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.
npx agentmods add instructions/cloudchef/atlasclaw/agents-mdgit clone --depth 1 https://github.com/CloudChef/atlasclawWhat 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 | $0.01885 | $0.01885 |
| Opus 5 | $0.00942 | $0.00942 |
| Sonnet 5 | $0.00377 | $0.00377 |
| Haiku 4.5 | $0.00188 | $0.00188 |
Grade A, and why
atlasclaw 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.
How it starts
The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - AtlasClaw Coding Guidelines
Coding guidelines for AI assistants working on the AtlasClaw enterprise agent framework.
Concrete provider packages do not live in this repository. AtlasClaw core loads
them through providers_root, typically from a sibling providers repository.
Build / Test / Lint Commands
Backend (Python)
# Run the service
uvicorn app.atlasclaw.main:app --reload --host 0.0.0.0 --port 8000
# Run all tests
pytest tests/atlasclaw -q
# Run a single test file
pytest tests/atlasclaw/test_agent.py -v
# Run a single test class
pytest tests/atlasclaw/test_agent.py::TestStreamEvent -v
# Run a single test method
pytest tests/atlasclaw/test_agent.py::TestStreamEvent::test_create_lifecycle_start -v
# Run tests with specific markers
pytest -m "not slow" # Skip slow tests
pytest -m llm # Run LLM integration tests (needs API key)
pytest -m e2e # Run end-to-end tests
# Run with coverage
pytest --cov=app.atlasclaw --cov-report=term-missing
Frontend (JavaScript)
cd app/frontend
# Install dependencies
npm install
# Build for production
npm run build
# Build for development (with sourcemap)
npm run build:dev
# Run tests
npm test
Required Reading
Before making any feature changes, bug fixes, or architectural decisions, consult these canonical documents:
| Document | Content | Path |
|---|---|---|
| Architecture | Design philosophy, system architecture, bootstrap sequence, request lifecycle, security model, extension points | docs/architecture.md |
| Module Details | Per-module API surface, class/method/enum reference, configuration options, dependencies | docs/module-details.md |
| Development Spec | Code style, architecture patterns, error handling, security, testing, extension development, deployment & operations, review checklist | docs/development-spec.md |
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.
- 2d ago First seen · 221 lines · 1,885 tokens per session scan A 27a49535a9b3
atlasclaw AGENTS.md is an instructions file published in the GitHub repository CloudChef/atlasclaw (87 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,885 tokens to every session, about $0.0094 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.
Other instructions, from other repositories
trueforge AGENTS.md
AGENTS.md instructions for truefoundry/trueforge, a project described as: The open-source agent harness - the runtime layer that turns an LLM into a working agent.
relay AGENTS.md
Instructions for AgentWorkforce/relay, covering git workflow rules, never push directly to main, correct workflow, ... do work .. and stop here - let user merge.
LeAgent AGENTS.md
Instructions for vixues/LeAgent, covering leagent development guidelines, project overview, architecture, execution topology (one kernel, many ingresses) and surface map (where things live).
claudeclaw CLAUDE.md
Instructions for sbusso/claudeclaw, covering claudeclaw, entry points, modes, directory = instance and architecture.
grix AGENTS.md
Instructions for askie/grix, covering grix agent guide, repository boundaries, required workflows, shared agent configuration and cross-component contracts.
neeko AGENTS.md
Instructions for tincopper/neeko, covering neeko — repository guidelines, 项目概览, 目录结构, 前端（feature-based 架构） and 后端（domain-driven 模块化架构）.