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 UAantovakul/no-npm-claude --skill no-npmgit clone --depth 1 https://github.com/UAantovakul/no-npm-claudeWrote 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/uaantovakul/no-npm-claude/no-npm)<a href="https://agentmods.dev/skills/uaantovakul/no-npm-claude/no-npm"><img src="https://agentmods.dev/badge/skills/uaantovakul/no-npm-claude/no-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/uaantovakul/no-npm-claude/no-npm"><img src="https://agentmods.dev/badge/skills/uaantovakul/no-npm-claude/no-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 | $0.00033 | $0.01902 |
| Opus 5 | $0.00016 | $0.00951 |
| Sonnet 5 | $0.00007 | $0.00380 |
| Haiku 4.5 | $0.00003 | $0.00190 |
Grade B, and why
no-npm scanned grade B with 1 finding 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 12d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
The hook `~/.claude/hooks/block-npm.js` is registered in `~/.claude/settings.json` How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
no-npm — Block npm/npx/yarn, pnpm only
Why this skill exists
The npm ecosystem went through a series of large supply-chain attacks
(Shai-Hulud Sep 2025, Shai-Hulud 2.0 Nov 2025, Mini Shai-Hulud May 2026).
The common vector across all three is a package's lifecycle scripts
(preinstall / install / postinstall), which the package manager runs
automatically during install. That is where the worm executes.
pnpm 10+ by default does NOT run dependency build scripts outside an
explicit allowlist (onlyBuiltDependencies / allowBuilds in
pnpm-workspace.yaml) — it only prints a warning. That closes the primary
vector. npm runs everything without asking — which is why npm is blocked
and pnpm is not.
✅ Furthermore — pnpm 11+ (released ~April 2026) enables
minimumReleaseAge=1440(a 24h cooldown on fresh versions) andblockExoticSubdepsby default. So on pnpm 11 both vectors are closed — execution (allowlist) and ingress (cooldown) — out of the box, no config. Before v11 the cooldown was0(opt-in). Source: https://pnpm.io/settings ("Default: 1440 (since v11)").⚠️
pnpm config get minimumReleaseAgereturningundefineddoes NOT mean "disabled":config getonly echoes explicit config, not the v11 built-in default.
The user's global decision: no npm/npx/yarn in this environment.
When npm/npx/yarn appears (from me or from the user)
As soon as a command contains npm, npx, or yarn as a standalone word —
whether I (Claude) am about to run it or the user asks for it directly:
-
Do NOT run it.
-
Issue a warning:
⛔ NPM IS BLOCKED IN THIS ENVIRONMENT. Use pnpm.
-
Offer the pnpm equivalent (table below) and ask for confirmation before running it.
If the user genuinely needs npm itself, they run the command manually in their
own terminal outside Claude Code; the block-npm.js hook blocks the attempt
through Bash regardless.
Equivalents table
| npm / npx / yarn | pnpm |
|---|---|
npm install / npm i |
pnpm install |
npm install <pkg> / npm i <pkg> |
pnpm add <pkg> |
npm install -D <pkg> |
pnpm add -D <pkg> |
npm install -g <pkg> |
pnpm add -g <pkg> |
npm uninstall <pkg> / npm rm <pkg> |
pnpm remove <pkg> |
npm update |
pnpm update |
npm run <script> |
pnpm <script> (or pnpm run <script>) |
npm test |
pnpm test |
npm ci |
pnpm install --frozen-lockfile |
npx <pkg> |
pnpm dlx <pkg> |
npx create-vite my-app |
pnpm create vite my-app |
yarn / yarn install |
pnpm install |
yarn add <pkg> |
pnpm add <pkg> |
yarn add -D <pkg> |
pnpm add -D <pkg> |
yarn remove <pkg> |
pnpm remove <pkg> |
yarn <script> |
pnpm <script> |
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.
- 12d ago First seen · 147 lines · 33 tokens per session scan B 65ec372e7cef
no-npm is a skill published in the GitHub repository UAantovakul/no-npm-claude (2 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 1,902 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
better-auth
Skill for integrating Better Auth - comprehensive TypeScript authentication framework for Cloudflare D1, Next.js, Nuxt, and 15+ frameworks. Use when adding auth, encountering D1 adapter errors, or implementing OAuth/2FA/RBAC features.
aceternity-ui
100+ animated React components (Aceternity UI) for Next.js with Tailwind. Use for hero sections, parallax, 3D effects, or encountering animation, shadcn CLI integration errors.
cloudflare-cron-triggers
Cloudflare Cron Triggers for scheduled Workers execution. Use for periodic tasks, scheduled jobs, or encountering handler not found, invalid cron expression, timezone errors.
cloudflare-durable-objects
Cloudflare Durable Objects for stateful coordination and real-time apps. Use for chat, multiplayer games, WebSocket hibernation, or encountering class export, migration, alarm errors.
cloudflare-browser-rendering
Cloudflare Browser Rendering with Puppeteer/Playwright. Use for screenshots, PDFs, web scraping, or encountering rendering errors, timeout issues, memory exceeded.
cloudflare-workers-ci-cd
Complete CI/CD guide for Cloudflare Workers using GitHub Actions and GitLab CI. Use for automated testing, deployment pipelines, preview environments, secrets management, or encountering deployment failures, workflow errors, environment configuration issues.