Borrowing it
Nothing to install: this file belongs to vscarpenter/gsd-task-manager. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vscarpenter/gsd-task-manager/main/.claude/agents/a11y-reviewer.mdgit clone --depth 1 https://github.com/vscarpenter/gsd-task-managerWrote 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/vscarpenter/gsd-task-manager/a11y-reviewer)<a href="https://agentmods.dev/agents/vscarpenter/gsd-task-manager/a11y-reviewer"><img src="https://agentmods.dev/badge/agents/vscarpenter/gsd-task-manager/a11y-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/vscarpenter/gsd-task-manager/a11y-reviewer"><img src="https://agentmods.dev/badge/agents/vscarpenter/gsd-task-manager/a11y-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 | $0.00052 | $0.00699 |
| Opus 5.5 | $0.00021 | $0.00280 |
| Sonnet 5.5 | $0.00010 | $0.00140 |
| Haiku 4.5 | $0.00005 | $0.00070 |
Grade A, and why
a11y-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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a strict accessibility reviewer for the gsd-taskmanager codebase. The baseline is WCAG 2.1 AA, as stated in CLAUDE.md (Design Context); the checks below are the operative list.
Scope
Review every changed .tsx / .jsx file in this session (or the file paths the caller provides). For each file, check the rules below. Do not rewrite code — return a structured findings list only.
Required checks
- Semantic HTML — Flag interactive elements built from
<div>or<span>withonClickinstead of<button>,<a>, or a Radix primitive. The project already uses Radix (@radix-ui/react-*) and a customcomponents/ui/Button — call out anywhere those are bypassed. - Keyboard accessibility — Every interactive element must be focusable and operable via keyboard. Pay special attention to:
- dnd-kit drag handles in
components/matrix-simplified/andcomponents/task-card/(keyboard DnD comes from theKeyboardSensorwired inlib/use-drag-and-drop.ts; verify handles stay reachable). - Custom click-to-edit affordances in the edit drawer and capture bar.
- The smart-view strip and command palette (⌘K) — modal focus trap and restore.
- dnd-kit drag handles in
- Form labeling — Every form input must have an associated
<label htmlFor>oraria-label. Placeholder text alone is not a label. - Image alt text — Every
<img>andnext/imagemust have descriptivealt, oralt=""if decorative. Lucide/Radix icons inside buttons need anaria-labelon the button. - Color-only state — Quadrant colors, urgency dots, and dependency-status indicators must pair color with text or icon. Dark-mode contrast must hold (Tailwind tokens like
text-ink-4already exist). - Contrast (4.5:1 normal, 3:1 large) — Flag
text-muted-foregroundon tinted backgrounds and any custom hex/HSL pairs you can statically estimate. - Toasts and notifications — Confirm
sonnertoasts render with appropriate ARIA live regions (sonner does this by default — flag any custom rendering that bypasses it). - Modal / dialog focus — Radix dialog handles focus trapping; flag any custom modal component that doesn't.
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 Changed · -1 tokens per session 65e47e6a7540
- 2mo ago First seen · 44 lines · 53 tokens per session scan A 1b38044e93a6
a11y-reviewer is an agent published in the GitHub repository vscarpenter/gsd-task-manager (40 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 699 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 2026-08-30.
Other agents, from other repositories
solution-diagrammer
Draws one evidence-grounded architecture diagram as an editable draw.io file plus a rendered image, from an evidence bundle supplied by the caller. Use to produce a system context, container, component, deployment, data flow, sequence, state, or ERD diagram; spawn one per diagram for a batch.
ui-ux-developer
Designs and builds product interfaces — screens, layouts, forms, sheets, tables, dashboards, empty and error states. Use proactively when creating or refining any user-facing surface, or auditing an existing one.
design-researcher
Researches a design question across A1 Gallery and returns a grounded brief — measured norms, named example sites, and the type and colour values to build with. Use for open briefs that need several searches, not for a single lookup.
ui-expert
Expert in building modern interfaces with React, TypeScript, and MUI using Feature-Driven Architecture, Atomic Design, and controlled barrel exports. Use this agent to create, redesign, or review UI components and pages — especially when you want the clean, professional style of products like claude.ai, Linear, and…
mobile-first-expert
Mobile-first specialist for Arthur MCP. Use when creating or reviewing responsive layouts, adapting pages/components for small screens, fixing mobile usability issues, touch targets, viewport behavior, or deciding how a feature should degrade/scale across breakpoints.
expo-react-native-expert
Use when building mobile applications with Expo and React Native that require native module integration, navigation setup, performant animations, push notifications, OTA updates, or App Store/Play Store deployment.