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/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/desktop-a11y-testing-coach)<a href="https://agentmods.dev/agents/community-access/accessibility-agents/desktop-a11y-testing-coach"><img src="https://agentmods.dev/badge/agents/community-access/accessibility-agents/desktop-a11y-testing-coach.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 5.1 | $0.00055 | $0.04044 |
| Opus 5 | $0.00028 | $0.02022 |
| Sonnet 5 | $0.00011 | $0.00809 |
| Haiku 4.5 | $0.00006 | $0.00404 |
Grade A, and why
Desktop A11y Testing Coach 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 4d 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 — 431 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authoritative Sources
- NVDA User Guide — https://www.nvaccess.org/files/nvda/documentation/userGuide.html
- JAWS Documentation — https://www.freedomscientific.com/training/jaws/
- Accessibility Insights for Windows — https://accessibilityinsights.io/docs/windows/overview/
- VoiceOver User Guide (macOS) — https://support.apple.com/guide/voiceover/welcome/mac
- UI Automation Testing — https://learn.microsoft.com/en-us/windows/win32/winauto/accessibility-testingtools
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.
Desktop Accessibility Testing Coach
Skills: python-development
You are a desktop accessibility testing coach -- an expert in verifying that desktop applications work correctly with assistive technology. You don't write product code -- you teach and guide testing practices for NVDA, JAWS, Narrator, VoiceOver, Accessibility Insights, and automated UIA testing frameworks.
You receive handoffs from the Developer Hub or Desktop A11y Specialist when testing verification is needed. You also work standalone when invoked directly. You coordinate with the web Testing Coach for shared methodology when desktop apps contain web views.
Core Principles
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.
- 4d ago First seen · 431 lines · 55 tokens per session scan A 3b7e496f3458
Desktop A11y Testing Coach is an agent published in the GitHub repository Community-Access/accessibility-agents (405 stars, last pushed 27d ago), licensed MIT. It adds 55 tokens to every session and 4,044 once invoked, about $0.0003 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
bench-runner
Executes a11y skill benchmarks across hosted and local model families. Runs cloud/Codex/Ollama benchmark scripts, monitors progress, handles errors and retries. Reports raw results to the team.
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).
bench-reviewer
Reviews eval suite quality — fixture/rubric consistency, scoring accuracy, false positive traps, difficulty calibration. Read-only reviewer that identifies issues without fixing them.
quality-assurance
Design quality assurance specialist for visual consistency and cross-browser testing.
qa-agent
QA and validation automation agent. Writes and executes test plans, captures visual state, validates UI correctness, runs accessibility audits, performs smoke tests. Use when testing apps, validating UI, running regression checks, or auditing accessibility.
Demonstrate
Agent for demonstrating VS Code features.