/dependency-audit

Decide whether to add, keep, or remove a dependency. Use before adding any package.

BOOST

archive228@archive228

GitHub

From plugin

loopkit

75553 skills1 agent4 commands2 MCP

Install

$ npx -y skills add Archive228/loopkit --skill dependency-audit --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
You can call itInvoke it directly when you want it.
Slash command/dependency-audit

Context preview

The summary Claude sees to decide when to auto-load this skill.

Decide whether to add, keep, or remove a dependency. Use before adding any package.

SKILL.md

dependency-audit.SKILL.md

name: dependency-audit
description: Decide whether to add, keep, or remove a dependency. Use before adding any package.
when_to_use: adding a package, a bloated lockfile, a CVE alert, "do we need this dep"

Dependency Audit

Before adding a package, ask: 1. **Can the stdlib do it?** No lodash for `Array.map`. No left-pad-tier packages. 2. **Is it already in the tree?** Don't add axios if the project uses fetch. 3. **Is it alive?** Last commit, open issues, maintainer responsiveness. 4. **Cost?** A 500KB dep to format a date isn't worth it. Check the install size and transitive deps. 5. **Security?** Known CVEs? Postinstall scripts? When you do add one, justify it in the PR body. Never silently grow package.json. For existing deps: anything unused or one-function gets removed.

Read it on GitHub ↗

Ships withloopkit

33 battle-tested skills + minimal .claude harness for any coding agent (Claude Code, Cursor, Codex, Gemini CLI).

Get the whole plugin

Stats

Node Bash SQL Git GitHub

+4 tags

Markdown Anthropic Gemini MCP

755

Stars

124

Forks