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 nebius/nebius-physical-ai --skill agent-visual-feedbackgit clone --depth 1 https://github.com/nebius/nebius-physical-aiWrote 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/nebius/nebius-physical-ai/agent-visual-feedback)<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/agent-visual-feedback"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/agent-visual-feedback.svg" alt="Measured on agentmods" 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 | $0.00040 | $0.01080 |
| Opus 5 | $0.00020 | $0.00540 |
| Sonnet 5 | $0.00008 | $0.00216 |
| Haiku 4.5 | $0.00004 | $0.00108 |
Grade A, and why
agent-visual-feedback 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 2d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Visual Feedback (Describe this)
Use this skill when the operator wants the agent to look at the current viewer and give actionable feedback — not a generic caption.
When To Use
- UI Describe this button (stays on the Rerun/viewer tab; chat opens as a drawer)
- Chat turns containing
[npa-visual-feedback]or “describe this viewer/visual” - Interpreting held-out Rerun frames, Isaac/GR00T-style sim views, rollout video, images, or Data-pane JSON
- For Sim2Real recordings, inspect
summary/stage_progressandsummary/policy_accessalongsiderollouts/outer_*/iter_*: camera and action entities share the same frame timeline; policy access is a link/download action and must never be described as policy execution inside Rerun. - Metadata-only feedback when a frame cannot be captured
Model
- Prefer a quality-captured frame (vision tier →
MiniMaxAI/MiniMax-M3). - Wait for a non-blank canvas (skip uniform black/white/mid-gray; dense RGB, skeletons on dark grids, and meshes are valid). Cleared WebGL buffers often look mid-gray — never attach those. Blank detection must keep enough resolution to see sparse orange/cyan skeleton strokes (do not 80px-downscale them away).
- Rerun capture must use the MediaStream bridge (
canvas.captureStream→<video>→ JPEG). Do not gate capture on syncdrawImageblank checks — those false-negative on live WebGL/WebGPU. - If capture fails, send metadata/text and use the reasoning tier — never pretend pixels were seen.
- Do not answer Describe-this from the grounded intent router.
- Open the chat drawer and show Describe this — capturing… immediately; do not wait for capture before the user bubble appears.
Visual kinds (generalized — no URI allowlists)
| Kind | Source | What to emphasize |
|---|---|---|
rerun |
Largest same-origin Rerun canvas after quality wait | Sim RGB, depth/seg, 3D mesh, tiled envs, policy strips — not “blank” by default |
video |
<video> current frame |
Task progress, success/failure cues |
image |
Preview <img> |
Scene contents, defects |
data |
<pre> / text excerpt |
Report fields, success_rate, missing keys |
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.
- 2d ago Changed 3533e40cd496
- 8d ago First seen · 91 lines · 40 tokens per session scan A 8d9f34840242
agent-visual-feedback is a skill published in the GitHub repository nebius/nebius-physical-ai (27 stars, last pushed today), licensed Apache-2.0. It adds 40 tokens to every session and 1,080 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.