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/desquared/agents-rules-skills/accessibility-annotationsnpx skills add Desquared/agents-rules-skills --skill accessibility-annotationsgit clone --depth 1 https://github.com/Desquared/agents-rules-skillsWrote 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/desquared/agents-rules-skills/accessibility-annotations)<a href="https://agentmods.dev/skills/desquared/agents-rules-skills/accessibility-annotations"><img src="https://agentmods.dev/badge/skills/desquared/agents-rules-skills/accessibility-annotations.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 | $0.00086 | $0.02199 |
| Opus 5 | $0.00043 | $0.01099 |
| Sonnet 5 | $0.00017 | $0.00440 |
| Haiku 4.5 | $0.00009 | $0.00220 |
Grade A, and why
accessibility-annotations 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 4d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility Annotations
Annotate Figma screens with accessibility (AX) annotations so engineers know the reading order, focus order, roles, labels, and alt text for every element.
Work is Figma-first: use the annotation library configured for the project. Never invent components or draw homemade highlight shapes.
Project configuration
This skill is design-system agnostic. Resolve these values before the first write, from the project handoff, the repo, or by asking once:
| Setting | How to resolve | Fallback |
|---|---|---|
| Annotation library | Handoff Annotation library field, or the AX library already published to the target Figma file |
Ask the user for the library name/URL |
| Component names | Inspect the library's component sets in the file | Order, Button, Image, Role Value Label, More info |
| Brand font | The font used by the library's text layers | Detect at runtime; see figma-tooling.md for the font-swap fallback |
| AX region | Handoff AX region, or the page/section holding the annotated screens |
Ask which section to annotate |
| Signed-off templates | Handoff template table | The user's most recently corrected screen |
If the library names components differently (for example Focus Order instead of Order), map them once and record the mapping in the handoff. Everything else in this skill stays the same.
Before you start
- Load your environment's Figma write skill (for example
figma-use) before every Figma write call. - Read the project handoff if one exists — it is the canonical status and lists signed-off templates. See handoff-template.md.
- Confirm the section/screen to annotate. Prefer one screen at a time; wait for user QA before applying to sibling screens.
- Open the matching user-corrected pattern (see patterns.md) and clone from it. Do not invent denser layouts.
Workflow
Task progress:
- [ ] Identify section + screens
- [ ] Pick pattern (A–I) from the signed-off template
- [ ] Inspect target nodes (texts, controls, existing AX)
- [ ] Clone library / canvas instances (never homemade shapes)
- [ ] Place orders + callouts (gutters, no stacking)
- [ ] Screenshot-verify
- [ ] Update handoff status
- [ ] Stop for user QA
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.
- 4d ago First seen · 168 lines · 86 tokens per session scan A 3a266316b86c
accessibility-annotations is a skill published in the GitHub repository Desquared/agents-rules-skills (4 stars, last pushed 21d ago), licensed MIT. It adds 86 tokens to every session and 2,199 once invoked, about $0.0004 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
hallmark
Anti-AI-slop design skill for greenfield pages, audits, redesigns, and design extraction from URLs or screenshots. Use when the user asks to build a new app or landing page, wants to redesign something, invokes Hallmark by name, or uses audit/redesign/study.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
desktop-principles
Desktop-specific UX principles - hover states, pointer precision, keyboard shortcuts, multi-window, focus management. Covers macOS, Windows, Linux, web desktop.
taiyi-ui-design
TaiyiForge 第 4 阶段 — UI/UX 契约，产出 UI-DESIGN.md。四端通用。.
accessibility-analysis
服務可達性分析工具箱（accessibility / service coverage）。當用戶說「30km 路網可達」「最近 X 站」「服務範圍」「沙漠」「孤島」「等時圈」「isochrone」「可達性分析」「路網覆蓋」或要新增任何「離 POI 多遠」類型的分析時觸發。整合 mini-taiwan-pulse + taipei-gis-analytics 兩端 SOP，覆蓋三種視覺模式（路網染色 / Polygon 沿路網 / Hex 格點）、三套既有 reference pipeline 對照、模式選擇決策樹、常見坑（Overpass mirror 不穩 / pyrosm 爆 RAM / multi-bucket /…
ui-design
UI 样式修改协作流程（已有界面的视觉层微调）。触发硬条件：页面已经在代码里跑着，改的只是它的视觉表现——布局、间距、颜色、字号、圆角、组件搭配。通过"读代码 + ASCII 画出现状让用户确认 → 给 2-3 个 ASCII 方案 → 用户选定 → 最小改动 → 微调"的流程，减少沟通偏差、避免浪费 token。产出：只动样式的代码 diff。硬边界：不动业务逻辑、不动数据流、不改交互行为、不顺手重构。不适用于：界面还不存在、要从零探索长什么样（用 design-exploration）、改的是功能或交互逻辑而不只是视觉（用 req-change-workflow）、照着设计图/截图复刻整页（用…