What is robots AGENTS.md?

A project guide for strands-labs/robots, a Python library for controlling, calibrating, simulating, and running policies on physical robots.

It helps maintain robot-control code, work with policy providers such as GR00T and LeRobot, and track follow-up work in GitHub.

It gives developers a shared reference for the repository layout, development process, and project-board rules.

How strands-labs/robots configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to strands-labs/robots. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/strands-labs/robots/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/strands-labs/robots

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/strands-labs/robots/agents-md/github.svg)](https://agentmods.dev/instructions/strands-labs/robots/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/strands-labs/robots/agents-md"><img src="https://agentmods.dev/badge/instructions/strands-labs/robots/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/strands-labs/robots/agents-md"><img src="https://agentmods.dev/badge/instructions/strands-labs/robots/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,112 This file is loaded in full into every session.

When invoked 4,112 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.04112	$0.04112
Opus 5.5	$0.01645	$0.01645
Sonnet 5.5	$0.00822	$0.00822
Haiku 4.5	$0.00411	$0.00411

Measured today against content hash 54a2047360fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

robots 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 today.

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 · 224 lines

How it starts

The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guide for coding agents (and people) working on strands-robots, a Python library for building robots. Read this first. The tests enforce most of the rules below, so a rule broken here is a red CI run.

What the library is

The same code drives a simulated robot or a real one. The package exports exactly eleven names plus __version__ (strands_robots/__init__.py, locked by tests/test_public_surface.py):

Name	Is
`Simulation`	One world: MuJoCo on CPU, Isaac Sim or Newton (MuJoCo-Warp) on GPU
`Robot`	A body in a world, or a real robot through a driver (optionally with a digital twin)
`Policy`	Turns an `Observation` into an `Action` (functions, ONNX, LeRobot, replay)
`Mesh`	Robots on other machines over Zenoh or AWS IoT Core
`Body`, `Description`	The body protocol and a robot's model facts
`Observation`, `Action`, `JointState`, `Pose`	Plain data types
`RequestRefused`	The one refusal error (a `PermissionError`)

Everything else (Scene, Backend, RunResult, Units, Calibration, ...) is imported from its subpackage, never from the top level.

Setup

uv venv -p 3.12 && source .venv/bin/activate
uv pip install -e ".[all,dev]"
uv pip install "lerobot[remote,feetech,dataset] @ git+https://github.com/huggingface/lerobot@main"

Python 3.10+ for the package; CI, mypy and LeRobot use 3.12.
[all] is every extra except isaac, newton and dev. Adding an extra means adding it to all (tests/test_install_lines.py).
LeRobot comes from its main branch and is never a wheel dependency (a wheel can't carry a git ref). The one line lives in strands_robots/_extras.py (LEROBOT), the hatch lerobot env and the docs; a test keeps them equal.
Headless Linux: set MUJOCO_GL=egl (CI does) or let _gl.ensure_gl() pick egl or osmesa. Import strands_robots before mujoco.

Run what CI runs

The required check is call-test-lint / Test and Lint (.github/workflows/test-lint.yml). Locally:

Read the full file on GitHub · 224 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.

today Changed · +4 lines · +109 tokens per session 54a2047360fd
yesterday Changed · +4 lines · +93 tokens per session f7cc59ff74bc
2d ago Changed · -84 lines · -816 tokens per session d7248415cebd
1mo ago Changed · +11 tokens per session 8763e1cf74d5
1mo ago Changed · -2,387 lines · -44,457 tokens per session 769a22da83ac
1mo ago Changed · +4 lines · +529 tokens per session ca3e50e27ed9
2mo ago Changed · +68 lines · +1,161 tokens per session aa10485df683
2mo ago Changed · +84 lines · +1,501 tokens per session 0ba3144f9503
2mo ago Changed · +51 lines · +952 tokens per session 6c03f8a58ea0
2mo ago First seen · 2,480 lines · 45,029 tokens per session scan A 278dd277ab7d

Subscribe to this mod's changes

robots AGENTS.md is an instructions file published in the GitHub repository strands-labs/robots (208 stars, last pushed yesterday), licensed Apache-2.0. It adds 4,112 tokens to every session, about $0.0164 per session on Opus 5.5. 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.

Hardware and IoT Languages Python robots strands-agents strands-labs vision-language-action world-foundation-models

robots AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
robots AGENTS.mdstrands-labs/robots	Instructions file	208	yesterday	Apache-2.0	A	4,112	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

robots: Instructions file for Codex