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 skills/abdelstark/worldforge/optional-runtime-smokesnpx skills add AbdelStark/worldforge --skill optional-runtime-smokesgit clone --depth 1 https://github.com/AbdelStark/worldforgeWhat 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 | $0.00059 | $0.00737 |
| Opus 5 | $0.00030 | $0.00368 |
| Sonnet 5 | $0.00012 | $0.00147 |
| Haiku 4.5 | $0.00006 | $0.00074 |
Grade A, and why
optional-runtime-smokes 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 3d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optional Runtime Smokes
Runtime Boundary
- Checkout-safe demos may inject deterministic runtimes. Do not describe them as neural inference.
- Live smokes require host-installed packages, checkpoints, credentials, and task-specific observation/action translators.
- Keep
stable_worldmodel, torch, LeRobot, Isaac GR00T, CUDA, TensorRT, datasets, checkpoints, and robot packages out ofproject.dependencies. - Never commit downloaded assets, checkpoints, datasets, cache directories, or runtime-specific credentials.
- Do not pad, project, or reinterpret mismatched action spaces inside WorldForge.
- Keep smoke output safe to attach unless it is explicitly local-only; redact cache roots, signed URLs, tokens, controller telemetry, and checkpoint bytes.
Command Selection
| Need | Start here |
|---|---|
| LeWorldModel adapter/planner path in a clean checkout | uv run worldforge-demo-leworldmodel |
| PushT robotics dependency/checkpoint status | scripts/robotics-showcase --health-only |
| Real LeWorldModel checkpoint smoke | uv run --python 3.13 --with "stable-worldmodel[train] @ git+https://github.com/galilai-group/stable-worldmodel.git" --with "datasets>=2.21" worldforge-smoke-leworldmodel ... |
| Build LeWorldModel object checkpoint | worldforge-build-leworldmodel-checkpoint with host-owned runtime deps |
| GR00T policy smoke | host-owned Isaac GR00T server or reachable remote policy server |
| LeRobot policy smoke | host-owned LeRobot install, policy checkpoint, observation builder, action translator |
Rules
scripts/robotics-showcase --health-onlyis non-mutating; it must not auto-build or download missing checkpoints.- Use
--revisionorLEWORLDMODEL_REVISIONto pin Hugging Face asset resolution. - Keep
torch.load(..., weights_only=True)unless a trusted legacy artifact explicitly requires--allow-unsafe-pickle. - Keep warning filters narrow. Use
WORLDFORGE_SHOW_RUNTIME_WARNINGS=1when raw third-party stderr is needed.
Definition Of Done
What ships with it
1 file 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.
- 3d ago First seen · 51 lines · 59 tokens per session scan A 0d633584ed86
optional-runtime-smokes is a skill published in the GitHub repository AbdelStark/worldforge (108 stars, last pushed 24d ago), licensed MIT. It adds 59 tokens to every session and 737 once invoked, about $0.0003 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 skills, from other repositories
mood
Tracks the USER's mood only — signals + synthesized decision from camera/voice/telegram. Do NOT use for emotion commands directed at the device ("show sad", "be happy", bare "sad now"); those go through emotion/SKILL.md and are never logged here. Music/wellbeing skills consume the latest decision.
hugging-face-trackio
Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API) or retrieving/analyzing logged metrics (CLI). Supports real-time dashboard visualization, HF Space syncing, and JSON output for automation.
marimo-pair
Work inside the user's live marimo notebook from the code editor: run Python in the same kernel the user does, inspect live notebook state, and commit durable notebook changes through code mode. Use whenever you create, analyze, or improve the user's marimo notebook.
physicsnemo-shard-tensor
Official NVIDIA-authored guidance for PhysicsNeMo ShardTensor domain parallelism — integrate domain parallelism into training/inference scripts (new or existing) with DDP or FSDP2, write and register shard patches to enable new layers/ops, and bootstrap multi-GPU correctness tests. Use when working with ShardTensor…
physicsnemo-discover
Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting, downscaling, physics-informed, inverse, generative). Points at existing files via live repo search; never writes code. Do NOT use for installation or environment…
pysr
Use when fitting equations to data with PySR or SymbolicRegression.jl, when a user wants an interpretable formula, symbolic model, scaling law, or empirical relation discovered from numeric data, or when debugging a PySR search that is slow, stuck, or giving poor equations.