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.
git clone --depth 1 https://github.com/Amey-Thakur/AI-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/commands/amey-thakur/ai-skills/review-accessibility)<a href="https://agentmods.dev/commands/amey-thakur/ai-skills/review-accessibility"><img src="https://agentmods.dev/badge/commands/amey-thakur/ai-skills/review-accessibility/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/commands/amey-thakur/ai-skills/review-accessibility"><img src="https://agentmods.dev/badge/commands/amey-thakur/ai-skills/review-accessibility.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 | $0.00019 | $0.00241 |
| Opus 5 | $0.00010 | $0.00120 |
| Sonnet 5 | $0.00004 | $0.00048 |
| Haiku 4.5 | $0.00002 | $0.00024 |
Grade A, and why
review-accessibility 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 4d 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.
What it actually says
You were invoked as a slash command. The user's input:
$ARGUMENTS
Use that input to fill this prompt's variables (take the main content, topic, or task from it; ask only if a required value is missing and not supplied), then follow the prompt exactly.
Review this for accessibility:
{interface}
Context: {context}
Follow the accessibility-review skill, plus keyboard-navigation, aria-usage, and color-contrast as relevant.
Report:
- Barriers that block a user from completing the task, first.
- Barriers that make it harder but not impossible, second.
- For each: who is affected, what happens, and the specific fix.
- What needs testing with a real screen reader or real users.
Rules: prioritise by impact on a person, not by rule identifier. Do not suggest ARIA where semantic HTML would do; state that explicitly when it applies. Say clearly which findings you cannot confirm without running assistive technology. Do not claim compliance with any standard.
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.
- 4d ago First seen · 35 lines · 19 tokens per session scan A d339d4a9f27b
review-accessibility is a command published in the GitHub repository Amey-Thakur/AI-SKILLS (7 stars, last pushed 5d ago), licensed MIT. It adds 19 tokens to every session and 241 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 2026-09-06.
Other commands, from other repositories
design-handoff
Build a current, labeled screenshot package of an app's UI for an external design reviewer, reusing the project's existing screenshot UITest + fastlane lane.
icon-composer
Design a HIG-correct layered Liquid Glass icon and produce Icon Composer-ready art plus an import checklist.
apple-review
Full Apple-grade review (design + engineering + compliance + keynote). Review only, no fixes. Runs the apple-review skill.
handoff
Assemble or verify the design handoff (tokens + section images + notes) that BUILD implements 1:1.
design-review
Structured design review of the current build or a URL — hierarchy, consistency, taste, polish.
accessibility
Audit product accessibility.