agentmods.dev

modelmux: Instructions file for Claude Code

CLAUDE.md

modelmux CLAUDE.md is an instructions file for Claude Code, Codex from JRWoodcock/modelmux. It costs 1,134 tokens per session, scanned A, original, Apache-2.0.

Instructions for working on modelmux, an MCP server that lets Codex, Claude Code, and Perplexity call one another from a terminal. It can pass local files to these AI services and ask one or several of them for responses.

In plain words
What is it for?
Maintaining the modelmux server, its AI-calling tools, file attachments, installer, environment variables, and connectivity tests.
Why use it?
It documents the project’s architecture, limits, configuration, installation, and testing so changes do not break its intended setup.

Instructions file for Claude CodeCodex

Written for Codex and Claude Code: reads ~/.codex or $CODEX_HOME, but also the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is JRWoodcock/modelmux's own configuration. It tells Claude Code and Codex how to work on modelmux itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything modelmux configures →

not rated 0repo 2mo ago A scan 1,134 tokens original Apache-2.0
View source ↗ JRWoodcock/modelmux
Reuse

Borrowing it

Nothing to install: this file belongs to JRWoodcock/modelmux. 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/JRWoodcock/modelmux/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/JRWoodcock/modelmux

Made for: Claude Code, Codex.

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.

agentmods badge for modelmux CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jrwoodcock/modelmux/claude-md/github.svg)](https://agentmods.dev/instructions/jrwoodcock/modelmux/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jrwoodcock/modelmux/claude-md"><img src="https://agentmods.dev/badge/instructions/jrwoodcock/modelmux/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.

agentmods 80×15 button for modelmux CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jrwoodcock/modelmux/claude-md"><img src="https://agentmods.dev/badge/instructions/jrwoodcock/modelmux/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,134 This file is loaded in full into every session.
When invoked 1,134 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01134 $0.01134
Opus 5 $0.00567 $0.00567
Sonnet 5 $0.00227 $0.00227
Haiku 4.5 $0.00113 $0.00113

Measured 9d ago against content hash be4c84527d10, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

modelmux 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 9d 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 · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code (and other agents) working in this repository.

What this is

modelmux is an MCP (Model Context Protocol) server that lets Claude Code, Codex, and Perplexity call each other as tools from within a terminal session. Files (text, code, images, PDFs) can be attached by local path and are forwarded to each AI in the appropriate API format. See README.md for the full user-facing docs.

Architecture

  • src/server.js — the entire MCP server. Speaks JSON-RPC 2.0 over stdio (newline-delimited). Registers four tools:
    • ask_claude — Anthropic API
    • ask_codex — OpenAI API
    • ask_perplexity — Perplexity web-grounded search API
    • broker — fans out to multiple AIs in parallel, optionally synthesizes
  • src/test.js — connectivity + file I/O smoke test (npm test).
  • install.sh — per-machine installer: checks Node, copies files to ~/.modelmux/, prompts for API keys (saved to ~/.zshrc), and registers the server with Claude Code and Codex. Detects each Desktop app's bundled binary when no CLI is on PATH, registers with keys embedded as env vars, and uses node's absolute path. Claude's -e is variadic — the server name must come before the -e flags or it gets swallowed as an env var. Codex uses --env.
  • update-keys.sh — re-syncs the embedded API keys from ~/.zshrc into the Claude and Codex registrations (Desktop apps don't read ~/.zshrc, so the embedded copies go stale when a key is rotated).
  • lib/common.sh — shared shell helpers sourced by both install.sh and update-keys.sh (colour output, find_claude/find_codex host detection, resolve_node, build_env_flags, and the refresh_{claude,codex}_registration helpers used by update-keys). Keep host-detection/key logic here, not duplicated in the two entry scripts. install.sh copies it to ~/.modelmux/lib/ so update-keys.sh can source it post-install. Host quirk: Codex's mcp add overwrites an existing server; Claude's errors on a duplicate (must remove first) and its -e is variadic (name before flags). The refresh helpers encode this.
  • install.sh also appends a Codex tool-routing rule to ~/.codex/AGENTS.md (fenced by a <!-- modelmux:tool-routing --> marker) so "ask Claude/Perplexity" uses the modelmux MCP tools instead of Codex's Computer Use plugin. The append is idempotent (marker-gated) and never overwrites existing AGENTS.md content.

Read the full file on GitHub · 80 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.

  1. 9d ago First seen · 80 lines · 1,134 tokens per session scan A be4c84527d10

Subscribe to this mod's changes

modelmux CLAUDE.md is an instructions file published in the GitHub repository JRWoodcock/modelmux (0 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,134 tokens to every session, about $0.0057 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 agentsClaude Codeai-agentsanthropicclaudeclicodex
Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 tokens

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 · 5,153 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

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens