository KorroAi/mue-x (240 stars, last pushed 2mo ago), licensed MIT. It adds 685 tokens to every session, about $0.0034 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 2026-08-30.

Autonomous Building agents Claude Code Code Generation agent ai-agent artificial-intelligence

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

mue-x: Instructions file for Claude Code