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 pwdev-solucoes/pwdev-claude-marketplace --skill qa-specialist-accessibilitygit clone --depth 1 https://github.com/pwdev-solucoes/pwdev-claude-marketplaceWrote 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/pwdev-solucoes/pwdev-claude-marketplace/qa-specialist-accessibility)<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/qa-specialist-accessibility"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/qa-specialist-accessibility/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/pwdev-solucoes/pwdev-claude-marketplace/qa-specialist-accessibility"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/qa-specialist-accessibility.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 | $0.00029 | $0.01141 |
| Opus 5.5 | $0.00012 | $0.00456 |
| Sonnet 5.5 | $0.00006 | $0.00228 |
| Haiku 4.5 | $0.00003 | $0.00114 |
Grade A, and why
qa-specialist-accessibility 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA accessibility specialist
Use this specialist when a QA workflow needs accessibility coverage for real product behavior. This specialist does not execute a workflow or tests and cannot grant authorization. Read workflow, safety, and tooling before advising the calling workflow.
Inputs
- Target, platform, environment, identified contract, applicable accessibility standard, and preserved criterion IDs and text.
- User journeys, component states, supported input methods, browser/device matrix, viewport and zoom requirements, and expected observable behavior.
- Native/library primitives actually rendered, accessible names, roles, states, relationships, status/error announcements, and content/language structure.
- Scanner, browser/device, platform inspector, assistive technology, and test-runner probes, each
with
state,result, andevidence. - Synthetic or reviewed data, evidence needs, access, and explicit authorization boundaries.
Procedure
- Preserve target, contract, criteria, standard, platform matrix, and authorization. Inspect the behavior actually rendered; a component library's accessibility claim is not product evidence.
- Define a keyboard-only journey for every applicable interaction: reach, operate, dismiss, reverse, escape traps, and recover from errors without a pointer. Record expected and observed behavior separately.
- Observe focus order, programmatic focus movement, return after dialogs, persistence across updates, and a visible focus indicator in each relevant state. Keyboard and focus observations must name the actual journey and component.
- Check accessible name, role, value/state, relationships, headings, labels, errors, live updates, and applicable assistive-technology output. A DOM attribute alone does not prove usable behavior.
- Use an existing scanner for detectable rules when probes support it, but keep its findings distinct. A scanner does not prove accessibility and cannot replace observable keyboard, focus, semantic, visual, or assistive-technology review.
- Ask
qa-toolingto classify each tool and prerequisite asavailable,missing, orunverifiedfrom supplied probes. Never install or fabricate a scanner, browser, device, or assistive-technology observation. - Return proposed coverage and limitations. Case/criterion results remain exactly
PASS,FAIL,BLOCKED,NOT_RUN, orNOT_APPLICABLE; only the calling workflow may derive the globalPASS,FAIL, orBLOCKEDverdict from valid evidence.
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 · 103 lines · 29 tokens per session scan A 6a8bf60103c4
qa-specialist-accessibility is a skill published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (3 stars, last pushed 10d ago), licensed Apache-2.0. It adds 29 tokens to every session and 1,141 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 2026-09-16.
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.
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.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.