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 stonegiantstudio/skills --skill eval-npmgit clone --depth 1 https://github.com/stonegiantstudio/skillsWrote 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/stonegiantstudio/skills/eval-npm)<a href="https://agentmods.dev/skills/stonegiantstudio/skills/eval-npm"><img src="https://agentmods.dev/badge/skills/stonegiantstudio/skills/eval-npm/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/stonegiantstudio/skills/eval-npm"><img src="https://agentmods.dev/badge/skills/stonegiantstudio/skills/eval-npm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00037 | $0.02703 |
| Opus 5 | $0.00018 | $0.01352 |
| Sonnet 5 | $0.00007 | $0.00541 |
| Haiku 4.5 | $0.00004 | $0.00270 |
Grade A, and why
eval-npm 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 9d 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 — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NPM Package Evaluator
Evaluate npm packages to find the best option for a given use case. Compare maintenance health, community adoption, and identify promising newcomers while avoiding abandoned projects.
Instructions
Step 0: Security Advisory Pre-Check
Before evaluating any packages, run the npm-security-advisory skill procedure against the target packages. The skill produces three classes of findings that factor into evaluation:
- Advisory hits from Socket.dev/OSV/npm audit (known CVEs, known malware).
- Step 4 metadata anomalies — supply-chain worm signals:
FRESH,SCRIPT_ADDED,CADENCE_BURST,PROVENANCE_REGRESSION,NEW_PUBLISHER+FRESH,IOC_MATCH,YANKED, etc. These catch attacks before threat feeds do. - Positive signals like
PROVENANCE_OK— surface these in the report as confidence-raising evidence.
- Mode 1 (audit): Check all packages from package.json. MALWARE/CRITICAL findings (advisory hit OR
IOC_MATCHOR two combined HIGH Step 4 signals) automatically score 0 on the "Quality Signals: known security vulnerabilities" dimension and get flagged with a red flag. Individual HIGH Step 4 signals knock the dimension down by 3 points each.PROVENANCE_OKadds 1 point. Do not skip evaluation — the user needs the full picture to choose a replacement. - Mode 2 (compare): Check all candidate packages. Advisory findings and Step 4 signals are surfaced in the comparison table — add a "Supply-chain signals" row alongside the existing "Security" row. A package with active MALWARE findings (advisory or
IOC_MATCH) gets an automatic "DO NOT USE" recommendation. A package withPROVENANCE_OKgets a small ranking boost when alternatives are otherwise tied.
This command supports two modes:
Mode 1: Package.json Audit
If the user says "audit my package.json", "check my dependencies", "scan package.json", or provides a package.json file:
- Read the package.json from the current directory or the provided file
- Extract all dependencies from both
dependenciesanddevDependencies - Triage scan each package - do a quick health check (not full evaluation):
- Last publish date
- Weekly downloads trend
- Known vulnerabilities
- Maintenance status (active/maintenance-mode/abandoned)
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.
- 9d ago First seen · 284 lines · 37 tokens per session scan A 95067eb2f440
eval-npm is a skill published in the GitHub repository stonegiantstudio/skills (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 37 tokens to every session and 2,703 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 2026-08-31.
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…