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.
git clone --depth 1 https://github.com/christopherlouet/claude-baseWrote 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.
[](https://agentmods.dev/commands/christopherlouet/claude-base/qa-design)<a href="https://agentmods.dev/commands/christopherlouet/claude-base/qa-design"><img src="https://agentmods.dev/badge/commands/christopherlouet/claude-base/qa-design.svg" alt="Measured on agentmods" height="20"></a>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 5.1 | $0.00000 | $0.00427 |
| Opus 5 | $0.00000 | $0.00214 |
| Sonnet 5 | $0.00000 | $0.00085 |
| Haiku 4.5 | $0.00000 | $0.00043 |
Grade A, and why
qa-design 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 3d 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.
What it actually says
QA-DESIGN Agent
UI/UX design audit and verification of web best practices.
Context
$ARGUMENTS
Objective
Audit an interface against 100+ rules covering accessibility, forms, animations, typography, images, UI performance, navigation, dark mode, touch, internationalization and responsive/mobile-first breakpoints.
Workflow
- Scan UI files (components, CSS, pages)
- Verify accessibility (contrast, ARIA, focus, keyboard)
- Verify forms (validation, feedback, autocomplete)
- Verify animations (reduced-motion, performance, timing)
- Verify typography, images, UI performance
- Verify navigation, dark mode, touch targets, i18n
- Verify responsive/mobile-first across the 7 breakpoints (320→2560px), viewport, touch sizing
- Produce the report with scores per category
Expected output
Overall score: X/100
| Category | Score | Critical issues | Recommendations |
|---|---|---|---|
| Accessibility | /10 | ||
| Forms | /10 | ||
| Animations | /10 | ||
| Typography | /10 | ||
| Images | /10 | ||
| UI Performance | /10 | ||
| Navigation | /10 | ||
| Dark Mode | /10 | ||
| Touch | /10 | ||
| i18n | /10 | ||
| Responsive | /10 |
Critical issues, quick wins, recommendations
[With file:line for each issue]
Related agents
| Agent | When to use it |
|---|---|
/qa:wcag-audit |
Detailed WCAG accessibility audit |
/qa:qa-perf |
Detailed performance audit |
/dev:dev-design-system |
Design tokens and design system |
IMPORTANT: Cover all 11 categories, not just the obvious ones.
YOU MUST provide concrete solutions with file:line.
NEVER ignore accessibility - it is a legal obligation.
Think hard about the overall user experience, not just the technical details.
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.
- 3d ago First seen · 61 lines · 0 tokens per session scan A d146042e12bc
qa-design is a command published in the GitHub repository christopherlouet/claude-base (5 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 427 tokens. 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 2026-09-03.
Other commands, from other repositories
bliss
Create distinctive, human-centered frontend interfaces. Use for UI components, pages, and applications with bold aesthetics and WCAG compliance.
ui-review
Retroactive visual audit of UI implementation with 1-4 scoring per dimension.
ccc-multi-frontend
Frontend-focused multi-model workflow: Research → Plan → Execute → Review, Gemini-led.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.