swarmclaw: Instructions file for Claude Code

CLAUDE.md

swarmclaw CLAUDE.md is an instructions file for Claude Code from swarmclawai/swarmclaw. It costs 3,713 tokens per session, scanned A, original, MIT.

Project instructions for coding agents working in the SwarmClaw repository.

In plain words
What is it for?
Use them when changing or releasing SwarmClaw code, especially when editing shared instructions, running the development server, or checking code quality.
Why use it?
They keep agent guidance consistent and define rules for the development server, TypeScript code, linting, and project architecture.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is swarmclawai/swarmclaw's own configuration. It tells Claude Code how to work on swarmclaw 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 swarmclaw configures →

Reuse

Borrowing it

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

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 swarmclaw CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/swarmclawai/swarmclaw/claude-md.svg)](https://agentmods.dev/instructions/swarmclawai/swarmclaw/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/swarmclawai/swarmclaw/claude-md"><img src="https://agentmods.dev/badge/instructions/swarmclawai/swarmclaw/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,713 This file is loaded in full into every session.
When invoked 3,713 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 $0.03713 $0.03713
Opus 5 $0.01857 $0.01857
Sonnet 5 $0.00743 $0.00743
Haiku 4.5 $0.00371 $0.00371

Measured 9d ago against content hash 1311cf6f937c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

swarmclaw 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 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.

CLAUDE.md · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Keeping Instructions in Sync

  • CLAUDE.md and AGENTS.md must stay in sync. When you add, edit, or remove a rule in one file, apply the same change to the other. They contain the same project guidelines — one for Claude Code, one for other coding agents.

Dev Server

  • NEVER kill the dev server (npm run dev, port 3456) without asking the user first. The user is often actively working against it, and other agents may be running tests against it. Always confirm before stopping, restarting, or killing the dev server process.

Code Quality

Lint baseline is a release gate. Run npm run lint:baseline before any production release. The baseline must pass — no net-new lint fingerprints. If you fix existing violations, run npm run lint:baseline:update to lock in the improvement.

Embrace TypeScript and the type system. Use proper types, interfaces, and generics. Never use any — use unknown, Record<string, unknown>, or define a proper interface. The type system is there to catch bugs at compile time; circumventing it defeats the purpose.

Lint rules exist to protect us. Do not suppress, disable, or work around lint rules. Fix the underlying code instead. If a rule is genuinely wrong for the project, change the rule in the lint config with a clear justification — but this should be rare. The default is to fix the code, not silence the linter.

Architecture

Prefer simple, maintainable, reliable architectures. Choose the straightforward approach over the clever one. Code that is easy to read, easy to debug, and easy to delete is better than code that is abstract, configurable, or "elegant." Avoid premature abstraction — three similar lines are better than a premature helper. Build for the current requirement, not hypothetical future ones.

Commit Messages

  • Never reference "Claude", "Anthropic", "Codex", "Co-Authored-By", or any AI tool in commit messages. Write commit messages as if a human authored the code.

Read the full file on GitHub · 190 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 · 190 lines · 3,713 tokens per session scan A 1311cf6f937c

Subscribe to this mod's changes

swarmclaw CLAUDE.md is an instructions file published in the GitHub repository swarmclawai/swarmclaw (667 stars, last pushed 2mo ago), licensed MIT. It adds 3,713 tokens to every session, about $0.0186 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

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