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/pollen-robotics/microduck_rl/agents-mdgit clone --depth 1 https://github.com/pollen-robotics/microduck_rlWrote 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/pollen-robotics/microduck_rl/agents-md)<a href="https://agentmods.dev/instructions/pollen-robotics/microduck_rl/agents-md"><img src="https://agentmods.dev/badge/instructions/pollen-robotics/microduck_rl/agents-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 | $0.04000 | $0.04000 |
| Opus 5 | $0.02000 | $0.02000 |
| Sonnet 5 | $0.00800 | $0.00800 |
| Haiku 4.5 | $0.00400 | $0.00400 |
Grade A, and why
microduck_rl 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 4d 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
RL training environments for Microduck — a ~800 g, ~25 cm tall bipedal
robot with 14 Dynamixel XL330 servos — built on mjlab
(MuJoCo Warp) with PPO (rsl_rl). Policies are trained here at 50 Hz, exported to
ONNX, and deployed by the runtime in the pollen-robotics/microduck repo on
the real robot. Sim2real transfer
is the whole point: every convention below exists because breaking it produced a
policy that worked in the viewer and failed on hardware.
Commands
uv run list-envs # live task registry
uv run train <TASK_ID> --env.scene.num-envs 4096 # train (add --hf-jobs for Hugging Face Jobs)
uv run train <TASK_ID> --env.scene.num-envs 64 --agent.max_iterations 5 # SMOKE TEST — always run first
uv run play <TASK_ID> --wandb-run-path <entity/project/run_id>
uv run scripts/export.py <TASK_ID> --wandb-run-path <...> # → ONNX (bakes obs normalizer — mandatory path)
uv run scripts/infer_policy.py --walking out.onnx # CPU MuJoCo deployment rehearsal
uv run --with pytest pytest tests/
A 5-iteration smoke test at 64 envs catches ~95% of config errors for cents. Never launch a long run without one.
Repo map
src/mjlab_microduck/tasks/mdp.py— ALL custom MDP functions (rewards, events, observations, commands, curricula). Add new functions here, grouped by task.src/mjlab_microduck/tasks/microduck_*_env_cfg.py— one cfg module per task family.microduck_velocity_env_cfg.pyis the main walking recipe AND the shared base (robot, DR, obs, commands) other envs build on or mirror.src/mjlab_microduck/tasks/__init__.py— task registration (base +-Backlash-variants).src/mjlab_microduck/tasks/backlash.py— wraps any env cfg into its backlash twin.src/mjlab_microduck/robot/microduck_constants.py— robot cfgs, HOME frame, BAM actuator cfg.src/mjlab_microduck/robot/microduck/— MJCF exports from Onshape (onshape-to-robot, oneconfig_mjcf_*.jsonper model) + scenes +add_backlash.py.src/mjlab_microduck/actuator/friction_dr_bam.py— BAM actuator + friction DR + backlash encoder.scripts/— export, infer, sim2real comparison, wandb helpers.tests/— cfg-invariant and mdp-function regression tests (CPU, no GPU needed).
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.
- 4d ago First seen · 246 lines · 4,000 tokens per session scan A aceb94476f03
microduck_rl AGENTS.md is an instructions file published in the GitHub repository pollen-robotics/microduck_rl (724 stars, last pushed 4d ago), licensed Apache-2.0. It adds 4,000 tokens to every session, about $0.0200 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
firmware CLAUDE.md
Claude Code instructions for OpenIPC/firmware, covering claude.md, what this is, before you start: is this the right repository?, build and common tasks.
Tutorial_AwesomeModernCPP AGENTS.md
AGENTS.md instructions for Awesome-Embedded-Learning-Studio/Tutorial_AwesomeModernCPP, covering agents.md, 这是什么, 通用 essentials(所有 agent 必读) and 你来做什么?(按场景路由).
brilliant_sdk AGENTS.md
Instructions for brilliantlabsAR/brilliant_sdk, covering brilliant sdk — agent guide, how an app works (the pattern behind everything), minimal reading paths, verify without hardware and testing.
NeoMind CLAUDE.md
Claude Code instructions for camthink-ai/NeoMind, covering neomind — edge ai platform for iot, development commands, ecosystem repositories, extension package contract (.nep) and device type template contract (json).
zmk-config AGENTS.md
AGENTS.md instructions for urob/zmk-config, covering customization guide, ground rules, how the multi-board layout works, adding a new board and where to change what.
ext-apps CLAUDE.md
Claude Code instructions for modelcontextprotocol/ext-apps, a project described as: Official repo for spec & SDK of MCP Apps protocol - standard for UIs embedded AI chatbots, served by MCP servers.