Borrowing it
Nothing to install: this file belongs to redai-infra/Relax. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/redai-infra/Relax/main/CLAUDE.mdgit clone --depth 1 https://github.com/redai-infra/RelaxWrote 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.
[](https://agentmods.dev/instructions/redai-infra/relax/claude-md)<a href="https://agentmods.dev/instructions/redai-infra/relax/claude-md"><img src="https://agentmods.dev/badge/instructions/redai-infra/relax/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00906 | $0.00906 |
| Opus 5 | $0.00453 | $0.00453 |
| Sonnet 5 | $0.00181 | $0.00181 |
| Haiku 4.5 | $0.00091 | $0.00091 |
Grade A, and why
Relax 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 8d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Relax is a high-performance RL post-training engine for multi-modal and agentic AI, built on Ray Serve, Megatron-LM, and SGLang. It supports algorithms like GRPO, DAPO, GSPO, SAPO, and On-Policy Distillation across Qwen3/Qwen3-VL/Qwen3-Omni models.
Common Commands
pip install -e . # Install package in dev mode
pip install -r requirements.txt # Install dependencies
make format # Run pre-commit (ruff, isort, mdformat, docformatter)
make lint # Run flake8 + mypy on relax/
make test # Run pytest tests/
pytest tests/test_foo.py::test_bar # Run a single test
pre-commit run --all-files # Lint + format (must run before commits)
make docs-dev # Start VitePress docs dev server
Architecture
Three-layer service-oriented architecture on Ray Serve:
- Controller (
relax/core/controller.py) - Top-level training loop, service orchestration, health monitoring - Service (
relax/core/service.py) - Lifecycle management, GPU placement groups, Ray Serve deployment wrapper - Components (
relax/components/) - Concrete RL services: Actor, Critic, Rollout, Advantages, GenRM, ActorFwd
Two execution modes:
- Colocate (Sync) - Actor & Rollout time-share same GPUs
- Fully Async - Independent GPU clusters per role with streaming data via TransferQueue
Key subsystems:
- Backends (
relax/backends/) - Megatron training backend (TP/PP/CP/EP) and SGLang inference engine - Engine (
relax/engine/) - Rollout generation, pluggable reward functions (engine/rewards/), data filtering, request routing - Distributed (
relax/distributed/) - Ray cluster management, DCS (NCCL broadcast-based weight sync) - Algorithm Registry (
relax/core/registry.py) - Maps algorithm names to component roles
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.
- 8d ago First seen · 83 lines · 906 tokens per session scan A 79166d89e270
Relax CLAUDE.md is an instructions file published in the GitHub repository redai-infra/Relax (580 stars, last pushed 10d ago), licensed Apache-2.0. It adds 906 tokens to every session, about $0.0045 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
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.
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).
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.
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.
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).
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.