agentmods.dev

swarm: Instructions file for Claude Code

CLAUDE.md

swarm CLAUDE.md is an instructions file for Claude Code from swarm-ai-research/swarm. It costs 4,326 tokens per session, scanned D, original, MIT.

A set of Claude Code instructions for a research repository. Claude Code is a coding agent that follows project guidance while editing and running code.

In plain words
What is it for?
Use it to follow the project's research workflow, inspect existing commands and agents, manage artifacts, and apply repository-specific development rules.
Why use it?
It keeps repository workflows consistent and discourages creating separate commands or agents when an existing one can be extended.

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 swarm-ai-research/swarm's own configuration. It tells Claude Code how to work on 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 swarm configures →

not rated 42repo +2 changed 3d ago D scan 4,326 tokens original MIT
View source ↗ swarm-ai-research/swarm swarm-ai.org
Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/swarm-ai-research/swarm/claude-md"><img src="https://agentmods.dev/badge/instructions/swarm-ai-research/swarm/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,326 This file is loaded in full into every session.
When invoked 4,326 The same file — it is already loaded in full.
Security scan D 2 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 $0.04326 $0.04326
Opus 5 $0.02163 $0.02163
Sonnet 5 $0.00865 $0.00865
Haiku 4.5 $0.00433 $0.00433

Measured 3d ago against content hash 4eb1e9b7e5d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade D, and why

swarm CLAUDE.md scanned grade D with 2 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 3d 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.

Reads MCP configurationmediumAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

- MCP integrations are configured in `.mcp.json` (safe-by-default placeholders; no secrets committed).

Recursive force deletehighDestructive command

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

- After rewriting a source file with a script (python heredoc, sed -i), a same-second mtime can defeat Python's bytecode-cache invalidation: imports then silently run the OLD code while the file shows the new code (obser
CLAUDE.md · 338 lines

How it starts

The opening of the file, as written. The whole thing — 338 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.

This repo is set up as a Claude Code template for SWARM-style research work:

  • Custom slash commands live in .claude/commands/ (e.g. /run_scenario, /sweep, /plot, /red_team).
  • Research-role specialist agents live in .claude/agents/.
  • Role-selection guidance lives in AGENTS.md; keep it synchronized with .claude/agents/.
  • Optional git hygiene hooks live in .claude/hooks/ (install via /install_hooks).
  • MCP integrations are configured in .mcp.json (safe-by-default placeholders; no secrets committed).

Extend, don't proliferate

Do not create new slash commands, agents, or hooks when an existing one can absorb the functionality. This repo has been through multiple consolidation passes. Before proposing anything new:

  1. Check existing commands first. Read .claude/commands/ and look for a command that covers the same workflow area. If one exists, add a --flag or mode to it instead of creating a new file.
  2. Prefer flags over files. A command with 3 clear modes (/ship, /ship --fix, /ship --all) is better than 3 separate commands (/commit_push, /fix_commit, /sweep_and_ship).
  3. Same rule for agents. If a new role overlaps with an existing agent's domain, extend that agent's .md with a new section rather than creating a new agent file.
  4. Same rule for hooks. Post-write checks are consolidated into a single post_write_check.sh. Add new checks as a section in that file, not as a new hook script.
  5. When in doubt, don't create. If you're unsure whether something warrants a new command, it probably doesn't. Add it as a mode on the closest existing command and note it in the migration table.
  6. Document every change. When extending a command with a new flag/mode or creating a new command:
    • Update the command's .md file with usage examples, argument parsing, and behavior for the new mode.
    • Add a migration table entry if replacing or absorbing an old command.
    • Update cross-references in other commands that mention the changed command.
    • Update AGENTS.md if agent roles change.
    • Run /audit_docs --nav-only if docs pages were added or moved.

Read the full file on GitHub · 338 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. 3d ago Changed · -12 lines · -159 tokens per session 4eb1e9b7e5d5
  2. 6d ago First seen · 350 lines · 4,485 tokens per session scan D b40587c9a037

Subscribe to this mod's changes

swarm CLAUDE.md is an instructions file published in the GitHub repository swarm-ai-research/swarm (42 stars, last pushed yesterday), licensed MIT. It adds 4,326 tokens to every session, about $0.0216 per session on Opus 5. A static security scan graded it D with 2 findings (reads mcp configuration, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Building agentsProject managementagi-safetyaiai-agentai-agentsclawxivopenclaw
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