launch-check

A production-readiness command that checks project conventions and, when a site is available, measures its Lighthouse scores. Lighthouse is a tool that evaluates web performance, accessibility, best practices, and SEO.

In plain words
What is it for?
Checking code conventions, image and metadata issues, and website performance, accessibility, best-practice, and SEO measurements.
Why use it?
It collects common launch checks in one run and shows whether the site meets the stated quality targets.

Command for Claude Code

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/launch-check
Clone the repo
git clone --depth 1 https://github.com/holger1411/astrodeck

Made for: Claude Code.

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 743 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5 $0.00011 $0.00743
Opus 5 $0.00005 $0.00371
Sonnet 5 $0.00002 $0.00149
Haiku 4.5 $0.00001 $0.00074

Measured 2d ago against content hash abd4565f9d98, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

launch-check scanned grade B with 1 finding 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

- Build: must pass without warnings
.claude/commands/launch-check.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Launch Check

Run a comprehensive production-readiness check that measures all skill KPIs at once.

URL provided by the user (detect a running dev/preview server if empty): $ARGUMENTS

1. Static convention checks (single source of truth)

npm run check:kpis

This covers: hardcoded colors, inline styles, tailwind.config existence, deprecated Astro patterns, images without alt, relative imports, non-OKLCH tokens, and pages without descriptions. Do NOT duplicate these with ad-hoc greps.

2. Lighthouse (all 4 categories)

If a server is running (dev or preview), run Lighthouse and report ALL 4 scores:

npx lighthouse <URL> --output=json --output-path=./lighthouse-report.json --chrome-flags="--headless --no-sandbox"
Category Target Responsible Skill
Performance >90 ui-design
Accessibility >90 accessibility
Best Practices >90 qa
SEO >90 content-seo

Also extract the detailed performance metrics:

  • FCP (First Contentful Paint) → target <1.8s
  • LCP (Largest Contentful Paint) → target <2.5s
  • TBT (Total Blocking Time) → target <200ms
  • CLS (Cumulative Layout Shift) → target <0.1

3. Build & types

npx tsc --noEmit 2>&1 | grep "error TS" | wc -l
npm run build
  • TypeScript errors: target 0
  • Build: must pass without warnings

4. Code quality

npm run lint
npm run format:check
  • ESLint errors/warnings: target 0
  • Formatting issues: target 0

5. Accessibility (server required)

  • Pa11y errors: 0 (npx pa11y <URL> --reporter=json)
  • Buttons without label: <button> without text content or aria-label

6. Content & SEO

  • Heading hierarchy: check for skipped levels
  • Meta descriptions: covered by npm run check:kpis

Output Format

## Launch Check Results

### ✅ Static KPI Checks
[Table from npm run check:kpis]

### ✅ Astro Framework
- TypeScript errors: 0
- Build: OK (X.Xs)

### ⚠️ Code Quality
- ESLint errors: 0
- ESLint warnings: 3
- Formatting: OK

### ✅ Lighthouse
- Performance: 98 | Accessibility: 100 | Best Practices: 100 | SEO: 100
- FCP 0.8s | LCP 1.2s | TBT 0ms | CLS 0

---

## Recommendations
1. [Prioritized fixes, highest priority first]
2. [...]

Read the full file on GitHub · 112 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. 2d ago First seen · 112 lines · 11 tokens per session scan B abd4565f9d98

Subscribe to this mod's changes

launch-check is a command published in the GitHub repository holger1411/astrodeck (72 stars, last pushed 26d ago), licensed MIT. It adds 11 tokens to every session and 743 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.