Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/NVlabs/ASPIREnpx agentmods add skills/nvlabs/aspire/yam-full-demoWrote 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-full-demo)<a href="https://agentmods.dev/skills/nvlabs/aspire/yam-full-demo"><img src="https://agentmods.dev/badge/skills/nvlabs/aspire/yam-full-demo/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-full-demo"><img src="https://agentmods.dev/badge/skills/nvlabs/aspire/yam-full-demo.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 | $0.00038 | $0.00574 |
| Opus 5 | $0.00019 | $0.00287 |
| Sonnet 5 | $0.00008 | $0.00115 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade A, and why
yam-full-demo 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 Full Demo
Run this skill from the Aspire real-robot workspace (aspire/real). Paths and
commands below are relative to that directory.
Canonical commands:
bash tools/yam_demo_preflight.sh
bash tmux/launch_yam_demo_services.sh --no-attach
bash tools/yam_demo_preflight.sh --services
bash cap/saved_scripts/yam_demo.sh full
bash cap/saved_scripts/yam_demo.sh bowls
bash cap/saved_scripts/yam_demo.sh bottle-rack
bash cap/saved_scripts/yam_demo.sh kitkat
bash cap/saved_scripts/yam_demo.sh drawer
bash cap/saved_scripts/yam_demo.sh drawer-close
bash cap/saved_scripts/yam_demo.sh drawer-candy
bash cap/saved_scripts/yam_demo.sh home
The demo launcher starts only both follower arms, the camera Portal, SAM3, and BundleSDF. Do not require AnyGrasp, cuRobo, PyRoki, or provider credentials for these saved-script commands.
Flow:
yam_demo.shis the preferred dispatcher forfull,bowls,white-dish,orange-on-white,can-trash,kitkat,bottle-rack,drawer,drawer-close,drawer-candy, andhome.yam_demo.sh full-> drawer-close/home, white-dish, orange-on-white, can-trash, KitKat, bottle-rack
Speed:
- Use
YAM_FULL_DEMO_SPEED_SCALEas the operator-facing full-demo speed knob.1.0preserves validated defaults, values above1.0speed up planned moves and shorten direct step durations, values below1.0slow them down. - The scale feeds home, drawer planning, rack dish/bowl planning and direct rack timing, can/trash planning, KitKat planning, and bottle-rack planning.
- Task-specific low-level
OPENFORGE_*_PLANNING_SPEED,*_STEP_S,*_PLAYBACK_SPEED, andOPENFORGE_OPEN_HOME_SPEED_RAD_Senv overrides are still available for focused debugging.
Top-level cap/saved_scripts/yam_demo.sh is the operator shell entrypoint.
Helper shells live under cap/saved_scripts/shell_scripts/; active Python task
implementations live at top level. Older probes, sweeps, alternates, and
retired shell flows live under cap/saved_scripts/legacy_codes/.
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 · 54 lines · 38 tokens per session scan A 8ec881bff7fe
yam-full-demo is a skill published in the GitHub repository NVlabs/ASPIRE (150 stars, last pushed 10d ago), licensed Apache-2.0. It adds 38 tokens to every session and 574 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-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…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.