A command that runs a broad quality check on an AstroDeck project, including code, build, accessibility, search visibility, and performance checks.

Use it before delivery or after changes to check conventions, linting, formatting, TypeScript, the production build, accessibility details, page metadata, and bundle size.

It gathers common project problems in one audit, reducing the need to run and interpret many checks separately.

audit — Command by holger1411

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.

agentmods

npx agentmods add commands/holger1411/astrodeck/audit

Clone the repo

git clone --depth 1 https://github.com/holger1411/astrodeck

Made for: Claude Code.

Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 525 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00008	$0.00525
Opus 5	$0.00004	$0.00262
Sonnet 5	$0.00002	$0.00105
Haiku 4.5	$0.00001	$0.00052

Measured 2d ago against content hash 956c7199e5e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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/commands/audit.md · 88 lines

What it actually says

Project Audit

Perform a comprehensive quality check of the AstroDeck project.

Focus requested by the user (audit everything if empty): $ARGUMENTS

1. Static convention checks (single source of truth)

Run the bundled KPI script — it covers hardcoded colors, inline styles, tailwind.config existence, deprecated Astro patterns, missing alt attributes, relative imports, non-OKLCH tokens, and pages without descriptions:

npm run check:kpis

Do NOT re-implement these checks with ad-hoc greps — the script is canonical.

2. Code Quality

npm run lint
npm run format:check
npx tsc --noEmit

3. Build Verification

npm run build

Check for warnings or errors in the build output.

4. Accessibility (beyond the static checks)

Buttons without accessible labels (<button> without text content or aria-label)
Missing ARIA attributes on interactive elements
Proper heading hierarchy (h1 -> h2 -> h3, no skipping)

5. SEO

Verify each page has:

Unique title tag
Meta description (150-160 chars)
OpenGraph tags (via SEO component)

6. Performance

Run npm run build — check bundle size
Verify images use Astro's <Image /> component where possible
Check for unnecessary client:load directives (prefer client:visible or client:idle)
External scripts have SRI integrity attributes

7. Theme Consistency

All color tokens use --color- prefix with OKLCH format
Both @theme and .dark blocks are in sync

Skills

For details, consult the qa and accessibility skills (.claude/skills/qa/SKILL.md, .claude/skills/accessibility/SKILL.md).

Output Format

## Audit Results

### Passed
- [List of passed checks]

### Warnings
- [List of warnings with file locations]

### Issues
- [List of issues that need fixing]

### Recommendations
- [Suggested improvements]

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.

2d ago First seen · 88 lines · 8 tokens per session scan A 956c7199e5e5

Subscribe to this mod's changes

audit is a command published in the GitHub repository holger1411/astrodeck (72 stars, last pushed 26d ago), licensed MIT. It adds 8 tokens to every session and 525 once invoked, about $0.0000 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.

Debugging

audit