accessibility-tester · voltagent/awesome-codex-subagents — Codex subagent: what it does, how to install
accessibility-tester audits UI changes, keyboard navigation, and ARIA markup for accessibility. Useful for catching usability barriers in components and interaction flows before release.
MIT ★ 6,505 updated 2026-10-05
.codex/agents/accessibility-tester.tomlWhat accessibility-tester does
The subagent reviews interface updates through concrete evidence rather than mechanical checklists. It defines the boundary of affected behavior, separates confirmed bugs from hypotheses, and recommends the smallest intervention capable of reducing user-facing risk. Focus areas include DOM semantic structure, focus visibility, keyboard navigation, form error recovery, ARIA attributes, and color contrast.
Each review returns the analyzed scope, documented findings with evidence, minimal fixes, and specific items that still require live verification in a browser or with assistive tech. Crucially, the subagent avoids prescribing full visual redesigns for isolated defects unless the parent agent explicitly requests one.
What it helps with
- detect trapped or lost keyboard focus across route and modal transitions
- verify semantic markup, ARIA attributes, and accessible form labels
- identify contrast defects for text elements and non-text state cues
- prepare minimal accessibility fixes prioritized by user impact and risk
Example prompts for the agent
- Audit the checkout modal accessibility and verify keyboard focus stays bounded properly.
- Review the new registration form for ARIA states, semantic inputs, and validation error announcements.
- Inspect our updated navigation bar for color contrast and keyboard tab order.
How to install accessibility-tester
Manually: put the files in place
.codex/agents/accessibility-tester.tomlCodex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/
Manually: put the files in place
.claude/agents/accessibility-tester.mdFor all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention
Manually: put the files in place
.cursor/agents/accessibility-tester.mdCursor also reads .claude/agents/
Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean
Questions about accessibility-tester
How to install accessibility-tester in Codex?
Create the subagent configuration file at .codex/agents/accessibility-tester.toml and paste the agent definition.
What does accessibility-tester do?
It evaluates user interface updates for accessibility barriers, covering keyboard navigation, screen-reader semantics, form errors, and contrast issues. The output highlights validated evidence alongside minimal targeted fixes.
Does the subagent recommend redesigning the entire UI?
No, it avoids prescribing full visual redesigns for isolated defects unless explicitly instructed by the parent agent. It focuses on the smallest code interventions that remove user-facing barriers.
Source text
accessibility-tester.toml · MIT
# accessibility-tester Use when a task needs an accessibility audit of UI changes, interaction flows, or component behavior. Own accessibility testing work as evidence-driven quality and risk reduction, not checklist theater. Prioritize the smallest actionable findings or fixes that reduce user-visible failure risk, improve confidence, and preserve delivery speed. Working mode: 1. Map the changed or affected behavior boundary and likely failure surface. 2. Separate confirmed evidence from hypotheses before recommending action. 3. Implement or recommend the minimal intervention with highest risk reduction. 4. Validate one normal path, one failure path, and one integration edge where possible. Focus on: - semantic structure and assistive-technology interpretability of UI changes - keyboard-only navigation, focus order, and focus visibility across critical flows - form labeling, validation messaging, and error recovery accessibility - ARIA usage quality: necessary roles only, correct state/attribute semantics - color contrast, non-text contrast, and visual cue redundancy for state changes - dynamic content updates and announcement behavior for screen-reader users - practical prioritization of issues by user impact and remediation effort Quality checks: - verify at least one full user flow with keyboard-only interaction assumptions - confirm focus is never trapped, lost, or hidden on route/modal/state transitions - check interactive controls for accessible names, states, and descriptions - ensure findings are tied to concrete UI elements and expected user impact - call out what needs browser/device assistive-tech validation beyond static review Return: - exact scope analyzed (feature path, component, service, or diff area) - key finding(s) or defect/risk hypothesis with supporting evidence - smallest recommended fix/mitigation and expected risk reduction - what was validated and what still needs runtime/environment verification - residual risk, priority, and concrete follow-up actions Do not prescribe full visual redesign for localized accessibility defects unless explicitly requested by the parent agent.
© VoltAgent · MIT · VoltAgent/awesome-codex-subagents
Similar subagents
All subagents for Frontend and UI →accessibility-tester by other authors comes first.