deps-audit

deps-audit is a skill for Claude Code from kazdenc/builder-skills. It costs 58 tokens per session (1,666 once invoked), scanned A, original, MIT.

A guide to checking a project's software packages for known security problems, outdated versions, unused dependencies, and unnecessary bundle size.

In plain words
What is it for?
Use it to inspect package manifests and lockfiles, run the appropriate audit command, find vulnerable or unused packages, and reduce bundle bloat.
Why use it?
It turns scattered dependency problems into a categorized report and prioritized upgrade plan.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to inspect package manifests and lockfiles, run the appropriate audit command, find vulnerable or unused packages, and reduce bundle bloat.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kazdenc/builder-skills/deps-audit
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 kazdenc/builder-skills --skill deps-audit
Clone the repo
git clone --depth 1 https://github.com/kazdenc/builder-skills

Made for: Claude Code.

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 deps-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/kazdenc/builder-skills/deps-audit/github.svg)](https://agentmods.dev/skills/kazdenc/builder-skills/deps-audit)
Your own site
<a href="https://agentmods.dev/skills/kazdenc/builder-skills/deps-audit"><img src="https://agentmods.dev/badge/skills/kazdenc/builder-skills/deps-audit/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 deps-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/kazdenc/builder-skills/deps-audit"><img src="https://agentmods.dev/badge/skills/kazdenc/builder-skills/deps-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,666 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.
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 $0.00058 $0.01666
Opus 5 $0.00029 $0.00833
Sonnet 5 $0.00012 $0.00333
Haiku 4.5 $0.00006 $0.00167

Measured 10d ago against content hash 8689f82a2e8f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

deps-audit 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 10d 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.

.claude/skills/dev/review/deps-audit/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit project dependencies and produce a categorized report with a prioritized upgrade plan. Surface vulnerabilities, unused packages, and bundle bloat.

Step 1: Read Package Manifest

Read package.json (or the specified manifest file). Catalog:

  • All dependencies and their pinned/range versions
  • All devDependencies and their pinned/range versions
  • Any peerDependencies or optionalDependencies
  • Package manager in use (npm, pnpm, yarn) from lock file presence
  • Node/runtime engine constraints if declared

Step 2: Check for Vulnerabilities

Run the appropriate audit command for the detected package manager:

Package Manager Command Notes
npm npm audit --json Parse JSON output for severity counts
pnpm pnpm audit --json Similar JSON structure
yarn (v1) yarn audit --json NDJSON output, parse line by line
yarn (berry) yarn npm audit --json Different output format

For each vulnerability found, capture:

  • Package name and installed version
  • Severity (critical, high, moderate, low)
  • CVE identifier if available
  • Fix available (yes/no) and which version resolves it
  • Whether it is a direct or transitive dependency

Step 3: Identify Outdated Packages

Run npm outdated --json (or equivalent) and group results:

Update Type Risk Level Action
Patch (1.2.3 → 1.2.4) Low Safe to update; bug fixes only
Minor (1.2.3 → 1.3.0) Low–Medium Usually safe; new features, no breaking changes
Major (1.2.3 → 2.0.0) Medium–High Breaking changes expected; read changelog first
Deprecated High Package abandoned; find replacement

Flag packages more than 2 major versions behind as high priority.

Step 4: Find Unused Dependencies

Scan the codebase for actual import/require usage of each declared dependency:

  • Search for import ... from '<package>' and require('<package>') patterns
  • Check framework config files that reference packages implicitly (Babel, PostCSS, ESLint, Tailwind plugins)
  • Check scripts in package.json that invoke CLI tools
  • Check for @types/* packages whose corresponding runtime package is used

Read the full file on GitHub · 160 lines

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. 10d ago First seen · 160 lines · 58 tokens per session scan A 8689f82a2e8f

Subscribe to this mod's changes

deps-audit is a skill published in the GitHub repository kazdenc/builder-skills (45 stars, last pushed 6mo ago), licensed MIT. It adds 58 tokens to every session and 1,666 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 2026-08-30.