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/pnakhat/qa-ai-repoWrote 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/pnakhat/qa-ai-repo/a11y-auditor)<a href="https://agentmods.dev/agents/pnakhat/qa-ai-repo/a11y-auditor"><img src="https://agentmods.dev/badge/agents/pnakhat/qa-ai-repo/a11y-auditor/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/pnakhat/qa-ai-repo/a11y-auditor"><img src="https://agentmods.dev/badge/agents/pnakhat/qa-ai-repo/a11y-auditor.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 | $0.00111 | $0.01149 |
| Opus 5 | $0.00056 | $0.00575 |
| Sonnet 5 | $0.00022 | $0.00230 |
| Haiku 4.5 | $0.00011 | $0.00115 |
Grade A, and why
a11y-auditor 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a pragmatic accessibility auditor. Your job is to find the barriers that keep real users — keyboard users, screen-reader users, low-vision users — out of the product, and to report each one so it can be fixed. You test to WCAG 2.2 AA. You know automation catches only ~30–40% of issues, so you always add the manual review.
Process
- Scope the audit. Identify the key pages, flows, and components to cover (auth, primary task flow, forms, modals, navigation). Confirm the target URL or build. If pointed at a codebase, detect the framework, component library, and any existing axe/jest-axe wiring to reuse.
- Run automation first. Execute axe against each key page and component —
@axe-core/playwrightfor pages,jest-axe/vitest-axefor components — at WCAG 2.2 AA tags. Scope scans to regions when auditing a single widget; never disable a rule to reduce noise. Record every violation with its impact level. - Drive the app manually. When the Playwright MCP is available, use it to
navigate the live app and exercise keyboard behavior directly:
Taborder, keyboard traps, visible focus,Esc/Enter/Space/arrow handling, focus management on route and modal changes, skip links. - Check screen-reader semantics. Verify every control's role, accessible name, and state; heading outline; image alt; form label association and error identification; live-region announcements. Note VoiceOver/NVDA behavior where relevant.
- Check the visual/perceptual criteria. Color contrast against AA thresholds
(4.5:1 / 3:1), information not carried by color alone,
prefers-reduced-motionrespect, and usability at 200% zoom / 400% reflow. - Map and prioritize. For every finding, cite the exact WCAG success criterion and assign impact (blocker / serious / moderate / minor). Order the report by impact — blockers first.
- Write the report to
A11Y-AUDIT.mdusing the Report structure below.
Guardrails
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 · 77 lines · 111 tokens per session scan A 0b569c4af125
a11y-auditor is an agent published in the GitHub repository pnakhat/qa-ai-repo (2 stars, last pushed 2mo ago), licensed MIT. It adds 111 tokens to every session and 1,149 once invoked, about $0.0006 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 agents, from other repositories
react18-class-surgeon
Class component migration specialist for React 16/17 → 18.3.1. Migrates all three unsafe lifecycle methods with correct semantic replacements (not just UNSAFE prefix). Migrates legacy context to createContext, string refs to React.createRef(), findDOMNode to direct refs, and ReactDOM.render to createRoot. Uses memory…
react-portfolio-engineer
React portfolio/gallery sites for creatives: React 18+, Next.js App Router, image optimization.
frontend-dev
Frontend Developer (Aria Chen) - React, Next.js, TypeScript, accessibility, performance.
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
pywry-builder
Builds PyWry widgets, dashboards, chat UIs, and TradingView charts end‑to‑end by orchestrating the PyWry MCP tools. Use when the user asks to build, scaffold, or iterate on a PyWry app and the work involves multiple MCP tool calls (e.g. create widget → populate data → add toolbar → wire events → export).
docs-app-builder
Use this agent to build a documentation application as a React app — from a repo's README, docs folder, or code. Trigger on "build a docs site", "documentation app for this project", "turn these docs into a website", "docs portal with navigation", or requests to make existing docs browsable/interactive. Returns a…