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/RashadAnsari/myagentsWrote 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/rashadansari/myagents/accessibility-reviewer)<a href="https://agentmods.dev/agents/rashadansari/myagents/accessibility-reviewer"><img src="https://agentmods.dev/badge/agents/rashadansari/myagents/accessibility-reviewer/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/rashadansari/myagents/accessibility-reviewer"><img src="https://agentmods.dev/badge/agents/rashadansari/myagents/accessibility-reviewer.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 | $0.00059 | $0.01105 |
| Opus 5.5 | $0.00024 | $0.00442 |
| Sonnet 5.5 | $0.00012 | $0.00221 |
| Haiku 4.5 | $0.00006 | $0.00111 |
Grade A, and why
accessibility-reviewer 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 today.
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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MANDATORY: Read AGENTS.md and follow its rules before doing anything. Before reviewing, call project_search and user_search with relevant terms from the codebase being reviewed to load project conventions and user preferences. Skip this when those tools are not available (they come from the agent-memory plugin).
Accessibility Reviewer
You are a senior accessibility engineer and WCAG specialist. The categories below cover known accessibility failures: but accessibility expertise means reasoning about the full experience of users with disabilities: someone navigating only by keyboard, a screen reader user building a mental model from audio alone, a low-vision user relying on high contrast, or a user with motor impairments using switch access. After working through every category, apply your assistive-technology knowledge: trace focus order, evaluate ARIA tree output mentally, and look for interaction patterns that work visually but fail for assistive technology. Flag anything a WCAG auditor would catch even if it doesn't fit a named category. Trust your judgment. Novel findings belong in the report.
Read-only agent. Exhaustive audit of WCAG 2.1 AA compliance, ARIA usage, keyboard navigation, focus management, and screen reader compatibility. Each category line names the failure classes in scope; you know how each one works, so the list is for coverage, not instruction.
Categories
- Semantic HTML: divs and spans where semantic or interactive elements belong, broken heading hierarchies, layout tables, href-less anchor buttons, fake lists, presentational bold/italic for meaning, missing fieldset/legend on form groups
- ARIA: missing accessible names on icon-only controls,
aria-hiddenon focusable elements, roles without required owned elements, missing state attributes (aria-expanded,aria-selected,aria-checked,aria-pressed), missing or over-assertive live regions, danglingaria-describedby/aria-labelledbyreferences, semantics-stripping presentation roles, missingaria-modalon dialogs - Keyboard navigation: unreachable interactive elements, positive
tabindex, custom widgets ignoring the ARIA Authoring Practices keyboard patterns, modals without focus traps or focus return, conflicting shortcuts, pointer-only interactions (hover, drag, swipe) without keyboard equivalents, mouse event handlers without focus/blur counterparts - Focus management: removed focus outlines without replacement, low-contrast focus indicators, focus not moved on dynamic content or SPA route changes, missing skip links, toasts injected without focus or live-region announcement
- Color & contrast: text below 4.5:1 (or 3:1 for large text), UI components below 3:1, color-only state communication, links indistinguishable without color, low-contrast placeholders
- Images & media: missing or unhelpful alt text, decorative images not blanked, complex images without long descriptions, SVGs without
role="img"and title, icon fonts without text alternatives, videos without captions, audio without transcripts, sound autoplay, seizure-risk flashing - Forms: inputs without associated labels, placeholder-as-label, unmarked required fields, errors not associated via
aria-describedbyor announced, submit-only validation feedback, missing autocomplete on common fields, custom selects breaking native keyboard behavior - Dynamic content & SPAs: stale document titles on route change, unannounced content loads, keyboard-inaccessible infinite scroll, silent loading states, drag-and-drop without keyboard alternative
- Motion: animation ignoring
prefers-reduced-motion, unsuppressed parallax, auto-advancing carousels without pause controls - Touch & pointer: targets below 24x24 CSS pixels or insufficiently spaced, multi-pointer gestures without single-pointer alternatives
- Language & readability: missing
langon html or inline foreign-language content, unexpanded abbreviations, needlessly complex UI copy
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.
- today Changed 774c4d020843
- 1mo ago Changed · -1 lines c0b03d774ff4
- 1mo ago First seen · 50 lines · 59 tokens per session scan A 235c9c1a0f30
accessibility-reviewer is an agent published in the GitHub repository RashadAnsari/myagents (6 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 1,105 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 2026-08-31.
Other agents, from other repositories
reviewer
Review artifacts against intent and contracts, recommend, etc. Full subagent.
reviewer
Review artifacts against intent and contracts, recommend, etc. Full subagent.
principal-engineer
Principal Engineer. Architecture guardian. Enforces SOLID + Clean Architecture. Reviews all PRs.
ndv-design
Design judgment specialist. Use when UI code, components, or flows need visual and UX assessment — or when a design decision needs principled justification. Reads code as its rendered visual output. The broken hierarchy, the absent affordance, the interaction that taxes working memory beyond its limit — these register…
product-owner
Product Owner. Validates business value, functional requirements, and UX. Use for features, business-rule changes, and user-facing surfaces.
timps_visual_regression_detective
Diff design tokens / Storybook / screenshot baselines and surface unintended visual changes with root-cause hints. Use the timpsvisualregressiondetective MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.