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/nvlabs/aspire/yam-robot-debuggingnpx skills add NVlabs/ASPIRE --skill yam-robot-debugginggit 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-robot-debugging)<a href="https://agentmods.dev/skills/nvlabs/aspire/yam-robot-debugging"><img src="https://agentmods.dev/badge/skills/nvlabs/aspire/yam-robot-debugging.svg" alt="Measured on agentmods" 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 | $0.00038 | $0.00476 |
| Opus 5 | $0.00019 | $0.00238 |
| Sonnet 5 | $0.00008 | $0.00095 |
| Haiku 4.5 | $0.00004 | $0.00048 |
Grade A, and why
yam-robot-debugging 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.
What it actually says
YAM Robot Debugging
Work from the Aspire real-robot workspace (aspire/real). Read its AGENTS.md
contract first; paths below are relative to that directory.
Act as a robotics debugging engineer. For a user-requested physical task, run the saved script, inspect evidence, patch, and retry bounded attempts until success, blocker, or operator stop.
Hard rule: motion-capable commands must set
OPENFORGE_ALLOW_PHYSICAL_MOTION=1.
Loop:
- Read the wrapper/script and recent logs.
- Check needed servers (
yam-server-setup). - Run syntax/no-motion checks when useful.
- Run the physical script.
- Inspect
logs/<run>/(yam-runtime-artifacts). - Patch the smallest useful code/parameter change, or switch strategy if the evidence points to a better motion/perception logic.
- Retry.
Reset the scene yourself when it is safe and simple. Pause and ask the human to reset only when the task scene is physically broken in a way the robot cannot fix safely, such as a target bottle falling down during a grasp attempt.
Promote reusable lessons after a verified success or clear rejection:
- Geometry, frames, camera/table/gripper facts ->
yam-geometry. - Demo wrappers and golden commands ->
yam-full-demo. - Log/artifact structure and failure signatures ->
yam-runtime-artifacts. - Server checks/restarts ->
yam-server-setup. - Pickup/grasp tactics ->
yam-grasp-pickup. - Held-object transport tactics ->
yam-transport. - Retreat, release, and recovery tactics ->
yam-retreat-recovery. - cuRobo sensitivity and waypoint sweeps ->
yam-motion-planner.
Keep each lesson compact and cite the run path/date. Do not put one-off object XYZs, long narratives, or unverified guesses in skills.
Avoid ticket/approval env clutter. Use evidence gates from the current run.
Prefer edits in cap/saved_scripts/**, skill_library/**, and
yam_runtime/**.
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 First seen · 50 lines · 38 tokens per session scan A 7082b947679e
yam-robot-debugging is a skill published in the GitHub repository NVlabs/ASPIRE (127 stars, last pushed 4d ago), licensed Apache-2.0. It adds 38 tokens to every session and 476 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
integrated-browser
Use this when working on the VS Code integrated browser ("browserView") to understand its architecture and mental model. Covers the embedded Chromium browser, its editor tab, navigation, overlay/layout, sessions, and agent browser tools under src/vs/platform/browserView and src/vs/workbench/contrib/browserView.
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…