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 Devrajsinh-Jhala/NPM-Vibe-check --skill npx-vibegit clone --depth 1 https://github.com/Devrajsinh-Jhala/NPM-Vibe-checkWrote 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/devrajsinh-jhala/npm-vibe-check/npx-vibe)<a href="https://agentmods.dev/skills/devrajsinh-jhala/npm-vibe-check/npx-vibe"><img src="https://agentmods.dev/badge/skills/devrajsinh-jhala/npm-vibe-check/npx-vibe/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/devrajsinh-jhala/npm-vibe-check/npx-vibe"><img src="https://agentmods.dev/badge/skills/devrajsinh-jhala/npm-vibe-check/npx-vibe.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 | $0.00055 | $0.00744 |
| Opus 5 | $0.00028 | $0.00372 |
| Sonnet 5 | $0.00011 | $0.00149 |
| Haiku 4.5 | $0.00006 | $0.00074 |
Grade A, and why
npx-vibe 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 7d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
npx-vibe Package Preflight
Inspect npm registry packages before allowing installation or execution. Treat the result as a review aid, fail closed on incomplete scans, and preserve the user's authority over risky actions.
Prefer the MCP tools
When the npx-vibe MCP server is connected, use its native tools instead of launching a shell command:
scan_packagefor one npm package spec.scan_projectfor registry dependencies from a project manifest; the whole lockfile tree is covered by default, passdirectOnlyto narrow it.approve_scriptswhen npm reports pendingallowScriptsentries, or a lockfile change adds a dependency with an install script.list_providersbefore selecting an optional AI model. No model catalog is bundled, so a model must be named explicitly.
Keep AI off unless the user explicitly asks for it or an established workflow requires it. MCP tool calls never accept API keys; provider credentials must come from the server environment.
Fall back to the CLI
Use the CLI when the MCP server is unavailable.
For one package:
npx --yes npx-vibe@latest --agent <package-spec>
For the current project's direct registry dependencies:
npx --yes npx-vibe@latest --agent --project .
Add --include-dev only when development dependencies are in scope. Project scans cover the whole lockfile tree by default; add --direct-only for the narrower, faster check.
Scanning never executes a package. Only npx-vibe run <spec> does, and it is never the right command for an automated check.
The outer npx --yes suppresses npm's package-download prompt; do not pass --yes or --force to npx-vibe itself.
Apply the decision
Read structuredContent from an MCP result, or parse CLI stdout as JSON, and use decision.action:
continue: Continue only with the install or execution the user already requested.review: Stop before execution, summarize the highest-severity findings and evidence, and request explicit human approval.stop: Do not install or execute the package. Explain the Block verdict and source evidence.retry: Treat the scan as incomplete. Report the operational error and do not infer safety from partial results.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago Changed · +5 lines cb9bee0261cc
- 11d ago First seen · 62 lines · 55 tokens per session scan A 64bb0edf7f9f
npx-vibe is a skill published in the GitHub repository Devrajsinh-Jhala/NPM-Vibe-check (0 stars, last pushed 9d ago), licensed MIT. It adds 55 tokens to every session and 744 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 2026-08-31.
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…