What is SwarmAI CLAUDE.md?

Repository instructions for SwarmAI, an agent operating system whose rules and checks control how its language-model proposals are accepted.

Use them when modifying or reviewing SwarmAI. They help select the right files and commands and ensure affected builds and tests pass before code is pushed.

They give coding assistants the project’s architecture, conventions, required tests, build commands, and conditions for pushing changes.

How xg-gh-25/SwarmAI configures Claude Code

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/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/xg-gh-25/SwarmAI

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/xg-gh-25/swarmai/claude-md/github.svg)](https://agentmods.dev/instructions/xg-gh-25/swarmai/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/xg-gh-25/swarmai/claude-md"><img src="https://agentmods.dev/badge/instructions/xg-gh-25/swarmai/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/xg-gh-25/swarmai/claude-md"><img src="https://agentmods.dev/badge/instructions/xg-gh-25/swarmai/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 679 This file is loaded in full into every session.

When invoked 679 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.

Model	Per session	Once invoked
Fable 5.1	$0.00679	$0.00679
Opus 5	$0.00340	$0.00340
Sonnet 5	$0.00136	$0.00136
Haiku 4.5	$0.00068	$0.00068

Measured 10d ago against content hash 1843f86f7686, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

SwarmAI 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 10d 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 · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Short entry point for Claude Code / Cursor / other AI coding assistants working in this repo.

SwarmAI is a self-evolving Agent OS, not a Claude wrapper. Cognition (how it judges — principles, rules, gates) is kept separate from knowledge (what it knows). The model proposes; a layer of gates + a staged pipeline + a validator dispose. Much of backend/core/ is "guardrails around an LLM" — that is the product.

Full architecture guide → AGENTS.md — the mental model, data flow, process topology, backend/frontend structure, security gates, conventions, and invariants. Read it before any non-trivial change. This file is the always-loaded short version; AGENTS.md is the depth.

Before you push — the local quality gate

MUST NOT push to GitHub unless ALL of these passed locally for the change:

Build green — backend ./prod.sh build, and/or cd desktop && npm run build:all (whichever the change touches).
Tests green — at least the affected suites (cd backend && python -m pytest tests/test_<module>.py --timeout=60 / cd desktop && npm test -- --run); full suite (SWARMAI_SUITE=1) when the blast radius warrants.
Eval green — cd backend && python scripts/ci_eval_gate.py (a pure freshness+green check, zero Bedrock cost — it does NOT run the judge).

If any of build / tests / eval was not run or is failing → do not push. Tests-green alone is not "qualified"; commit ≠ qualified ≠ deployed — a build makes a binary, code isn't live until rebuild+restart. Commit directly to main (project convention); never auto-branch.

Commit identity

Every commit MUST end with Co-Authored-By: Swarm <[email protected]> — never Claude/Anthropic identity. A PreToolUse gate blocks commits missing it, but nothing auto-inserts it: write the line yourself. See AGENTS.md → "Git Commits" for why (shadowed local hooks + two-layer enforcement).

Dev commands

./dev.sh                          # full dev (backend + Vite + Tauri window)
./prod.sh build                   # PyInstaller build + verify + deploy to daemon
cd desktop && npm run build:all   # frontend production build (embedded in the .app)
cd backend && python -m pytest tests/test_<module>.py -v --timeout=60   # targeted tests

Read the full file on GitHub · 52 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.

10d ago First seen · 52 lines · 679 tokens per session scan A 1843f86f7686

Subscribe to this mod's changes

SwarmAI CLAUDE.md is an instructions file published in the GitHub repository xg-gh-25/SwarmAI (44 stars, last pushed 3d ago), licensed MIT. It adds 679 tokens to every session, about $0.0034 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.

agentic-ai ai-agent aws-bedrock claude claude-sdk context-engineering

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

SwarmAI: Instructions file for Claude Code