microduck_rl provides reinforcement-learning environments for training walking and recovery policies for Microduck, an 800-gram, 25-centimetre bipedal robot, in MuJoCo through mjlab. It trains policies with PPO in simulation, including actuator and terrain variation, then exports them to ONNX for deployment on the physical robot.
Borrowing it
Nothing to install: this file belongs to pollen-robotics/microduck_rl. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/pollen-robotics/microduck_rl/develop/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/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.
<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="Reviewed on agentmods" width="80" 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 5.1 | $0.05326 | $0.05326 |
| Opus 5.5 | $0.02130 | $0.02130 |
| Sonnet 5.5 | $0.01065 | $0.01065 |
| Haiku 4.5 | $0.00533 | $0.00533 |
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 10d 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 — 306 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 publish --task <TASK_ID> --wandb-run-path <...> --checkpoint N --repo <user>/microduck-<name> --kind episodic --duration-s 4.0
# → HF Hub repo (policy.onnx + schema-2 manifest.json + README) the daemon loads via `robotctl policy add`
# add --share-training to also bundle the training checkpoint (opt-in, see below)
uv run share-training --wandb-run-path <...> --checkpoint N [--onnx hf://<policy-repo>/<file>.onnx]
# → training bundle (full .pt + provenance + teachers) in <owner>/microduck-training
uv run train <TASK_ID> --init-checkpoint hf://<owner>/microduck-training/bundles/<exp>/<run>_<iter>
# resume from a bundle (MICRODUCK_WARM_START=1 to warm-start another task)
uv run scripts/infer_policy.py --walking out.onnx # CPU MuJoCo deployment rehearsal (BAM M6 actuators as in training; --no-bam = XML PD)
uv run --with pytest pytest tests/
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.
- 10d ago Changed · +36 lines · +747 tokens per session f49caec51ff9
- 1mo ago Changed · +1 lines · +45 tokens per session 2230a98be94b
- 1mo ago Changed · +17 lines · +334 tokens per session 4493d2d72d83
- 2mo ago Changed · +6 lines · +200 tokens per session f7d4ae83ee74
- 2mo 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 (2,817 stars, last pushed yesterday), licensed Apache-2.0. It adds 5,326 tokens to every session, about $0.0213 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.
microduck_rl AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| microduck_rl AGENTS.mdpollen-robotics/microduck_rl | Instructions file | 2.8k | yesterday | Apache-2.0 | A | 5,326 | 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 |