What is OpenEnv CLAUDE.md?

A set of instructions for using Claude Code in the Hugging Face OpenEnv repository. It explains the project structure, development workflow, design rules, and team setup.

Use it when starting work in OpenEnv, choosing between development modes, reviewing project guidance, or installing the repository's Git hooks.

It gives new contributors a shared way to understand the repository and make changes that follow its documented rules.

OpenEnv CLAUDE.md — Instructions file by huggingface

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/huggingface/openenv/claude-md

Clone the repo

git clone --depth 1 https://github.com/huggingface/OpenEnv

Per session 2,936 This file is loaded in full into every session.

When invoked 2,936 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.

Model	Per session	Once invoked
Fable 5	$0.02936	$0.02936
Opus 5	$0.01468	$0.01468
Sonnet 5	$0.00587	$0.00587
Haiku 4.5	$0.00294	$0.00294

Measured yesterday against content hash bc01c938b866, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

OpenEnv 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 yesterday.

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 · 306 lines

How it starts

The opening of the file, as written. The whole thing — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code when working with this repository.

New Here? Start With These

README.md - Project overview, architecture, quick start
REPO_WALKTHROUGH.md - Directory structure with annotations
PRINCIPLES.md - Design principles and trade-offs
INVARIANTS.md - Rules that must never be violated
envs/echo_env/ - Reference implementation to study

Agentic-First Workflow

OpenEnv uses Claude Code as the primary development tool. We follow a two-phase model:

Design/Alignment (human-owned): RFCs, principles, trade-off decisions
Implementation (Claude-owned): The mechanical loop of coding and testing
Review (collaborative): Claude catches bugs, flags alignment questions for humans

Getting Started

Skills and agents are auto-discovered when you run Claude Code in this repo:

git clone https://github.com/huggingface/OpenEnv
cd OpenEnv
# Install git hooks for the team
bash .claude/hooks/install.sh
# Run Claude Code - skills and agents are automatically available

Verify with /agents or ask "what skills are available?"

Two Development Modes

OpenEnv supports two development modes:

Explore Mode (Main Repo)

When working in the main repository clone, direct edits are allowed:

Quick exploration and prototyping
Small fixes that don't need TDD workflow
Documentation updates

TDD Mode (Opt-In)

TDD is activated by /work-on-issue, which writes a .tdd-session.json marker. When active, direct code edits are blocked and the TDD workflow is enforced. Manually created worktrees do NOT activate TDD — only /work-on-issue does.

Say "skip TDD" to bypass blocking
Run bash .claude/hooks/tdd-deactivate.sh to turn off TDD enforcement

Creating a Worktree

# Worktree without TDD enforcement (free editing)
.claude/scripts/worktree-create.sh add-feature
cd .worktrees/add-feature

# Worktree WITH TDD enforcement (via /work-on-issue)
/work-on-issue #42

Read the full file on GitHub · 306 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.

yesterday First seen · 306 lines · 2,936 tokens per session scan A bc01c938b866

Subscribe to this mod's changes

OpenEnv CLAUDE.md is an instructions file published in the GitHub repository huggingface/OpenEnv (2,531 stars, last pushed 4d ago), licensed BSD-3-Clause. It adds 2,936 tokens to every session, about $0.0147 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.

Git and workflow Productivity

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

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

OpenEnv CLAUDE.md