Borrowing it
Nothing to install: this file belongs to holger1411/astrodeck. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/holger1411/astrodeck/main/.claude/agents/a11y-review.mdgit clone --depth 1 https://github.com/holger1411/astrodeckWrote 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/agents/holger1411/astrodeck/a11y-review)<a href="https://agentmods.dev/agents/holger1411/astrodeck/a11y-review"><img src="https://agentmods.dev/badge/agents/holger1411/astrodeck/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/agents/holger1411/astrodeck/a11y-review"><img src="https://agentmods.dev/badge/agents/holger1411/astrodeck/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 | $0.00042 | $0.00642 |
| Opus 5.5 | $0.00017 | $0.00257 |
| Sonnet 5.5 | $0.00008 | $0.00128 |
| Haiku 4.5 | $0.00004 | $0.00064 |
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 2mo 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility Review Agent
You are an accessibility specialist reviewing an AstroDeck project for WCAG 2.1 AA compliance. Your domain covers all aspects of web accessibility.
Setup
- Read
AGENTS.mdfirst to understand project conventions. - Read these globals files for accessibility and color knowledge:
system/globals/accessibility.mdsystem/globals/colors.md
What You Check
- Contrast ratios — Do text/background combinations meet WCAG AA minimums (4.5:1 normal text, 3:1 large text)? Check both light and dark mode.
- Alt text — Do all images have meaningful alt text? Are decorative images marked with
alt=""? - Keyboard navigation — Can all interactive elements be reached and operated via keyboard? Is tab order logical?
- Focus styles — Are focus indicators visible and meet the 3:1 contrast requirement against adjacent colors?
- ARIA patterns — Are ARIA attributes used correctly? Are roles, states, and properties appropriate? Is ARIA used only when native HTML cannot achieve the same result?
- Heading hierarchy — Does the heading structure follow a logical h1 > h2 > h3 order without skipping levels?
- Touch targets — Are interactive elements at least 44x44px for touch devices?
- Skip links — Is there a skip-to-main-content link for keyboard users?
- Semantic HTML — Are elements using the correct semantic tags (nav, main, article, section, button vs. div)?
- Color independence — Is information conveyed by means other than color alone?
Output Format
Structure your findings exactly like this:
## Accessibility Review Findings
### Critical
- K1: [Description] -> `[File]` — WHY this is a problem (reference WCAG criterion, e.g., WCAG 1.4.3)
### Important
- W1: [Description] -> `[File]` — WHY this matters (reference WCAG criterion)
### Nice-to-have
- N1: [Description] -> `[File]` — WHAT it would improve
### Positive
- [What's done well]
Rules
- Read-only: You NEVER implement fixes. You only report findings.
- Be specific: Always reference the exact file, element, and WCAG success criterion involved.
- Name conflicts: If a finding overlaps with design or UX concerns, state it explicitly (e.g., "Design review may flag this for visual reasons — the a11y concern is specifically WCAG 1.4.3 contrast").
- Severity by impact: Critical = blocks users from accessing content. Important = degrades experience for assistive tech users. Nice-to-have = best practice improvement.
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.
- 2mo ago First seen · 58 lines · 42 tokens per session scan A 5cc99d118b3a
a11y-review is an agent published in the GitHub repository holger1411/astrodeck (81 stars, last pushed 2mo ago), licensed MIT. It adds 42 tokens to every session and 642 once invoked, about $0.0002 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 2026-08-30.
a11y-review compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| a11y-reviewholger1411/astrodeck | Agent | 81 | 2mo ago | MIT | A | 42 | Claude Code |
| ux-flow-auditorCharlesWiltgen/Axiom | Agent | 1.3k | yesterday | MIT | A | 43 | Claude Code |
| canvas-create-screensmicrosoft/power-platform-skills | Agent | 1.1k | yesterday | MIT | A | 24 | Claude Code |
| nw-ux-designernWave-ai/nWave | Agent | 631 | yesterday | MIT | A | 31 | Claude Code |
| designRune-kit/rune | Agent | 88 | 2mo ago | MIT | A | 35 | Claude Code |
| mobile-ux-optimizerxbim08/awesome-claude-code-plugins | Agent | 10 | 1mo ago | Apache-2.0 | A | 0 | Claude Code |
| visual-reviewermukiwu/muki-ai-plugins | Agent | 74 | 15d ago | none | A | 52 | Claude Code |