yam-robot-debugging

yam-robot-debugging is a skill for Claude Code, Codex from NVlabs/ASPIRE. It costs 38 tokens per session (476 once invoked), scanned A, original, Apache-2.0.

A debugging workflow for YAM physical robots in the Aspire real-robot workspace. It runs saved scripts, examines runtime evidence, changes code or settings, and retries bounded physical tests.

In plain words
What is it for?
Use it to edit and run robot scripts, inspect logs and other run artifacts, troubleshoot motion or perception behavior, and record reusable lessons after a verified result.
Why use it?
It turns robot debugging into a repeatable loop and uses logs and run artifacts to guide the next change. Physical movement requires an explicit safety setting.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/nvlabs/aspire/yam-robot-debugging
Any agent
npx skills add NVlabs/ASPIRE --skill yam-robot-debugging
Clone the repo
git clone --depth 1 https://github.com/NVlabs/ASPIRE

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for yam-robot-debugging

README.md
[![agentmods](https://agentmods.dev/badge/skills/nvlabs/aspire/yam-robot-debugging.svg)](https://agentmods.dev/skills/nvlabs/aspire/yam-robot-debugging)
Your own site
<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>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 476 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 5d ago against content hash 7082b947679e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

aspire/real/.agents/skills/yam-robot-debugging/SKILL.md · 50 lines

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:

  1. Read the wrapper/script and recent logs.
  2. Check needed servers (yam-server-setup).
  3. Run syntax/no-motion checks when useful.
  4. Run the physical script.
  5. Inspect logs/<run>/ (yam-runtime-artifacts).
  6. Patch the smallest useful code/parameter change, or switch strategy if the evidence points to a better motion/perception logic.
  7. 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/**.

Changes

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.

  1. 5d ago First seen · 50 lines · 38 tokens per session scan A 7082b947679e

Subscribe to this mod's changes

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.

Related

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.

microsoft/vscode · 68 tokens

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…

google/skills · 83 tokens

jetson-diagnostic

Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.

NVIDIA/skills · 30 tokens

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…

NVIDIA/skills · 236 tokens

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…

SnailSploit/Claude-Red · 113 tokens

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…

NVIDIA/skills · 94 tokens