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 EngineerWithAI/engineerwith-agents --skill screen-reader-testinggit clone --depth 1 https://github.com/EngineerWithAI/engineerwith-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/engineerwithai/engineerwith-agents/screen-reader-testing)<a href="https://agentmods.dev/skills/engineerwithai/engineerwith-agents/screen-reader-testing"><img src="https://agentmods.dev/badge/skills/engineerwithai/engineerwith-agents/screen-reader-testing/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/engineerwithai/engineerwith-agents/screen-reader-testing"><img src="https://agentmods.dev/badge/skills/engineerwithai/engineerwith-agents/screen-reader-testing.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 | $0.00039 | $0.02952 |
| Opus 5.5 | $0.00016 | $0.01181 |
| Sonnet 5.5 | $0.00008 | $0.00590 |
| Haiku 4.5 | $0.00004 | $0.00295 |
Grade A, and why
screen-reader-testing 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.
This is a copy
89% identical to screen-reader-testing — 410 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 534 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Screen Reader Testing
Practical guide to testing web applications with screen readers for comprehensive accessibility validation.
When to Use This Skill
- Validating screen reader compatibility
- Testing ARIA implementations
- Debugging assistive technology issues
- Verifying form accessibility
- Testing dynamic content announcements
- Ensuring navigation accessibility
Core Concepts
1. Major Screen Readers
| Screen Reader | Platform | Browser | Usage |
|---|---|---|---|
| VoiceOver | macOS/iOS | Safari | ~15% |
| NVDA | Windows | Firefox/Chrome | ~31% |
| JAWS | Windows | Chrome/IE | ~40% |
| TalkBack | Android | Chrome | ~10% |
| Narrator | Windows | Edge | ~4% |
2. Testing Priority
Minimum Coverage:
1. NVDA + Firefox (Windows)
2. VoiceOver + Safari (macOS)
3. VoiceOver + Safari (iOS)
Comprehensive Coverage:
+ JAWS + Chrome (Windows)
+ TalkBack + Chrome (Android)
+ Narrator + Edge (Windows)
3. Screen Reader Modes
| Mode | Purpose | When Used |
|---|---|---|
| Browse/Virtual | Read content | Default reading |
| Focus/Forms | Interact with controls | Filling forms |
| Application | Custom widgets | ARIA applications |
VoiceOver (macOS)
Setup
Enable: System Preferences → Accessibility → VoiceOver
Toggle: Cmd + F5
Quick Toggle: Triple-press Touch ID
Essential Commands
Navigation:
VO = Ctrl + Option (VoiceOver modifier)
VO + Right Arrow Next element
VO + Left Arrow Previous element
VO + Shift + Down Enter group
VO + Shift + Up Exit group
Reading:
VO + A Read all from cursor
Ctrl Stop speaking
VO + B Read current paragraph
Interaction:
VO + Space Activate element
VO + Shift + M Open menu
Tab Next focusable element
Shift + Tab Previous focusable element
Rotor (VO + U):
Navigate by: Headings, Links, Forms, Landmarks
Left/Right Arrow Change rotor category
Up/Down Arrow Navigate within category
Enter Go to item
Web Specific:
VO + Cmd + H Next heading
VO + Cmd + J Next form control
VO + Cmd + L Next link
VO + Cmd + T Next table
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 First seen · 534 lines · 39 tokens per session scan A 1205d9d30506
screen-reader-testing is a skill published in the GitHub repository EngineerWithAI/engineerwith-agents (4 stars, last pushed 9mo ago), licensed MIT. It adds 39 tokens to every session and 2,952 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 89% identical to screen-reader-testing, differing in 410 lines, and is treated as a copy.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.