synerise-design: Skill for Claude Code

.claude/skills/package-audit/SKILL.md

package-audit is a skill for Claude Code from Synerise/synerise-design. It costs 41 tokens per session (3,647 once invoked), scanned A, original, MIT.

A quality audit for one component package in a design system, a shared library of reusable interface components. It produces a severity-ranked report and a prioritised plan for fixes.

In plain words
What is it for?
Use it to inspect a component package for dead code, missing unit or interactive tests, incomplete Storybook stories, console logs, dependency problems, and README gaps.
Why use it?
It brings code quality, tests, documentation, Storybook examples, and dependency hygiene into one review instead of checking them separately.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is Synerise/synerise-design's own configuration. It tells Claude Code how to work on synerise-design itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything synerise-design configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Synerise/synerise-design. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Synerise/synerise-design/master/.claude/skills/package-audit/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Synerise/synerise-design

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 package-audit

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/synerise/synerise-design/package-audit"><img src="https://agentmods.dev/badge/skills/synerise/synerise-design/package-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,647 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 pass 7 Sept 2026
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 $0.00041 $0.03647
Opus 5 $0.00020 $0.01824
Sonnet 5 $0.00008 $0.00729
Haiku 4.5 $0.00004 $0.00365

Measured 4d ago against content hash aa005e8f6ac3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

package-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 4d 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/package-audit/SKILL.md · 280 lines

How it starts

The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Overview

Perform a thorough quality audit of a single component package in the design system. The audit covers dead code, unit tests, Storybook stories, interactive tests, console logs, suppression comments, code organisation, README completeness, and package.json dependency hygiene. Output is a structured report grouped by severity, followed by a prioritised fix plan for critical and important findings.

Arguments

The user must provide:

  1. Package name — e.g., modal, button, popover (kebab-case directory name under packages/components/)

If the package name was not provided, ask: "Which package would you like to audit? (e.g. modal, button, popover)"

Workflow

Step 1 — Locate the package

Find and read all source files for the package:

packages/components/<package-name>/src/         ← component source
packages/storybook/stories/components/<PascalName>/   ← stories

If the stories directory uses a different casing or name, search with:

packages/storybook/stories/components/**/<PascalName>*.stories.tsx

Read all relevant files before forming any judgements. Typical structure to read:

  • package.json — declared dependencies, peerDependencies, devDependencies
  • <Name>.tsx — main component
  • <Name>.types.ts / <Name>.types.tsx — prop types
  • <Name>.styles.tsx / style/ — styled-components
  • index.ts / index.tsx — public exports
  • Sub-component files in nested directories
  • Custom hooks: use*.ts / use*.tsx
  • Utility/helper files: *utils*, *helpers*, *constants*
  • __specs__/ or *.test.tsx — unit tests
  • *.stories.tsx — regular stories
  • *.test.stories.tsx / *.tests.stories.tsx — interactive/play stories
  • README.md — package documentation

Step 2 — Run automated checks

Run these commands and capture the output; use findings to support manual analysis:

# Check for console.log / console.error / console.warn
grep -rn "console\." packages/components/<package-name>/src/ --include="*.ts" --include="*.tsx"

# Check for ts-ignore / ts-expect-error / @ts-nocheck
grep -rn "@ts-ignore\|@ts-expect-error\|@ts-nocheck" packages/components/<package-name>/src/

# Check for eslint-disable comments
grep -rn "eslint-disable" packages/components/<package-name>/src/

# List exported symbols from index
cat packages/components/<package-name>/src/index.ts 2>/dev/null || cat packages/components/<package-name>/src/index.tsx

# Count test files
find packages/components/<package-name>/src -name "*.test.tsx" -o -name "*.spec.tsx" | wc -l

# Count story files
find packages/storybook/stories/components/<PascalName> -name "*.stories.tsx" 2>/dev/null | wc -l

# Check README exists and get its size
wc -l packages/components/<package-name>/README.md 2>/dev/null || echo "MISSING"

# List all import statements in source files (to cross-reference against package.json)
grep -rh "^import" packages/components/<package-name>/src/ --include="*.ts" --include="*.tsx" | grep "from '" | sed "s/.*from '\\([^']*\\)'.*/\\1/" | grep -v '^\.' | sort -u

# Check for MDX overview
ls packages/storybook/stories/components/<PascalName>/Overview.mdx 2>/dev/null || echo "MISSING"

# List argTypes from stories
grep -A 1 "argTypes:" packages/storybook/stories/components/<PascalName>/<PascalName>.stories.tsx | head -30

Read the full file on GitHub · 280 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. 4d ago First seen · 280 lines · 41 tokens per session scan A aa005e8f6ac3

Subscribe to this mod's changes

package-audit is a skill published in the GitHub repository Synerise/synerise-design (96 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 3,647 once invoked, about $0.0002 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 2026-09-04.