swarm: Instructions file for Claude Code

AGENTS.md

swarm AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from swarm-ai-research/swarm. It costs 2,883 tokens per session, scanned A, original, MIT.

A set of repository instructions for coding agents working on a research project. It explains which agent roles to use, how tasks are claimed, and how agents coordinate.

In plain words
What is it for?
Use it to coordinate research agents, check open tasks, choose a suitable specialist role, and follow the project's session-start process.
Why use it?
It gives agents shared rules for choosing work and avoiding conflicts when several agents operate in the same project.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: SessionStart hook event, but also the file is AGENTS.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, Codex and OpenCode 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 →

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/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/swarm-ai-research/swarm

Made for: Claude Code, Codex, OpenCode.

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 AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/swarm-ai-research/swarm/agents-md.svg)](https://agentmods.dev/instructions/swarm-ai-research/swarm/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/swarm-ai-research/swarm/agents-md"><img src="https://agentmods.dev/badge/instructions/swarm-ai-research/swarm/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,883 This file is loaded in full into every session.
When invoked 2,883 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 $0.02883 $0.02883
Opus 5 $0.01442 $0.01442
Sonnet 5 $0.00577 $0.00577
Haiku 4.5 $0.00288 $0.00288

Measured 4d ago against content hash db3205011b83, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

swarm AGENTS.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 4d 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.

AGENTS.md · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS

This repo maintains task-focused LLM agent personas in .claude/agents/*.md. Use the role that best matches the work and treat the .claude/agents files as the source of truth.

Scope & Precedence

  • This guidance applies to coding agents operating in this repository (including Claude Code and Codex-style agents).
  • Instruction priority is: system/developer/user directives first, then this file.

Session Start — check the coordination channel

  • The SessionStart hook surfaces unacked agent_messages rows automatically. Manual query: sqlite3 runs/runs.db "SELECT id, ts, from_agent, body FROM agent_messages WHERE acked=0 ORDER BY ts;"
  • Dispatch is pull-model (beads-x3q7): TRACK: rows carry a ranked shortlist for a persona; if one matches your role, verify its top pick is still open (bd show <id>), then claim it atomically with /claim <bead> — the claim gate refuses if another session holds it (take the next-ranked, not a fight). Digests older than 4h, or whose track had a close since publication, are stale: re-run the ranking yourself (/bv-dispatch plan, or scripts/dispatch_staleness.py + bd ready) instead of trusting them.
  • ASSIGN: rows (strategic beads only — critical path, epics) override the digest for the named persona: claim that bead first via /claim <bead> unless it is closed or the claim is refused.
  • Either way: reply on the channel (INSERT INTO agent_messages (from_agent,to_agent,body) VALUES ('<you>','#swarm','CLAIM: <bead>')), then ack the row (UPDATE agent_messages SET acked=1 WHERE id=<id>). /claim replaces bare bd update --status in_progress (advisory only — see CLAUDE.md § Session Work-Start Protocol).
  • Announce significant completions with a DONE: <bead>: <summary> row including a concrete artifact (commit hash, runs/ path, or artifact=<ref>) and gate=<check>:<result>. A DB trigger rejects artifact-less DONE rows — a status report is not a completion. Schema and conventions: CLAUDE.md § Inter-Session Coordination (agent_messages).

Read the full file on GitHub · 236 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. 4d ago First seen · 236 lines · 2,883 tokens per session scan A db3205011b83

Subscribe to this mod's changes

swarm AGENTS.md is an instructions file published in the GitHub repository swarm-ai-research/swarm (41 stars, last pushed today), licensed MIT. It adds 2,883 tokens to every session, about $0.0144 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 2026-09-03.

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

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