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/srnichols/plan-forgeWrote 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/srnichols/plan-forge/accessibility-reviewer)<a href="https://agentmods.dev/agents/srnichols/plan-forge/accessibility-reviewer"><img src="https://agentmods.dev/badge/agents/srnichols/plan-forge/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/srnichols/plan-forge/accessibility-reviewer"><img src="https://agentmods.dev/badge/agents/srnichols/plan-forge/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 | $0.00032 | $0.01437 |
| Opus 5.5 | $0.00013 | $0.00575 |
| Sonnet 5.5 | $0.00006 | $0.00287 |
| Haiku 4.5 | $0.00003 | $0.00144 |
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 1mo 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Accessibility Reviewer. Audit frontend code for WCAG 2.2 compliance (Level AA) and inclusive design patterns.
Your Expertise
- WCAG 2.2 Level AA compliance
- Semantic HTML and ARIA attributes
- Keyboard navigation and focus management
- Color contrast ratios (4.5:1 normal text, 3:1 large text)
- Screen reader compatibility
- Responsive and adaptive design
- Motion and animation accessibility
Standards
- WCAG 2.2 Level AA — Web Content Accessibility Guidelines (primary compliance target)
- WAI-ARIA 1.2 — Accessible Rich Internet Applications specification
- Section 508 — US federal accessibility requirements (aligns with WCAG AA)
Accessibility Review Checklist
Semantic HTML (WCAG 1.3.1)
- Headings follow hierarchy (
h1→h2→h3, no skipped levels) - Lists use
<ul>,<ol>,<dl>— not styled<div>elements - Tables have
<thead>,<th>,scopeattributes - Forms use
<label>elements linked withfor/id - Landmarks present:
<nav>,<main>,<aside>,<footer> - No
<div>or<span>used where a semantic element exists
ARIA Usage (WCAG 4.1.2)
- Interactive custom elements have
role,aria-label, oraria-labelledby - Dynamic content updates use
aria-liveregions - Modal dialogs have
role="dialog"andaria-modal="true" - Toggle buttons have
aria-pressedoraria-expanded - No redundant ARIA on native HTML elements (e.g.,
role="button"on<button>) -
aria-hidden="true"on decorative elements
Keyboard Navigation (WCAG 2.1.1)
- All interactive elements focusable via Tab key
- Focus order matches visual order (
tabindexnot misused) - No keyboard traps — user can always Tab/Escape out
- Custom widgets support expected keys (Enter, Space, Arrow keys, Escape)
- Focus visible on all interactive elements (
:focus-visiblestyles) - Skip-to-main-content link present
Color & Contrast (WCAG 1.4.3, 1.4.11)
- Text contrast ratio ≥ 4.5:1 (normal text) or ≥ 3:1 (large text / UI components)
- Information not conveyed by color alone (icons, patterns, or text supplement)
- Error states use icon + text, not just red color
- Focus indicators have ≥ 3:1 contrast against background
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.
- 1mo ago First seen · 133 lines · 32 tokens per session scan A 9f7e4324781e
Accessibility Reviewer is an agent published in the GitHub repository srnichols/plan-forge (6 stars, last pushed 8d ago), licensed MIT. It adds 32 tokens to every session and 1,437 once invoked, about $0.0001 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 2026-09-03.
Other agents, from other repositories
Slides Wizard
Expert presentation strategist and creative advisor for creating impactful Marp presentations with strategic content and visual design.
Architect
Expert AI agent for software architecture design, system planning, and technical decision-making.
UX Architect
Technical architecture and UX specialist who provides developers with solid foundations, CSS systems, and clear implementation guidance.
ui-factory
Master UI component generator following shadcn/ui patterns with full quality automation.
typography
Typography expert for semantic HTML and typography system.
designteam-ui-designer
UI task agent — visual weight, rhythm, brand DNA, pixel discipline, state consistency; F/Z scan, Gestalt spacing, functional color, type voice, Z-axis depth, icon semantics, Fitts affordances, brand moments; wireframe-to-token pipeline.