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 punkadillo/figma-code-composer --skill a11y-auditgit clone --depth 1 https://github.com/punkadillo/figma-code-composerWrote 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/punkadillo/figma-code-composer/a11y-audit)<a href="https://agentmods.dev/skills/punkadillo/figma-code-composer/a11y-audit"><img src="https://agentmods.dev/badge/skills/punkadillo/figma-code-composer/a11y-audit.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 | $0.00074 | $0.02358 |
| Opus 5 | $0.00037 | $0.01179 |
| Sonnet 5 | $0.00015 | $0.00472 |
| Haiku 4.5 | $0.00007 | $0.00236 |
Grade A, and why
a11y-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 6d 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.
This is a copy
100% identical to a11y-audit — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility Audit
WCAG 2.2 Accessibility Audit and Remediation Skill
Description
The a11y-audit skill provides a complete accessibility audit pipeline for modern web applications. It implements a three-phase workflow -- Scan, Fix, Verify -- that identifies WCAG 2.2 Level A and AA violations, generates exact fix code per framework, and produces stakeholder-ready compliance reports.
For every violation it finds, it provides the precise before/after code fix tailored to your framework (React, Next.js, Vue, Angular, Svelte, or plain HTML).
What this skill does:
- Scans your codebase for every WCAG 2.2 Level A and AA violation, categorized by severity (Critical, Major, Minor)
- Fixes each violation with framework-specific before/after code patterns
- Verifies that fixes resolve the original violations and introduces no regressions
- Reports findings in a structured format suitable for developers, PMs, and compliance stakeholders
- Integrates into CI/CD pipelines to prevent accessibility regressions
Features
| Feature | Description |
|---|---|
| Full WCAG 2.2 Scan | Checks all Level A and AA success criteria across your codebase |
| Framework Detection | Auto-detects React, Next.js, Vue, Angular, Svelte, or plain HTML |
| Severity Classification | Categorizes each violation as Critical, Major, or Minor |
| Fix Code Generation | Produces before/after code diffs for every issue |
| Color Contrast Checker | Validates foreground/background pairs against AA and AAA ratios |
| Compliance Reporting | Generates stakeholder reports with pass/fail summaries |
| CI/CD Integration | GitHub Actions, GitLab CI, Azure DevOps pipeline configs |
| Keyboard Navigation Audit | Detects missing focus management and tab order issues |
| ARIA Validation | Checks for incorrect, redundant, or missing ARIA attributes |
Severity Definitions
| Severity | Definition | Example | SLA |
|---|---|---|---|
| Critical | Blocks access for entire user groups | Missing alt text, no keyboard access to navigation | Fix before release |
| Major | Significant barrier that degrades experience | Insufficient color contrast, missing form labels | Fix within current sprint |
| Minor | Usability issue that causes friction | Redundant ARIA roles, suboptimal heading hierarchy | Fix within next 2 sprints |
What ships with it
15 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.
- assets/sample-component.tsx 1.2 KB
- expected_outputs/sample-contrast-output.txt 813 B
- expected_outputs/sample-scan-output.json 898 B
- expected_outputs/sample-scan-report.md 2.2 KB
- references/aria-patterns.md 5.9 KB
- references/audit-report-template.md 1.3 KB
- references/ci-cd-integration.md 3.3 KB
- references/color-contrast-guide.md 2.5 KB
- references/examples-by-framework.md 8.0 KB
- references/framework-a11y-patterns.md 14 KB
- references/testing-checklist.md 1.7 KB
- references/wcag-22-new-criteria.md 2.1 KB
- references/wcag-quick-ref.md 6.4 KB
- scripts/a11y_scanner.py 29 KB runs code
- scripts/contrast_checker.py 16 KB runs code
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.
- 6d ago First seen · 212 lines · 74 tokens per session scan A e1cbabce8168
a11y-audit is a skill published in the GitHub repository punkadillo/figma-code-composer (3 stars, last pushed 18d ago), licensed MIT. It adds 74 tokens to every session and 2,358 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to a11y-audit, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
tutti-ui-system
Use when working with @tutti-os/ui-system components, replacing local UI with shared components, querying component ids or metadata, promoting UI into shared base or business components, or maintaining UI-system storyboard inventory.
mcp-host-styling-integration
Integrates MCP App UI with host theming system. Applies host CSS variables, handles onhostcontextchanged, safe area insets, display mode detection, and fullscreen configuration.
moai-design-tools
Design tool integration specialist covering Figma MCP, Pencil renderer, and Pencil-to-code export. Use when fetching design context from Figma, rendering Pencil designs, or exporting to React/Tailwind code.
moai-ref-ui-polish
UI polish and interface-completion reference: the small visual details — concentric border radius, optical alignment, shadow-vs-border, motion easing, typography smoothing, tabular numbers, icon stroke weight, hit areas — that separate polished interfaces from generic ones. Agent-extending skill that amplifies…