Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add int2t05/engineering-skills/plugin install engineering-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/int2t05/engineering-skills/a11y-review)<a href="https://agentmods.dev/skills/int2t05/engineering-skills/a11y-review"><img src="https://agentmods.dev/badge/skills/int2t05/engineering-skills/a11y-review/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/int2t05/engineering-skills/a11y-review"><img src="https://agentmods.dev/badge/skills/int2t05/engineering-skills/a11y-review.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 | $0.00087 | $0.01257 |
| Opus 5 | $0.00044 | $0.00629 |
| Sonnet 5 | $0.00017 | $0.00251 |
| Haiku 4.5 | $0.00009 | $0.00126 |
Grade A, and why
a11y-review 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 11d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility Review
Accessibility is a verify-phase audit, the same shape as security-review: define the
conformance target, run the automated layer, walk the manual checks, triage each finding
to fix or accept-with-rationale. Automated tools (axe-core) catch ~30–40% of issues; the
rest require a keyboard and screen-reader walkthrough. A page that passes axe but fails
keyboard nav is not accessible.
When to use
- Reviewing a UI change (new page, component, form, interaction) before merge.
- A feature touches focus order, dynamic content, media, or color-only signaling.
- Hitting a conformance requirement (WCAG 2.1/2.2 AA is the legal/commercial default; AA is the target here unless stated).
- An automated a11y scan (axe, Lighthouse) surfaced findings to triage.
Not for: general code-quality review (use code-review); machine-detectable lint/style (use linting); runtime behavior bugs (use debugging). a11y-review is the human-judgment + tool-assisted audit layer.
Steps
1. Confirm the conformance target and scope
WCAG 2.2 AA is the default (covers 2.1 AA + new criteria). AAA is opt-in and only for specific surfaces. Scope: which pages/components are in this review? A full-site audit is different from a single-PR review — state the boundary.
2. Run the automated layer
axe-core (or Lighthouse a11y audit) catches the machine-detectable class: missing alt text, empty buttons, insufficient contrast (ratio < 4.5:1 for text), duplicate IDs, missing form labels, invalid ARIA roles. Run it against the rendered DOM, not the source — client-rendered content needs a real browser. Capture every finding with its rule ID.
3. Walk the manual WCAG checks
Automated tools miss the structural and interaction issues. Check per page/component — see references/wcag-checklist.md for the criterion-by-criterion list. The high-value manual checks:
- Keyboard — every interactive element reachable in logical order via Tab; no keyboard traps; visible focus indicator on every focusable element.
- Focus management — route changes and modal opens move focus; modals trap focus correctly and return it on close.
- Heading order —
<h1>→<h2>→<h3>without skipping levels; one<h1>per view. - Color independence — information isn't conveyed by color alone (error states have text/icon, not just red); links are distinguishable beyond color.
- Dynamic content —
aria-liveregions announce updates; loading and error states are perceivable by AT. - Media — images have alt (decorative =
alt=""); video has captions; audio has transcript.
What ships with it
2 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.
- 11d ago First seen · 74 lines · 87 tokens per session scan A 09e7990f12fa
a11y-review is a skill published in the GitHub repository int2t05/engineering-skills (3 stars, last pushed 10d ago), licensed MIT. It adds 87 tokens to every session and 1,257 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
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.
Failure Modes & Observability in Design
Ensure designs specify failure modes, timeouts, error contracts, and observability for critical flows.
sonarqube
Levantar SonarQube con Docker, analizar el código y proponer mejoras. También: análisis estático, deuda técnica, code smells, cobertura, calidad automatizada.
audit
Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.
skeptical-triage
Reusable 3-round self-challenge + arbiter pattern for filtering false positives from findings/verdicts. Use when the cost of a false-positive gate block exceeds the cost of 4 extra LLM turns.
anti-patterns
Catalogue of known SDLC anti-patterns that greatcto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).