claude-swarm: Instructions file for Claude Code

CLAUDE.md

claude-swarm CLAUDE.md is an instructions file for Claude Code from cj-vana/claude-swarm. It costs 3,967 tokens per session, scanned C, original, MIT.

Repository-specific instructions for Claude Code, including how to build, test, debug, and understand the codebase. They also describe an MCP server, a standard way for AI tools to use external capabilities, that coordinates worker sessions.

In plain words
What is it for?
Building and testing the project, checking types, running individual tests, debugging the MCP server, and coordinating parallel coding workers.
Why use it?
They give the coding agent the project’s commands, structure, and operating rules in one place, reducing guesswork during development.

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 cj-vana/claude-swarm's own configuration. It tells Claude Code how to work on claude-swarm 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-swarm configures →

Reuse

Borrowing it

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

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-swarm CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/cj-vana/claude-swarm/claude-md"><img src="https://agentmods.dev/badge/instructions/cj-vana/claude-swarm/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,967 This file is loaded in full into every session.
When invoked 3,967 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.03967 $0.03967
Opus 5 $0.01983 $0.01983
Sonnet 5 $0.00793 $0.00793
Haiku 4.5 $0.00397 $0.00397

Measured 9d ago against content hash d2516047f770, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

claude-swarm CLAUDE.md scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

**base-constraints.ts** - Immutable security boundaries (frozen at runtime). Defines prohibited tools (rm -rf, sudo, etc.), prohibited paths (/etc, ~/.ssh, etc.), and maximum privilege ceiling. LLM-generated protocols ca
CLAUDE.md · 335 lines

How it starts

The opening of the file, as written. The whole thing — 335 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.

Build and Development Commands

npm run build         # Compile TypeScript and copy dashboard assets
npm run dev           # Watch mode for TypeScript compilation
npm start             # Run the compiled MCP server
npm run inspector     # Debug with MCP Inspector
npx tsc --noEmit      # Type-check without emitting (CI validation)
npm test              # Run all tests with Vitest
npm run test:watch    # Run tests in watch mode
npm run test:coverage # Run tests with coverage report
npx vitest run src/utils/git-verification.test.ts  # Run a single test file

Install the MCP server into Claude Code:

claude mcp add claude-swarm --scope user -- node $(pwd)/dist/index.js

Install the /swarm skill for guided orchestration:

mkdir -p ~/.claude/skills/swarm && cp skill/SKILL.md ~/.claude/skills/swarm/

Architecture Overview

This is an MCP (Model Context Protocol) server that orchestrates parallel Claude Code worker swarms via tmux sessions. The pattern separates concerns between an orchestrator (which plans and monitors) and workers (which implement individual features).

Core Components

src/index.ts - MCP server entry point registering 55+ tools. All tool handlers are defined inline. Tool schemas use Zod for validation. The file is structured by tool category: core orchestration, worker management, competitive planning, confidence monitoring, feature management, session control, post-completion reviews, protocol management, protocol networking, context management, and repository setup.

src/state/manager.ts - Persistent state management using the "notebook pattern". Stores session state in .claude/orchestrator/state.json with atomic writes (temp file + rename). Also generates claude-progress.txt for human readability and init.sh for environment setup. Manages feature context (FeatureContext), routing config, and protocol bindings per feature.

Read the full file on GitHub · 335 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 · 335 lines · 3,967 tokens per session scan C d2516047f770

Subscribe to this mod's changes

claude-swarm CLAUDE.md is an instructions file published in the GitHub repository cj-vana/claude-swarm (110 stars, last pushed 6mo ago), licensed MIT. It adds 3,967 tokens to every session, about $0.0198 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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

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