SwarmAI: Instructions file for Claude Code

AGENTS.md

SwarmAI AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from xg-gh-25/SwarmAI. It costs 5,366 tokens per session, scanned A, original, MIT.

Repository instructions for AI coding assistants working on SwarmAI, a self-evolving operating system for software agents. They explain its architecture, data flow, and rules for changing the code.

In plain words
What is it for?
Use them when editing SwarmAI to follow its project structure, review rules, processing stages, and automatically refreshed documentation.
Why use it?
They help an agent understand which files control behavior and which store knowledge, reducing unsafe or misunderstood changes.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: PreToolUse hook event, but also the file is AGENTS.md. Also seen: mentions subagents; mentions Claude Code; mentions AGENTS.md.

This is xg-gh-25/SwarmAI's own configuration. It tells Claude Code, Codex and OpenCode how to work on SwarmAI 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 SwarmAI configures →

Reuse

Borrowing it

Nothing to install: this file belongs to xg-gh-25/SwarmAI. 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/xg-gh-25/SwarmAI/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/xg-gh-25/SwarmAI

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 SwarmAI AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/xg-gh-25/swarmai/agents-md/github.svg)](https://agentmods.dev/instructions/xg-gh-25/swarmai/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/xg-gh-25/swarmai/agents-md"><img src="https://agentmods.dev/badge/instructions/xg-gh-25/swarmai/agents-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 SwarmAI AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/xg-gh-25/swarmai/agents-md"><img src="https://agentmods.dev/badge/instructions/xg-gh-25/swarmai/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,366 This file is loaded in full into every session.
When invoked 5,366 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. ✓ AI security review Fable 5.1 · 7 Sept 2026 📄 Read the review
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 $0.05366 $0.05366
Opus 5 $0.02683 $0.02683
Sonnet 5 $0.01073 $0.01073
Haiku 4.5 $0.00537 $0.00537

Measured 9d ago against content hash 39c72625d39a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

SwarmAI 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 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.

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 · 368 lines

How it starts

The opening of the file, as written. The whole thing — 368 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for AI coding assistants (Claude Code, Kiro, Cursor, Codex, and others) working in this repository.

Auto-refresh: the <!-- CAPABILITIES --> block below is regenerated by backend/scripts/refresh_ai_docs.py; everything else is hand-authored. Edit prose freely — just keep the marked block and the section headings intact.


What SwarmAI Is (read this first — it changes how you should judge the code)

SwarmAI is a self-evolving Agent OS, not a chatbot and not a Claude wrapper. The distinction is load-bearing for anyone editing this repo:

  • Cognition is separated from knowledge. The OS (how the system judges — its principles, rules, and gates) is deliberately kept apart from the disk (what it knows — memory rows, domain docs). One edited line in a governed context file shifts judgment more than a thousand knowledge entries. When you touch this codebase, ask which layer you're in: a behavior change is an OS change; a fact change is a disk change. They have different review bars.
  • The model proposes, the OS disposes. Model output is never trusted on its own. A layer of gates, a staged pipeline, and a validator sit above it and hold authority. This is why so much of backend/core/ looks like "guardrails around an LLM" — that is the product.
  • Value compounds across sessions. Sessions are discontinuous; intelligence shouldn't be. Post-session hooks fire between runs (distillation, evolution, context-health, cultivation), so the next session starts warmer than the last. Code that runs after a session ends is not an afterthought here — it's the mechanism.
  • A recurring error class becomes a structural gate. When the same mistake shows up 3+ times, the fix is not another prose rule — it's a gate in security_hooks.py where the wrong move physically cannot happen. If you're tempted to "add a warning comment," consider whether a gate is the real fix.
  • Every project is a domain brain (a DDD). A project is not a folder of files — it's a brain with one universal six-section structure (Identity · Knowledge · Gates · Capabilities · Delivery · Refresher), identical for every domain, governing 0..N assets (a code repo, a data source, a corpus — or nothing). See Projects/*/.

Read the full file on GitHub · 368 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 · 368 lines · 5,366 tokens per session scan E 39c72625d39a

Subscribe to this mod's changes

SwarmAI AGENTS.md is an instructions file published in the GitHub repository xg-gh-25/SwarmAI (44 stars, last pushed 2d ago), licensed MIT. It adds 5,366 tokens to every session, about $0.0268 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

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