teamclaw AGENTS.md

Project instructions for TeamClaw, an open-source platform where multiple AI agents collaborate, built with TypeScript and Next.js.

In plain words
What is it for?
Installing dependencies, building, testing, linting, type-checking, and following the project's coding conventions.
Why use it?
They explain how to set up the project and check changes before committing.

Instructions file for CodexOpenCode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/teamclawai/teamclaw/agents-md
Clone the repo
git clone --depth 1 https://github.com/teamclawai/teamclaw

Made for: Codex, OpenCode.

Per session 1,863 This file is loaded in full into every session.
When invoked 1,863 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01863 $0.01863
Opus 5 $0.00932 $0.00932
Sonnet 5 $0.00373 $0.00373
Haiku 4.5 $0.00186 $0.00186

Measured 2d ago against content hash 6db444d76eac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

teamclaw 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 2d 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 · 312 lines

How it starts

The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TeamClaw - Agent Development Guidelines

For AI agents and human developers contributing to TeamClaw


Project Overview

TeamClaw is an open-source multi-agent AI collaboration platform built with TypeScript and Next.js.

Repository: https://github.com/yourusername/teamclaw
License: MIT
Version: 0.1.0


Quick Start for Contributors

Prerequisites

  • Node.js 18+
  • pnpm 8+
  • Git

Setup

# Clone and setup
git clone https://github.com/yourusername/teamclaw.git
cd teamclaw
pnpm install
pnpm build

# Configure
cp config/default.json config/local.json
# Edit config/local.json with your OpenRouter API key

# Run dev server
pnpm dev

Build / Lint / Test Commands

Root Level

pnpm install          # Install all dependencies
pnpm build            # Build all packages
pnpm test             # Run all tests
pnpm check            # Lint and type check (REQUIRED before commit)

Package Level

cd packages/<package-name>
pnpm build            # Build package
pnpm check            # Lint and type check
pnpm test             # Run package tests

Code Style Guidelines

TypeScript

  • No any types unless absolutely necessary with explicit comment
  • Always use explicit types for function parameters and return values
  • Never use inline imports - always use standard top-level imports
  • Strict mode enabled - no implicit any

Imports

// Good
import { AgentCore } from "@teamclaw/core";
import { MessageRouter } from "./router";

// Bad
const AgentCore = await import("@teamclaw/core");

Naming Conventions

Element Convention Example
Files kebab-case message-router.ts
Classes PascalCase class AgentOrchestrator
Functions camelCase function handleMessage()
Constants UPPER_SNAKE const MAX_RETRIES = 3
Interfaces PascalCase interface AgentConfig
Types PascalCase type MessageHandler

Read the full file on GitHub · 312 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. 2d ago First seen · 312 lines · 1,863 tokens per session scan A 6db444d76eac

Subscribe to this mod's changes

teamclaw AGENTS.md is an instructions file published in the GitHub repository teamclawai/teamclaw (5 stars, last pushed 6mo ago), licensed MIT. It adds 1,863 tokens to every session, about $0.0093 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 2026-08-31.