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 skills/getcrew44/crew44/accessibility-reviewnpx skills add getcrew44/crew44 --skill accessibility-reviewgit clone --depth 1 https://github.com/getcrew44/crew44Wrote 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/getcrew44/crew44/accessibility-review)<a href="https://agentmods.dev/skills/getcrew44/crew44/accessibility-review"><img src="https://agentmods.dev/badge/skills/getcrew44/crew44/accessibility-review.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 | $0.00035 | $0.00717 |
| Opus 5 | $0.00017 | $0.00358 |
| Sonnet 5 | $0.00007 | $0.00143 |
| Haiku 4.5 | $0.00003 | $0.00072 |
Grade A, and why
accessibility-review 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 5d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility Review
Catch the issues that block users before they reach engineering. Most accessibility failures are predictable from the design alone.
WCAG 2.1 AA quick reference
Perceivable
- 1.1.1 — Non-text content has alt text.
- 1.3.1 — Structure and meaning conveyed semantically, not visually.
- 1.4.3 — Contrast ≥ 4.5:1 for body text, ≥ 3:1 for large text (18px+).
- 1.4.11 — Non-text contrast ≥ 3:1 for UI components and meaningful graphics.
Operable
- 2.1.1 — All functionality available by keyboard.
- 2.4.3 — Logical focus order matches the visible reading order.
- 2.4.7 — Focus indicator is visible and not hidden by
outline: none. - 2.5.5 — Touch target ≥ 44×44 CSS pixels.
Understandable
- 3.2.1 — Predictable on focus; no unexpected context changes.
- 3.3.1 — Errors are identified clearly and tied to the failing field.
- 3.3.2 — Inputs have visible labels or instructions, not just placeholders.
Robust
- 4.1.2 — Every interactive control has a name, role, and value exposed to assistive tech.
Common issues to look for first
- Insufficient color contrast — especially gray-on-white body text and brand-color CTAs.
- Form fields with placeholder-as-label (placeholder disappears on focus).
- Click targets under 44×44.
- Focus indicators removed in CSS without a replacement.
- Modals that trap focus incorrectly (or don't trap at all).
- Color used as the only signal (red text alone for errors, green-only success).
- Icon-only buttons with no accessible name.
- Auto-playing media with no pause control.
Testing approach
- Automated contrast and structure scan first (catches the easy wins).
- Walk the screen by keyboard only. Tab, Shift+Tab, Enter, Space, Escape, arrow keys.
- Screen reader pass (VoiceOver or NVDA). Listen to how each element announces.
- Zoom to 200%. Does the layout break? Does anything become unreachable?
Output
- Summary — total issues, count by severity (critical / major / minor).
- Findings — grouped by WCAG principle (Perceivable / Operable / Understandable / Robust). Each finding: element, issue, WCAG criterion, severity, recommended fix.
- Color contrast check — table of body text, secondary text, UI elements, with foreground/background/ratio/pass.
- Keyboard walkthrough — note any element that cannot be reached, activated, or escaped via keyboard.
- Priority fixes — top three, each named with who it blocks and what it unblocks.
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.
- 5d ago First seen · 68 lines · 35 tokens per session scan A bb9ee752f20d
accessibility-review is a skill published in the GitHub repository getcrew44/crew44 (359 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 717 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 2026-08-30.
Other skills, from other repositories
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
test
Detect the project’s test stack, run the narrowest useful tests, create tests when authorized, and report coverage/gaps honestly.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
agy-delegate
Delegate a coding task to the Google Antigravity CLI (agy) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Antigravity or agy - phrasings like "have Antigravity do X", "delegate this to agy", "run it through agy", or "use…
zcode-delegate
Delegate a coding task to the Z.AI ZCode CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to ZCode — phrasings like "have ZCode do X", "delegate this to ZCode", "run it through ZCode", or "use ZCode to implement/fix/refactor" — or…