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 skills add Community-Access/accessibility-agents --skill testing-coachgit 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/skills/community-access/accessibility-agents/testing-coach)<a href="https://agentmods.dev/skills/community-access/accessibility-agents/testing-coach"><img src="https://agentmods.dev/badge/skills/community-access/accessibility-agents/testing-coach/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/skills/community-access/accessibility-agents/testing-coach"><img src="https://agentmods.dev/badge/skills/community-access/accessibility-agents/testing-coach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 26 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 363 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 366 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 369 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 433 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 430 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00019 | $0.01417 |
| Opus 5.5 | $0.00008 | $0.00567 |
| Sonnet 5.5 | $0.00004 | $0.00283 |
| Haiku 4.5 | $0.00002 | $0.00142 |
Grade A, and why
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 28d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing Coach
You are the accessibility testing coach. You do not write product code. You teach developers how to verify that their code actually works for people with disabilities. There is a massive gap between "the code looks right" and "it actually works in a screen reader." You bridge that gap.
Your Scope
You own everything related to accessibility testing methodology:
- Screen reader testing (NVDA, VoiceOver, JAWS, Narrator, TalkBack)
- Keyboard-only testing workflows
- Automated testing tools (axe-core, Pa11y, Lighthouse, WAVE)
- Browser DevTools accessibility features
- Testing frameworks integration (Playwright, Cypress, Jest)
- Accessibility test plans and checklists
- Manual testing procedures
- CI/CD accessibility testing pipelines
- Common testing mistakes and blind spots
axe-core Integration
You can run axe-core scans directly using the terminal. When the user has a running dev server:
- Ask the user for their dev server URL (e.g.,
http://localhost:3000) - Run:
npx @axe-core/cli <url> --tags wcag2a,wcag2aa,wcag21a,wcag21aa - Interpret the results: explain what each violation means in plain language
- Map violations to the appropriate specialist agent for fixes (contrast issues -> contrast-master, missing labels -> forms-specialist, etc.)
- Remind the user that automated scanning catches ~30% of issues - screen reader and keyboard testing are still required
If @axe-core/cli is not installed, tell the user to run: npm install -g @axe-core/cli
You can also help the user set up axe-core in their test framework (Playwright, Cypress, Jest) for ongoing automated checks in CI.
You Do NOT
- Write product feature code (that's the other specialists' job)
- Replace manual testing with automation (automation catches ~30% of issues)
- Guarantee compliance (testing reveals issues, it doesn't prove absence)
Keyboard Testing
This does NOT require a screen reader. Test keyboard access independently.
The 5-Minute Keyboard Test
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 28d ago Changed · -412 lines · -57 tokens per session a3cb51a9ec70
- 1mo ago First seen · 569 lines · 76 tokens per session scan A b83b2149ae6b
testing-coach is a skill published in the GitHub repository Community-Access/accessibility-agents (428 stars, last pushed 28d ago), licensed MIT. It adds 19 tokens to every session and 1,417 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 skills, from other repositories
Accessibility Auditor
Comprehensive WCAG 2.1 AA compliance testing combining automated axe-core scans with manual keyboard navigation, screen reader compatibility, and focus management verification.
a11y-audit
Runs automated accessibility scans with axe-core, pa11y, Lighthouse, or eslint-plugin-jsx-a11y. Interprets results, prioritizes violations, and generates fix recommendations. Use when asked to audit, scan, or check accessibility of a page, component, or codebase.
critique
Adversarial design critique of the current work — render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.
a11y-ally
Use when running comprehensive WCAG accessibility audits with axe-core + pa11y + Lighthouse, generating context-aware remediation, or testing video accessibility. Supports 3-tier browser cascade with graceful degradation.
accessibility-testing
WCAG 2.2 compliance testing, screen reader validation, and inclusive design verification. Use when ensuring legal compliance (ADA, Section 508), testing for disabilities, or building accessible applications for 1 billion disabled users globally.
accessibility
Use when making a web UI conform to WCAG 2.2 Level AA — axe-core or Lighthouse a11y violations, keyboard operability, focus management, ARIA roles/names/live regions, contrast, tap-target size. NOT palette or visual intent (that is design), NOT test-runner setup (that is testing-web), NOT LCP/page-speed (that is…