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/huggingface/lelab/claude-mdgit clone --depth 1 https://github.com/huggingface/leLabWhat 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 | $0.01656 | $0.01656 |
| Opus 5 | $0.00828 | $0.00828 |
| Sonnet 5 | $0.00331 | $0.00331 |
| Haiku 4.5 | $0.00166 | $0.00166 |
Grade A, and why
leLab CLAUDE.md scanned grade A with 1 finding 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Run the Python tests with `pytest` (config in [pyproject.toml](pyproject.toml); install dev deps via `pip install -e ".[test]"`). Tests live in [tests/](tests/) and cover request schemas, pure helpers, and idle/mutex bra How it starts
The opening of the file, as written. The whole thing — 75 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.
Repository purpose
LeLab is a FastAPI + React web interface wrapping the LeRobot framework for the SO-101 leader/follower arm. It exposes teleoperation, dataset recording, calibration, replay, and training as HTTP/WebSocket endpoints, replacing LeRobot's CLI + keyboard-driven flows.
The frontend (React + Vite) lives in frontend/. The built bundle in frontend/dist/ is committed and shipped inside the Python wheel as package data (frontend.__init__.py makes setuptools treat it as a package); lelab/server.py mounts it as StaticFiles at / so a single lelab process serves both API and UI on :8000. The frontend/ directory is also force-pushed to the LeLab HF Space by .github/workflows/sync_space.yml — that's a separate runtime; the Space builds the Dockerfile (which runs npm run build again, so committed dist/ doesn't matter to it).
Common commands
Install (editable, requires Python ≥3.10):
pip install -e .
lerobot is pinned to a release tag on huggingface/lerobot (currently v0.6.0, see pyproject.toml) — installed from git rather than PyPI because the published wheels don't expose the lerobot-rollout script that lelab/rollout.py shells out to. Bump the tag when you want a newer upstream release; expect import-path drift (e.g. lerobot.configs.dataset, lerobot.utils.feature_utils, lerobot.common.control_utils) and adjust call sites accordingly.
Run servers (entry point defined in pyproject.toml):
lelab # uvicorn on :8000, serves built frontend at /, opens browser
lelab --dev # spawns Vite dev (:8080) + uvicorn --reload (:8000), opens browser to :8080
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.
- 3d ago First seen · 75 lines · 1,656 tokens per session scan A bedf4aa75216
leLab CLAUDE.md is an instructions file published in the GitHub repository huggingface/leLab (159 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,656 tokens to every session, about $0.0083 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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).
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.