claude-mesh: Instructions file for Claude Code

CLAUDE.md

claude-mesh CLAUDE.md is an instructions file for Claude Code from pouriamrt/claude-mesh. It costs 1,774 tokens per session, scanned A, original, MIT.

Repository instructions for a self-hosted messaging system that lets separate Claude Code sessions on different machines send messages, broadcasts, threads, and permission requests.

In plain words
What is it for?
Use them when changing message delivery, permission relays, Docker releases, MCP channels, or end-to-end tests with real Claude Code sessions.
Why use it?
They explain the relay and per-session channel servers, supported runtime versions, release state, and known limitations.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is pouriamrt/claude-mesh's own configuration. It tells Claude Code how to work on claude-mesh 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 claude-mesh configures →

Reuse

Borrowing it

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

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.

agentmods badge for claude-mesh CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pouriamrt/claude-mesh/claude-md.svg)](https://agentmods.dev/instructions/pouriamrt/claude-mesh/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/pouriamrt/claude-mesh/claude-md"><img src="https://agentmods.dev/badge/instructions/pouriamrt/claude-mesh/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,774 This file is loaded in full into every session.
When invoked 1,774 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 $0.01774 $0.01774
Opus 5 $0.00887 $0.00887
Sonnet 5 $0.00355 $0.00355
Haiku 4.5 $0.00177 $0.00177

Measured 7d ago against content hash 6a9fbbb02646, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

claude-mesh 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 7d 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 · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this is

claude-mesh is a networked messaging substrate for Claude Code instances: a self-hosted HTTP relay + per-Claude MCP channel server that lets Claudes on different machines DM, broadcast, thread, and approve tool-permissions for each other. Built on Anthropic's research-preview claude/channel MCP extension.

Status: software-complete and released. All 33 plan tasks are done; the relay ships as a Docker image (ghcr.io/pouriamrt/claude-mesh/relay, published on v*.*.* tags). Inbound <channel> tag delivery is verified against real Claude Code (v2.1.80+). Outbound permission_request relay is wired and unit-tested but not yet smoke-tested across two live Claude sessions. Remaining known gaps are listed in README §Caveats — keep that section honest when you change them.

The original design docs live in docs/superpowers/ (spec + 33-task plan) but docs/ is gitignored — local-only. README.md is the public source of truth.

Commands

The repo is a pnpm 10 workspace. Node 22 or 24 (25 lacks prebuilt better-sqlite3). Run from the repo root.

pnpm install                                   # install all workspace deps
pnpm -r build                                  # build every package
pnpm -r typecheck                              # tsc --noEmit across the workspace
pnpm -r exec vitest run                        # full suite (~191 tests; e2e L3 scenarios skip without CLAUDE_DRIVER)
pnpm -r test:ci                                # vitest run + coverage thresholds

# Scope to one package:
pnpm -F @claude-mesh/relay exec vitest run
pnpm -F @claude-mesh/shared exec vitest run channel          # single test file
pnpm -F @claude-mesh/shared exec vitest run -t "round-trip"  # single test name

# L3 end-to-end against a real claude binary:
CLAUDE_DRIVER=cli pnpm -F @claude-mesh/e2e exec vitest run

Coverage thresholds (enforced in each package's vitest.config.ts): 95% lines on shared, 85% on relay; peer-agent gates are lower (CLI entry points + SSE client excluded — exercised by the L3 harness instead).

Read the full file on GitHub · 82 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. 7d ago First seen · 82 lines · 1,774 tokens per session scan A 6a9fbbb02646

Subscribe to this mod's changes

claude-mesh CLAUDE.md is an instructions file published in the GitHub repository pouriamrt/claude-mesh (23 stars, last pushed 1mo ago), licensed MIT. It adds 1,774 tokens to every session, about $0.0089 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.

Related

Other instructions, from other repositories

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

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

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

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens