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/strands-labs/robots/agents-mdgit clone --depth 1 https://github.com/strands-labs/robotsWhat 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 | $0.42935 | $0.42935 |
| Opus 5 | $0.21468 | $0.21468 |
| Sonnet 5 | $0.08587 | $0.08587 |
| Haiku 4.5 | $0.04294 | $0.04294 |
Grade A, and why
robots AGENTS.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 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
into `subprocess.run`, `subprocess.Popen`, MJCF / XML interpolation, or filesystem How it starts
The opening of the file, as written. The whole thing — 2,400 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - strands-labs/robots
Overview
strands-robots is a robot control library for Strands Agents. It provides policy inference, teleoperation, calibration, and simulation tools for physical robots.
Project Dashboard
Board: https://github.com/orgs/strands-labs/projects/2
Project ID: PVT_kwDOD151Fs4BSRJP
RULE: ALWAYS use the project board to track work. When creating follow-up items, create GitHub issues and add them to this board with Status + Priority set. Never track work only in local markdown - the board is the source of truth.
Repository Structure
strands_robots/
├── policies/ # Policy providers (pluggable via registry)
│ ├── base.py # Abstract Policy base class
│ ├── factory.py # create_policy() factory + registry
│ ├── mock.py # MockPolicy for testing
│ ├── groot/ # NVIDIA GR00T N1.5/N1.6/N1.7 inference
│ │ ├── policy.py # Gr00tPolicy (ZMQ + HTTP modes)
│ │ ├── client.py # Gr00tInferenceClient
│ │ ├── data_config.py # Gr00tDataConfig + ModalityConfig
│ │ └── data_configs.json # 25 robot embodiment configs
│ └── lerobot_local/ # HuggingFace LeRobot direct inference
│ ├── policy.py # LerobotLocalPolicy (RTC support)
│ ├── processor.py # ProcessorBridge (pre/post pipelines)
│ └── resolution.py # Policy class resolution (v0.4/v0.5)
├── registry/ # JSON registry for policy discovery
├── tools/ # Strands @tool functions
│ ├── gr00t_inference.py # GR00T inference tool
│ ├── lerobot_calibrate.py
│ ├── lerobot_camera.py
│ ├── lerobot_teleoperate.py
│ ├── pose_tool.py
│ └── serial_tool.py
├── robot.py # Core Robot class
└── utils.py # Shared utilities (require_optional, etc.)
tests/ # Unit tests (run with: hatch run test)
tests_integ/ # Integration tests (run with: hatch run test-integ)
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 · 2,400 lines · 42,935 tokens per session scan A c1d91c3fd20e
robots AGENTS.md is an instructions file published in the GitHub repository strands-labs/robots (143 stars, last pushed 2d ago), licensed Apache-2.0. It adds 42,935 tokens to every session, about $0.2147 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
stack-chan AGENTS.md
Instructions for stack-chan/stack-chan, covering agents.md, project overview, core architecture, modular component system and key directories.
agent-sop AGENTS.md
Instructions for strands-agents/agent-sop, covering agents.md - ai assistant context for agent sop project, project overview, directory structure, development patterns and sop format structure.
strands-sglang AGENTS.md
Instructions for strands-rl/strands-sglang, covering agents.md, project overview, commands, setup and linting.
job-search-agent AGENTS.md
Instructions for deeheber/job-search-agent, covering job search agent and conventions.
sdk-python AGENTS.md
Instructions for strands-compose/sdk-python, covering strands-compose — agent instructions, response style, do not, still required and read the skill first — mandatory.
devduck AGENTS.md
Instructions for cagataycali/devduck, covering agents.md — devduck, project: devduck, architecture, key design patterns and self-awareness.