codemesh CLAUDE.md

Instructions for CodeMesh, an MCP server that lets an AI agent discover and call tools from multiple MCP servers by running TypeScript code.

In plain words
What is it for?
Use it to discover tools, retrieve their TypeScript interfaces, combine calls across HTTP, standard-input, or WebSocket servers, and document unclear tool results.
Why use it?
It provides one way to coordinate tools across different servers without loading every tool definition into the agent's context at once.

Instructions file

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/kiliman/codemesh/claude-md
Clone the repo
git clone --depth 1 https://github.com/kiliman/codemesh
Per session 1,351 This file is loaded in full into every session.
When invoked 1,351 The same file โ€” 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.

ModelPer sessionOnce invoked
Fable 5 $0.01351 $0.01351
Opus 5 $0.00675 $0.00675
Sonnet 5 $0.00270 $0.00270
Haiku 4.5 $0.00135 $0.00135

Measured 2d ago against content hash c6e90fae8a78, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codemesh CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories โ€” prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency โ€” measured 2d 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 ยท 164 lines

How it starts

The opening of the file, as written. The whole thing โ€” 164 lines โ€” stays where its author put it; the contents beside it link to each section on GitHub.

CodeMesh MCP Server

CodeMesh is a "Code Mode" MCP server that executes TypeScript code against multiple MCP tools. Think of it as a universal adapter that lets agents write code to orchestrate ANY MCP server.

๐ŸŽฏ Core Concept

Instead of exposing individual MCP tools, CodeMesh provides:

  1. discover-tools - See what's available (context-efficient overview)
  2. get-tool-apis - Get TypeScript APIs for specific tools
  3. execute-code - Execute TypeScript that calls multiple tools
  4. add-augmentation - Document unclear outputs (self-improving!)

๐Ÿ—๏ธ Project Structure

packages/
โ”œโ”€โ”€ codemesh-server/    # Main CodeMesh MCP server
โ”œโ”€โ”€ client/             # CLI for testing
โ”œโ”€โ”€ example-server/     # Demo HTTP server
โ”œโ”€โ”€ weather-server/     # Demo stdio server
โ””โ”€โ”€ geocode-server/     # Demo stdio server

๐Ÿš€ Key Features

Multi-Server Support

  • โœ… HTTP, stdio, and websocket transports
  • โœ… Connect to multiple servers simultaneously
  • โœ… Execute code that calls tools from different servers
  • โœ… Works with any MCP-compliant server

Context Efficiency

  • โœ… Tiered discovery prevents context pollution
  • โœ… Load only the tool APIs you need
  • โœ… Single execute-code tool vs dozens of individual tools

Self-Improving Architecture ๐ŸŽ‰

  • โœ… Auto-augmentation: Agents document unclear outputs
  • โœ… // EXPLORING comment: Triggers mandatory documentation workflow
  • โœ… Nuclear option: Returns ERROR until augmentation created
  • โœ… Proven effective: Agent B one-shotted what Agent A struggled with!
  • โœ… Knowledge compounds: Each exploration helps future agents

Security

  • โœ… MCP SDK compliant env var handling
  • โœ… Environment variable substitution: ${VAR:-default}
  • โœ… Principle of least privilege
  • โœ… Safe to commit configs (use env vars for secrets)

๐Ÿ“ Auto-Augmentation Workflow

The Problem: Agents trial-and-error unclear tool outputs instead of documenting them.

The Solution: Make exploration without documentation an ERROR!

Read the full file on GitHub ยท 164 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. 2d ago First seen ยท 164 lines ยท 1,351 tokens per session scan A c6e90fae8a78

Subscribe to this mod's changes

codemesh CLAUDE.md is an instructions file published in the GitHub repository kiliman/codemesh (26 stars, last pushed 10mo ago), licensed MIT. It adds 1,351 tokens to every session, about $0.0068 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.