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 arozumenko/sdlc-skills --skill accessibility-auditgit clone --depth 1 https://github.com/arozumenko/sdlc-skillsWrote 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/arozumenko/sdlc-skills/accessibility-audit)<a href="https://agentmods.dev/skills/arozumenko/sdlc-skills/accessibility-audit"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/accessibility-audit/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/arozumenko/sdlc-skills/accessibility-audit"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/accessibility-audit.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 | $0.00028 | $0.00582 |
| Opus 5 | $0.00014 | $0.00291 |
| Sonnet 5 | $0.00006 | $0.00116 |
| Haiku 4.5 | $0.00003 | $0.00058 |
Grade A, and why
accessibility-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 10d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility & WCAG Analysis
Two analysis passes:
- Accessibility ♿ — General a11y, user experience impact
- WCAG Compliance 📋 — Technical WCAG 2.1 AA/AAA criteria
Data Sources
Primary — browser_snapshot(): the accessibility tree gives roles, accessible
names, and structure for every element. Use it to check for missing accessible
names, wrong roles, and reading-order-vs-visual-order mismatches.
browser_take_screenshot() — visual review for contrast, focus visibility,
layout/reading order, and issues no accessibility tree can show.
Limitation: the factory's Playwright MCP toolset has no browser_evaluate
(and therefore no way to inject axe-core), so there are no axe violation IDs,
impact levels, or helpUrl/failureSummary evidence in this environment.
Every finding must instead cite a browser_snapshot node or a screenshot region
as evidence, and confidence must be scored against that weaker evidence (per the
evidence rule in audit-methodology.md) — never claim an axe-core finding or
impact level that wasn't actually gathered.
Accessibility ♿ — Focus Areas
Look for: missing alt text, unlabeled form controls, poor color contrast, keyboard navigation issues, missing ARIA roles, focus order problems, skip navigation, screen reader compatibility, interactive elements without accessible names, missing form error announcements.
WCAG 📋 — Criteria
See references/wcag-checklist.md for full criteria:
- Contrast ratios below 4.5:1 (AA) or 7:1 (AAA)
- Missing text alternatives (1.1.1)
- Keyboard traps (2.1.2)
- Time limits without controls (2.2.1)
- No bypass blocks (2.4.1)
- Focus not visible (2.4.7)
- Language not specified (3.1.1)
- Error identification missing (3.3.1)
- Name/role/value violations (4.1.2)
Output
Produce findings in the shared schema — see the qa-auditor audit-methodology.md.
Each finding must reference specific evidence: a browser_snapshot node (role +
accessible name) or a screenshot region — never an axe violation ID (unavailable
in this environment; see Limitation above).
What ships with it
1 file 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.
- 10d ago First seen · 63 lines · 28 tokens per session scan A b3cb8504eebd
accessibility-audit is a skill published in the GitHub repository arozumenko/sdlc-skills (20 stars, last pushed 5d ago), licensed MIT. It adds 28 tokens to every session and 582 once invoked, about $0.0001 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.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.