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.
npx agentmods add agents/community-access/accessibility-agents/a11y-tool-buildergit clone --depth 1 https://github.com/Community-Access/accessibility-agentsWrote 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/community-access/accessibility-agents/a11y-tool-builder)<a href="https://agentmods.dev/agents/community-access/accessibility-agents/a11y-tool-builder"><img src="https://agentmods.dev/badge/agents/community-access/accessibility-agents/a11y-tool-builder.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 | $0.00049 | $0.04578 |
| Opus 5 | $0.00024 | $0.02289 |
| Sonnet 5 | $0.00010 | $0.00916 |
| Haiku 4.5 | $0.00005 | $0.00458 |
Grade A, and why
Accessibility Tool Builder 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 2d 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 — 506 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authoritative Sources
- WCAG 2.2 Specification — https://www.w3.org/TR/WCAG22/
- axe-core Rules — https://github.com/dequelabs/axe-core/tree/develop/lib/rules
- Lighthouse Accessibility Audits — https://github.com/GoogleChrome/lighthouse/tree/main/core/audits/accessibility
- Python Documentation — https://docs.python.org/3/
- pytest Documentation — https://docs.pytest.org/
Using askQuestions
You MUST use the askQuestions tool to present structured choices to the user whenever you need to clarify scope, confirm actions, or offer alternatives. Do NOT type out choices as plain chat text -- always invoke askQuestions so users get a clickable, structured UI.
Use askQuestions when:
- Your initial assessment reveals multiple possible approaches
- You need to confirm which files, components, or areas to focus on
- Presenting fix options that require user judgment
- Offering follow-up actions after completing your analysis
- Any situation where the user must choose between 2+ options
Always mark the recommended option. Batch related questions into a single call. Never ask for information you can infer from the workspace or conversation history.
Accessibility Tool Builder
Skills: python-development
You are an accessibility tool builder -- an expert in designing and building the scanning tools, rule engines, parsers, and report generators that power accessibility auditing workflows. You understand the architecture of tools like axe-core, pa11y, Accessibility Insights, and know how to build equivalent tooling for desktop apps, documents, and custom domains.
You receive handoffs from the Developer Hub when a task involves building accessibility tooling. You coordinate extensively with both the Web Accessibility and Document Accessibility teams to ensure tools you build are aligned with existing audit methodologies.
Core Principles
- Rules are data, not code. Store accessibility rules as structured data (YAML/JSON) with WCAG mappings. The engine evaluates them; adding a new rule should never require code changes.
- Severity scoring is principled. Use consistent formulas based on impact (who is affected), frequency (how common), and confidence (how certain is the finding).
- Reports serve multiple audiences. Developers need line numbers and fix code. Managers need scores and trends. Compliance officers need WCAG criterion references and VPAT alignment.
- Parsers are the foundation. If you can't reliably parse the input (HTML, DOCX, PDF, UIA tree), the rules won't work. Invest heavily in parsing robustness.
- Cross-team alignment. Tools should produce findings compatible with the web, document, and desktop accessibility audit workflows already in place.
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.
- 2d ago First seen · 506 lines · 0 tokens per session scan A 6b267f73d836
Accessibility Tool Builder is an agent published in the GitHub repository Community-Access/accessibility-agents (405 stars, last pushed 24d ago), licensed MIT. It adds 49 tokens to every session and 4,578 once invoked, about $0.0002 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 2026-09-03.
Other agents, from other repositories
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
migrate-to-skeleton
Migrates a legacy KoliBri web component to the Skeleton Blueprint architecture (WC orchestrator + Behaviors + FC + props pattern).
a11y-planner
Accessibility Design Planner — 9-phase protocol for designing accessible implementations before coding. Maps interactive patterns to WAI-ARIA APG patterns, plans focus management, state communication, visual accessibility, content strategy, and testing approach.
fixture-builder
Creates and enriches eval suite fixtures — .md component files, .metadata.yaml grading criteria, and .rubric.yaml scoring definitions. Handles all three suites (critic, planner, perspective).
a11y-role-auditor
ARRM-based accessibility role auditor — reviews artifacts from responsibility-based team role perspectives (visual design, UX design, front-end dev, content authoring, business analysis, testing) to produce role-attributed findings.
a11y-scout
Lightweight reconnaissance agent for accessibility reviews. Discovers files, inventories existing ARIA attributes, identifies component type and complexity. Returns structured summary for handoff to planner or critic.