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 | $0.05407 |
| Opus 5.5 | $0.00000 | $0.02163 |
| Sonnet 5.5 | $0.00000 | $0.01081 |
| Haiku 4.5 | $0.00000 | $0.00541 |
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 9d 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 — 283 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. What this pipeline needs is the mjlab extra (mjlab + torch: add_scene_mjlab, term tracing, .pt conversion) plus onnxruntime, which step 7 runs the exported graphs under:
- Repo already has an environment → add to it:
uv pip install "mjswan[mjlab]" onnxruntime. - Fresh clone with nothing →
uv venv && uv pip install -e . && uv pip install "mjswan[mjlab]" onnxruntime. - No
uvavailable → install into the interpreter that already runs the target, against its ownsys.prefix.
Every source is its own extra and import mjswan touches none of them, so install only the one the checkpoints come from: wandb for a W&B run path, hf for anything fetched from the Hub, e.g. "mjswan[mjlab,wandb]".
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.
- 9d ago Changed · +1 lines a0ef7d01554e
- 12d ago Changed · +12 lines 67ad89a74855
- 14d ago Changed · +2 lines e91c5b5af37c
- 1mo ago Changed · +4 lines cfc7905c039a
- 1mo ago Changed · +16 lines d5ecc52b5941
- 1mo 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 (362 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 5,407 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
dart-model-upgrade
DART Model Upgrade: audit and update DART AI infrastructure for model or coding-agent upgrades, including named models, reasoning modes, migrations, compatibility reviews, and visual simulation-debugging evaluations.
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.
cdf-autonomous-vehicle-dataset-generation
Prepare payloads, run and monitor the Autonomous Vehicle Dataset Generation Airflow workflow, and inspect results for driving-clip retrieval and Cosmos3-Nano variants. Existing clips with no retrieval use cdf-video-data-augmentation; seed-image event or anomaly generation uses cdf-event-video-generation.
nemotron-retrieval-recipes
Use for Nemotron embed/rerank recipes, including Nemotron 3.5 multimodal SDG, tuning, evaluation, and deployment. Not for generic retrieval.
nemotron-nano3
Reference desk for Nemotron 3 Nano / Llama-Nemotron Nano 3 — architecture, training data, recipes, evaluation, quantization, deployment. Use when the user asks facts about the model rather than building a pipeline.