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.
npx skills add JansenAnalytics/claudex --skill design-criticgit clone --depth 1 https://github.com/JansenAnalytics/claudexWrote 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/skills/jansenanalytics/claudex/design-critic)<a href="https://agentmods.dev/skills/jansenanalytics/claudex/design-critic"><img src="https://agentmods.dev/badge/skills/jansenanalytics/claudex/design-critic/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.
<a href="https://agentmods.dev/skills/jansenanalytics/claudex/design-critic"><img src="https://agentmods.dev/badge/skills/jansenanalytics/claudex/design-critic.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00111 | $0.02628 |
| Opus 5.5 | $0.00044 | $0.01051 |
| Sonnet 5.5 | $0.00022 | $0.00526 |
| Haiku 4.5 | $0.00011 | $0.00263 |
Grade A, and why
design-critic 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Critic
Autonomous UI/UX reviewer. Point it at any running web app → get a prioritized list of every visual, responsive, accessibility, and functionality issue with actionable fixes.
Scripts: ${CLAUDE_SKILLS_DIR:-$HOME/.claude-agent/.claude/skills}/design-critic/scripts/
Reviews: ~/.design-critic/reviews/
Binary: ~/bin/design-critic
Quick Reference
S=${CLAUDE_SKILLS_DIR:-$HOME/.claude-agent/.claude/skills}/design-critic/scripts
# Full review (the default workflow)
design-critic http://localhost:5173
# Quick check (mobile + desktop, no lighthouse)
design-critic http://localhost:5173 --quick
# Full audit (all 9 viewports, lighthouse, dark mode, discovery, vision prompts)
design-critic http://localhost:5173 --full
# Responsive focus (all viewport sizes, no lighthouse)
design-critic http://localhost:5173 --responsive
# After fixes — compare with previous review
design-critic http://localhost:5173 --compare ~/.design-critic/reviews/PREVIOUS_DIR
The Autonomous Review Workflow
This is the workflow to use before telling the user anything is "done":
Step 1: Run the review
design-critic http://localhost:5173 --full
Step 2: Read the report
cat ~/.design-critic/reviews/LATEST/report.md
Step 3: AI visual review of screenshots
# Use the image tool on captured screenshots with generated vision prompts
cat CAPTURE_DIR/vision-prompts.json | jq '.[0]'
# Then use image tool: analyze the screenshot with the vision prompt
Step 4: Fix all critical + high issues
Step 5: Re-run and compare
design-critic http://localhost:5173 --compare ~/.design-critic/reviews/PREVIOUS_DIR
Step 6: Only report "done" when score ≥ 80 and 0 critical issues
What It Detects
📱 Responsive / Layout
- Horizontal overflow — elements extending beyond viewport (causes horizontal scrolling)
- Content hidden on mobile — scroll height dramatically shorter than desktop
- Buttons/links disappearing at smaller viewports
- Broken grids — misaligned columns, uneven gutters
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 321 lines · 111 tokens per session scan A df4dad5f1be9
design-critic is a skill published in the GitHub repository JansenAnalytics/claudex (5 stars, last pushed 4mo ago), licensed MIT. It adds 111 tokens to every session and 2,628 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
check
Reviews diffs, PRs, release readiness, and publishing follow-through. Use when asked to review, triage issues or PRs, or ship. Not for debugging root causes or prose.
accessibility
Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".
best-practices
Apply modern web development best practices for security, compatibility, and code quality. Use when asked to "apply best practices", "security audit", "modernize code", "code quality review", or "check for vulnerabilities".
accessibility
Use when making a web UI conform to WCAG 2.2 Level AA — axe-core or Lighthouse a11y violations, keyboard operability, focus management, ARIA roles/names/live regions, contrast, tap-target size. NOT palette or visual intent (that is design), NOT test-runner setup (that is testing-web), NOT LCP/page-speed (that is…
review-all
Multi-agent code review for diffs (project-agnostic). Covers standards, bugs, security, DRY, smells, perf, tests, API contracts, a11y/i18n. Verifies each finding to eliminate false positives. Use for /review-all, pre-PR/pre-commit review, or auditing uncommitted/staged changes.
html-artifact
Create self-contained HTML artifacts (single-file by default, split bundles when oversized) for complex, reviewable, or shareable work outputs. Use for an HTML artifact, browser-viewable report, implementation plan, PR/code-review report, dashboard, or mini deck, or for long Markdown-like outputs needing navigation or…