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/nebius/nebius-physical-ainpx agentmods add skills/nebius/nebius-physical-ai/foxgloveWrote 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/foxglove)<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/foxglove"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/foxglove/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/nebius/nebius-physical-ai/foxglove"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/foxglove.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 159 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium MCP Rug Pull · line 188 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
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 | $0.00058 | $0.03834 |
| Opus 5 | $0.00029 | $0.01917 |
| Sonnet 5 | $0.00012 | $0.00767 |
| Haiku 4.5 | $0.00006 | $0.00383 |
Grade A, and why
foxglove 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.
How it starts
The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Foxglove Embedded Viewer
NPA embeds Foxglove with the official
@foxglove/embed TypeScript SDK:
the SDK creates an iframe pointing at a Foxglove deployment and drives it over
postMessage (setDataSource, selectLayout, seekPlayback, ready/error).
What NPA ships vs what Foxglove hosts — NPA serves the MIT-licensed SDK
(fetched unmodified from npm, sha512-verified) plus your recordings. The viewer
application is Foxglove's: either https://embed.foxglove.dev/ (users sign in to
a Foxglove organization on a plan that allows embedding) or your self-hosted
deployment. Without a configured embed source the viewer pane says so — it never
renders an empty frame and calls it a viewer.
Which viewer when
NPA ships two MCAP viewers; they are complements, not alternatives:
skills/tools/lichtblick/SKILL.md (OSS) |
this skill (official Foxglove) | |
|---|---|---|
| What runs | Lichtblick web build (MPL-2.0) served by the agent, in-page | Foxglove's own app in a cross-origin iframe, driven by @foxglove/embed |
| Account | none | a Foxglove org on a plan that allows embedding |
| Renders MCAP | yes, out of the box | yes, after sign-in |
| Recording path | same-origin /lichtblick/recordings/ (no CORS) |
/foxglove/data/ (CORS + byte ranges) |
| Use it for | default operator playback, CI, air-gapped | customers standardized on Foxglove (layouts, extensions, org sharing) |
The agent's Foxglove pane picks between them at runtime
(/api/foxglove/config → viewer_backend): the official app when
NPA_FOXGLOVE_EMBED_SRC is configured and the SDK assets are installed,
otherwise the self-hosted OSS viewer, otherwise an explained unavailable state.
NPA_FOXGLOVE_VIEWER_BACKEND=foxglove-sdk|self-hosted forces one.
When To Use
- Adding/changing the agent's Foxglove viewer pane or
/api/foxglove/*endpoints - Publishing
.mcap/.bagrecordings for playback in the agent - Building/running the
npa-foxglove-embedcontainer - Converting run artifacts to MCAP (
npa workbench foxglove convert-run) - Debugging "viewer unavailable", CORS, or byte-range playback problems
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 · 243 lines · 58 tokens per session scan A 33df3e8459ff
foxglove is a skill published in the GitHub repository nebius/nebius-physical-ai (28 stars, last pushed today), licensed Apache-2.0. It adds 58 tokens to every session and 3,834 once invoked, about $0.0003 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.