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 insightsgit 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/insights)<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/insights"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/insights/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/insights"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/insights.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 | $0.00044 | $0.01877 |
| Opus 5 | $0.00022 | $0.00938 |
| Sonnet 5 | $0.00009 | $0.00375 |
| Haiku 4.5 | $0.00004 | $0.00188 |
Grade A, and why
insights 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Insights (Lineage & Metrics backbone)
Insights is the connective tissue that makes workflow runs legible. It turns the structured reports/manifests other tools already emit into a queryable lineage graph + common metrics store — the foundation for dashboards and an orchestrating agent. It does not replace any tool; it aggregates them.
Three-access pattern
Source of truth is the FastAPI service
(npa/src/npa/workbench/insights/service.py). The CLI
(npa/src/npa/cli/workbench/insights.py) and SDK
(npa/src/npa/sdk/workbench/insights.py) are thin clients. Do not duplicate
logic across layers.
Store layout
The store is an append-only index on S3 under a configurable prefix
(--output-path), with a JSONL fallback so it works without any database:
records.jsonl— metric records (npa.insights.metric_record.v1).edges.jsonl— lineage edges (npa.insights.lineage_edge.v1).records.d/andedges.d/— immutable append shards, one object per write.
Every append writes a new shard object; readers concatenate the base object (legacy stores) plus all shards. Never rewrite a whole JSONL object to append: object storage has no native append, so read-modify-write silently drops rows when two writers overlap (both read N, both write N + their own).
Readers expose a logically idempotent view: metric rows are deduplicated by run, source artifact URI, metric, stage/tool, canonical labels (including curve step), and lineage; lineage edges use their endpoint/version/relation/run identity. This also repairs legacy stores that already contain duplicate shards. Explicit emissions without an artifact URI retain their timestamp/value identity so distinct observations with the same metric name are not collapsed.
Do NOT introduce a database service or hardcode a metadata backend. Reuse the
LanceDB tool as the optional query index (HTTP seam in integrations.py),
exactly as dataset does; absence degrades to the JSONL scan.
Interfaces
CLI:
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 91e007da07b0
- 10d ago First seen · 152 lines · 44 tokens per session scan A 14bb59a3d91e
insights is a skill published in the GitHub repository nebius/nebius-physical-ai (27 stars, last pushed today), licensed Apache-2.0. It adds 44 tokens to every session and 1,877 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…