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 NVlabs/ASPIRE --skill yam-motion-plannergit clone --depth 1 https://github.com/NVlabs/ASPIREWrote 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/nvlabs/aspire/yam-motion-planner)<a href="https://agentmods.dev/skills/nvlabs/aspire/yam-motion-planner"><img src="https://agentmods.dev/badge/skills/nvlabs/aspire/yam-motion-planner/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/nvlabs/aspire/yam-motion-planner"><img src="https://agentmods.dev/badge/skills/nvlabs/aspire/yam-motion-planner.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 | $0.00042 | $0.00591 |
| Opus 5 | $0.00021 | $0.00296 |
| Sonnet 5 | $0.00008 | $0.00118 |
| Haiku 4.5 | $0.00004 | $0.00059 |
Grade A, and why
yam-motion-planner 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 11d 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.
What it actually says
YAM Motion Planner
cuRobo is sensitive to the real start state. A no-motion/pre-motion plan can pass, then a real run can fail because physical execution replans from the actual EEF pose, joint state, gripper load, or a slightly different scene pose.
When cuRobo fails:
- Inspect the current scene, robot state, failed target pose, and failed stage.
- Decide whether the target is physically unreasonable or just planner-sensitive.
- If the motion is feasible, do not treat one IK/path failure as final.
- Try nearby target offsets and extra waypoints that make the same task easier: retreat lanes, lift-before-shift, shift-before-approach, lower/higher staging poses, or less extreme rack/bin/place coordinates.
- Preview from the current robot state, not only from an ideal scripted state.
- Prefer waypoint sets that pass perturbation sweeps, not just one clean pass.
Robustness sweep pattern:
- Perturb candidate waypoints and final targets by small XYZ/RPY offsets that represent likely real-world variance.
- Include start-state sensitivity when possible: preview from the current arm posture, or rerun previews after moving to the actual preceding waypoint.
- Record pass/fail rate, first failed stage, pose, and planner error in
logs/<run>/plans/. - Pick the candidate with high pass rate, clear margins from obstacles, and simple task semantics.
Useful sweep examples:
legacy_codes/kitkat_trash_waypoint_robustness_sweep.pylegacy_codes/kitkat_handover_clearance_waypoint_sweep.pylegacy_codes/bottle_rack_waypoint_robustness_sweep.pylegacy_codes/bottle_fixed_pour_waypoint_robustness_sweep.py
Typical useful perturbations:
- placement/drop targets:
x,y,z +/- 2-5 cm - staging/retreat waypoints:
x,y,z +/- 3-8 cm - orientation: yaw/roll/pitch variants near the intended gripper axis
- approach order: split compound moves into one-axis waypoints
If a real run stops after a cuRobo failure while holding an object, first reason from the current scene. If the object is still safely held, plan a held-object recovery from the current EEF pose: preview nearby rack/bin/table targets, add intermediate waypoints, release, retreat, then home/open. Ask the human to reset only if the scene is physically broken or unsafe for the robot to fix.
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.
- 11d ago First seen · 53 lines · 42 tokens per session scan A 344f09631981
yam-motion-planner is a skill published in the GitHub repository NVlabs/ASPIRE (143 stars, last pushed 9d ago), licensed Apache-2.0. It adds 42 tokens to every session and 591 once invoked, about $0.0002 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
gke-ai-troubleshooting-tpu-dynamic-slices-monitoring
Monitors, troubleshoots, and manages GKE TPU Dynamic Slices custom resources. Use when checking TPU slice lifecycle states, troubleshooting slice provisioning failures, validating single-slice or multi-slice (JobSet) workload manifests, or safely patching stuck finalizers and disabling the slice controller. Don't use…
gke-ai-troubleshooting-tpu-vbar-oom
Diagnoses and prevents vbarcontrolagent segfaults, out-of-memory (OOM) errors, and TPU device initialization failures on TPU v6e nodes in GKE caused by race conditions during TPU device resets or high-frequency metrics polling. Use when troubleshooting vbarcontrolagent crashes, memory cgroup OOMs in serial console…
competition-firmware-layout
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for firmware images, partition tables, boot chains, update packages, extracted filesystems, embedded configs, and device-facing trust boundaries. Use when the user asks to unpack firmware, map partition layout, inspect bootloader or init…
doca-flow
Build and debug DOCA Flow applications on supported NVIDIA NICs/DPUs: define match/action pipes, initialize ports and representors, choose forwarding targets, validate pipes before hardware programming, read counters, match the Flow version to the installed DOCA release, and diagnose Flow API errors. Trigger on DOCA…
diagnose-driver-install
Diagnose NVIDIA driver installation failures on DeepOps-managed nodes — nvidia-smi errors, "No devices were found", DKMS build failures, or GPU pods crash-looping. Use before reinstalling anything.
catc-troubleshoot
Catalyst Center troubleshooting workflows - device unreachable investigation, client connectivity issues, interface down analysis, site-wide outage triage, wireless roaming problems, integration with pyATS for CLI-level diagnostics. Use when a device is unreachable, a user reports connectivity problems, an interface…