npm-safety

npm-safety is a skill for Claude Code from lifedever/skills-plugin. It costs 164 tokens per session (2,079 once invoked), scanned A, original, MIT.

A safety check for npm, Yarn, and pnpm packages, which are reusable JavaScript and TypeScript dependencies. It uses Socket.dev to review packages before installation and to audit an existing project’s dependency tree.

In plain words
What is it for?
Checking packages before adding them, auditing all project dependencies, assessing whether a package is safe to install, and fixing reported CVEs where supported.
Why use it?
It helps reveal security and supply-chain concerns before unfamiliar code becomes part of a project, while respecting the project’s existing package manager.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_SKILL_DIR} variable. Also seen: names the AskUserQuestion tool; mentions Claude Code.

Part of the lifedever plugin — 15 skills shipped together

Good fit Checking packages before adding them, auditing all project dependencies, assessing whether a package is safe to install, and fixing reported CVEs where supported.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lifedever/skills-plugin/npm-safety
Install

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.

Any agent
npx skills add lifedever/skills-plugin --skill npm-safety
Clone the repo
git clone --depth 1 https://github.com/lifedever/skills-plugin

Made for: Claude Code.

Or install lifedever, the plugin that ships this one along with the rest of its 15 skills.

Wrote 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.

agentmods badge for npm-safety

README.md
[![agentmods](https://agentmods.dev/badge/skills/lifedever/skills-plugin/npm-safety/github.svg)](https://agentmods.dev/skills/lifedever/skills-plugin/npm-safety)
Your own site
<a href="https://agentmods.dev/skills/lifedever/skills-plugin/npm-safety"><img src="https://agentmods.dev/badge/skills/lifedever/skills-plugin/npm-safety/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.

agentmods 80×15 button for npm-safety

Your own site · 80×15
<a href="https://agentmods.dev/skills/lifedever/skills-plugin/npm-safety"><img src="https://agentmods.dev/badge/skills/lifedever/skills-plugin/npm-safety.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 164 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,079 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, 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 Anti-Refusal · line 153
    Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.
    Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00164 $0.02079
Opus 5 $0.00082 $0.01040
Sonnet 5 $0.00033 $0.00416
Haiku 4.5 $0.00016 $0.00208

Measured 9d ago against content hash c19a6d095be9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

npm-safety 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/preflight.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/npm-safety/SKILL.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

npm-safety

Vet npm-ecosystem packages with socket.dev before they enter the project. The skill is the orchestrator: it runs the safety checks, surfaces capability / supply-chain signals, and only then runs the project's own package manager for the actual install.

The skill is package-manager-aware. It detects whether the project uses npm, yarn, or pnpm from the lockfile and uses that one — it does not force npm install.

When to use which command

Situation Command
User asks to add 1+ packages socket package shallow npm <a> <b> ... (batch) or socket package score npm <a> (deep, single)
User asks for project-wide audit socket scan create in the project root
User asks "is package X safe?" without intent to install yet socket package score npm <X> --markdown
User asks to fix CVEs socket fix (npm projects only — see Caveats)

Workflow: pre-install vetting

This is the most common path. Follow it whenever the user asks to add a new dependency, regardless of the package manager they mention.

Step 1 — Preflight

Run the preflight script from the project root the user is working in:

bash "${CLAUDE_SKILL_DIR}/scripts/preflight.sh" "<project-dir>"

The script:

  • Confirms socket CLI is installed (exit 2 with install hint if not)
  • Confirms an API token is configured (exit 2 with setup hint if not)
  • Detects package manager from lockfile (pnpm-lock.yaml > yarn.lock > package-lock.json), or from packageManager field in package.json as fallback
  • Prints key=value pairs on stdout — parse package_manager and lockfile

If preflight exits non-zero, stop and show the user the stderr message verbatim. Do not attempt to install anything until they fix the prerequisite.

Step 2 — Query Socket for risk signals

For a single package, use socket package score — it includes transitive dependency scores, which matters because most supply-chain risk lives in transitives:

Read the full file on GitHub · 155 lines

Files

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.

Changes

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.

  1. 9d ago First seen · 155 lines · 164 tokens per session scan A c19a6d095be9

Subscribe to this mod's changes

npm-safety is a skill published in the GitHub repository lifedever/skills-plugin (11 stars, last pushed 18d ago), licensed MIT. It adds 164 tokens to every session and 2,079 once invoked, about $0.0008 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 83 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens