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/andr-ca/agentharness/accessibilitynpx skills add andr-ca/agentharness --skill accessibilitygit clone --depth 1 https://github.com/andr-ca/agentharnessWhat 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 | $0.00044 | $0.01238 |
| Opus 5 | $0.00022 | $0.00619 |
| Sonnet 5 | $0.00009 | $0.00248 |
| Haiku 4.5 | $0.00004 | $0.00124 |
Grade A, and why
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 2d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility
This skill is self-contained for day-to-day use. Deeper reference (needs
the full harness checkout): patterns/accessibility/README.md (full
examples including ARIA live regions and APG patterns). External
canonical sources: WCAG 2.2 and the
WAI-ARIA Authoring Practices.
Target: WCAG 2.2 Level AA.
The first rule: don't use ARIA if a native element exists
A native <button>, <a href>, <input>, <label>, <nav>, or
<table> brings keyboard behavior, focus management, and the correct
role/state for free. role="button" + tabindex + keyboard handler is
a liability you now own forever.
<!-- Good: browser handles focus, Enter, Space, and role automatically -->
<button type="button" onclick="save()">Save</button>
<!-- Avoid: you must re-implement everything the native button provides -->
<div role="button" tabindex="0" onclick="save()" onkeydown="handleKey(event)">Save</div>
Perceivable
- Text alternatives. Meaningful images:
altdescribing purpose. Decorative images:alt="". Icon-only controls:aria-labelor visually-hidden text. - Contrast. Body text ≥ 4.5:1 against background. Large text (≥ 24px, or ≥ 18.66px bold) and UI components/graphics ≥ 3:1. Verify computed colors — don't eyeball.
- Color alone is not enough. A red border and an error text/icon — not red alone.
Operable
- Keyboard. All interactive elements must be reachable by Tab, in
logical order, with no keyboard trap.
tabindex="0"for natural order;tabindex="-1"for programmatic-only focus; never positive values. - Visible focus. Never
outline: nonewithout a clearly visible replacement. Keyboard users navigate by it. - Skip link. First focusable element on pages with repeated
navigation:
<a href="#main">Skip to main content</a>. - Target size. Interactive targets ≥ 24×24 px (WCAG 2.2 §2.5.8), with adequate spacing if smaller.
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.
- 2d ago First seen · 119 lines · 44 tokens per session scan A 7ca0d8abc785
accessibility is a skill published in the GitHub repository andr-ca/agentharness (1 stars, last pushed 2d ago), licensed MIT. It adds 44 tokens to every session and 1,238 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 2026-08-31.
Other skills, from other repositories
critique
Run a 5-dimension expert design review on any HTML artifact in the project — Philosophy / Visual hierarchy / Detail / Functionality / Innovation, each scored 0–10. Outputs a single self-contained HTML report with a radar chart, evidence-backed scores, and three lists: Keep / Fix / Quick-wins. Use when the brief asks…
html-ppt-zhangzara-block-frame
Rescuing a messy startup deck into a board-grade system — the diagnosis, the page grammar, and the rebuilt proof pages. Built as a decision-grade design craft deck for founders, exec presenter.
html-ppt-zhangzara-blue-professional
OpenDesign's QBR for the executive committee: what moved, what stalled, and the resource reallocation ask. Built as a decision-grade corporate strategy deck for executive committee.
html-ppt-zhangzara-creative-mode
A brand visual-identity system reveal for an outdoor label — logo, color, type, and the rules that keep it consistent. Built as a decision-grade design craft deck for brand team, client.
html-ppt-zhangzara-editorial-tri-tone
A type-and-color system for a culture magazine relaunch — the grid, the tri-tone palette, and the layout kit. Built as a decision-grade design craft deck for editorial & design team.
html-ppt-zhangzara-neo-grid-bold
A designer's portfolio narrative for a senior interview — three case studies, the craft, and the judgment behind each. Built as a decision-grade career deck for hiring panel.