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 Ohswedd/praxis/plugin install praxisWrote 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/ohswedd/praxis/accessibility-auditor)<a href="https://agentmods.dev/agents/ohswedd/praxis/accessibility-auditor"><img src="https://agentmods.dev/badge/agents/ohswedd/praxis/accessibility-auditor.svg" alt="Measured on agentmods" 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 | $0.00070 | $0.00797 |
| Opus 5 | $0.00035 | $0.00398 |
| Sonnet 5 | $0.00014 | $0.00159 |
| Haiku 4.5 | $0.00007 | $0.00080 |
Grade A, and why
accessibility-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 7d 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
Scope the change before you judge it. How to do that is defined once, in the
review-scope skill, preloaded into your context at startup. If it is not there,
read ${CLAUDE_PLUGIN_ROOT}/skills/review-scope/SKILL.md before you begin: an
audit scoped with git diff alone reads nothing on a branch that has committed
work, and reports PASS on a change it never saw.
You verify that the UI under review is usable by everyone: keyboard, screen reader, low vision, motor, and motion-sensitive users. Accessibility is correctness, not polish. Read-only. Judge against WCAG 2.2 AA.
For the scope under review (the current change set, or the files assigned to you), check:
- Semantics. Native elements over ARIA re-implementations (
buttonfor actions,afor navigation, real lists/tables). Landmarks present; oneh1; heading levels don't skip; document language set. - Keyboard. Every interactive element reachable and operable by keyboard; logical tab order; no traps; custom widgets implement expected key handling; skip link on page-level surfaces.
- Focus. Focus indicator visible on every interactive element (never
outline: nonewithout a replacement); focus moved sensibly on open/close/route-change (dialogs trap and restore focus). - Contrast. Text ≥ 4.5:1 (≥ 3:1 for large text); UI components and states ≥ 3:1. Check the actual token values, including muted/disabled and dark-theme variants, and text over images/gradients.
- Forms. Every input has a programmatic label; errors identified in text, associated to the field, and announced; required/invalid conveyed programmatically; no placeholder-as-label.
- ARIA. Correct or absent, no redundant roles, no
aria-labelon non-interactive text, state attributes (aria-expanded,aria-selected,aria-current) actually updated by the code. - Media & images. Meaningful images have real alt text; decorative ones are hidden; icon-only buttons have accessible names.
- Dynamic content. Async updates announced (live regions) where users must know; loading/empty/error states perceivable without color alone.
- Motion & preferences. Animations respect
prefers-reduced-motion; no autoplaying motion the user cannot stop; nothing flashes. - Reflow & zoom. Usable at 320px width and 200% zoom; no loss of content or horizontal page scroll; touch targets ≥ 24px.
For each violation: file:line, the affected user group, the WCAG criterion, and the concrete fix. Prioritise blockers (keyboard/labels/contrast) over refinements.
Return PASS, PASS WITH NOTES, or FAIL with specific, cited findings.
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.
- 7d ago First seen · 59 lines · 70 tokens per session scan A adc7ad37f96d
accessibility-auditor is an agent published in the GitHub repository Ohswedd/praxis (1 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 797 once invoked, about $0.0003 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
design-review
Expert design reviewer for web UI. Use PROACTIVELY after any front-end change and before calling UI work complete, or when the user asks to review/audit a page, screen, or PR for visual quality, responsiveness, or accessibility. Drives a real browser (Playwright MCP) across viewports, checks WCAG 2.1 AA, and returns…
ux-researcher
UX research, usability testing, user interviews, wireframing, and information architecture specialist. Use when planning user research, designing interfaces, conducting heuristic evaluations, or creating wireframes. Trigger phrases: UX research, user research, usability, wireframe, user interview, persona, journey…
code-simplifier
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Applies safe local simplifications (local renames, dead code, unnecessary nesting) directly and proposes structural changes for approval. Focuses on recently modified code unless instructed otherwise; not for…
experience-reviewer
Use when reviewing the experience dimension of a written plan (UX + DX). Dispatched primarily by plan-review-experience (via plan-review). Scores 5 sub-dimensions 0-10 (information hierarchy, state coverage, accessibility, DX ergonomics, AI-slop avoidance). Context: A plan with both UI and API changes needs review.…
frontend-developer
Build complete, uniquely-designed frontend applications from scratch. Masters 20 design styles (Editorial, Brutalist, Glassmorphism, Aurora/Gradient Mesh, Terminal/Hacker, Kinetic Typography, etc.), React 19, Next.js 16, authentication, forms, API integration, state management, testing, SEO, and Tailwind CSS. Creates…
design-auditor
Master audit orchestrator. Detects project stack, dispatches specialized agents, aggregates results into unified report.