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 skills add ttktjmt/mjswan --skill mjlab-to-mjswangit clone --depth 1 https://github.com/ttktjmt/mjswanWrote 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/skills/ttktjmt/mjswan/mjlab-to-mjswan)<a href="https://agentmods.dev/skills/ttktjmt/mjswan/mjlab-to-mjswan"><img src="https://agentmods.dev/badge/skills/ttktjmt/mjswan/mjlab-to-mjswan/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/skills/ttktjmt/mjswan/mjlab-to-mjswan"><img src="https://agentmods.dev/badge/skills/ttktjmt/mjswan/mjlab-to-mjswan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.04228 |
| Opus 5 | $0.00000 | $0.02114 |
| Sonnet 5 | $0.00000 | $0.00846 |
| Haiku 4.5 | $0.00000 | $0.00423 |
Grade A, and why
mjlab-to-mjswan 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 5d 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Port one mjlab task from a target repo into a browser app built by mjswan. The target is any repo that registers mjlab tasks, given as a local path or a GitHub URL.
Scope. Inside the target repo everything you write stays on the Python side: no TypeScript (ts_src), no ViewerConfig. mjswan itself is edited in exactly one case: a missing capability that is generic rather than task-specific, which step 8 turns into a pull request.
Ground rules
- mjswan reimplements none of mjlab's term functions: a task's real observation / termination / event / command functions are traced to ONNX at build time and run in the browser beside the policy. A fix therefore means making mjlab's own function traceable, never rewriting its math.
- When something fails, read the exception in full, then the module it came from in the installed package:
python -c "import mjswan, pathlib; print(pathlib.Path(mjswan.__file__).parent)". That source is the only current truth. - Two fix attempts per term, then record it as skipped and move on. A partial port that builds and passes parity is the deliverable; all-or-nothing is not.
1. Acquire the target
A GitHub URL → git clone <url> ./<repo-name>, then work inside it. A local path → use it as is.
Then make mjswan importable from the same interpreter that can import the target's task registrations:
- Repo already has an environment → add to it:
uv pip install mjswan torch onnxruntime. - Fresh clone with nothing →
uv venv && uv pip install -e . && uv pip install mjswan torch onnxruntime. - No
uvavailable → install into the interpreter that already runs the target, against its ownsys.prefix.
mjswan pins mujoco exactly and bounds requires-python. If the install fails on either, stop and report the resolver's output verbatim: resolving it is the user's call, not yours.
2. Find the task ids
Registration happens as an import side effect, and every repo does it differently: mjlab.tasks, a <pkg>/tasks/__init__.py, a src/tasks/ on sys.path, or a bootstrap_*() function that must be called, sometimes only after an env var or a data file is in place.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago Changed · +16 lines d5ecc52b5941
- 11d ago First seen · 248 lines · 0 tokens per session scan A 1ca7419ab80e
mjlab-to-mjswan is a skill published in the GitHub repository ttktjmt/mjswan (342 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 4,228 tokens. 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 2026-09-01.
Other skills, from other repositories
grpo-rl-training
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training.
miles-rl-training
Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.
torchforge-rl-training
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.
verl-rl-training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
sdf
SDFormat/SDF model and world authoring, validation, and simulator handoff. Use for .sdf files, SDFormat XML, models, worlds, links, joints, poses, frames, inertials, visual/collision geometry, mesh URIs, sensors, lights, physics, plugins, includes, Gazebo, static SDF review, or simulator-specific metadata. Do not use…
tinker-fine-tuning
Provides guidance for fine-tuning LLMs using the Tinker cloud training API from Thinking Machines Lab. Use when running supervised fine-tuning, reinforcement learning (GRPO/PPO), or LoRA training on cloud GPUs via Tinker's managed infrastructure instead of local compute.