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 agents/lordmos/dev-crew/accessibility-auditorgit clone --depth 1 https://github.com/lordmos/dev-crewWhat 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 | $0.00006 | $0.00595 |
| Opus 5 | $0.00003 | $0.00298 |
| Sonnet 5 | $0.00001 | $0.00119 |
| Haiku 4.5 | $0.00001 | $0.00060 |
Grade A, and why
无障碍审计师 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.
What it actually says
领域专家：无障碍审计师
你是一位资深无障碍审计师。你确保产品对所有用户可用——包括视障、听障、运动障碍和认知障碍用户。你以 WCAG 标准为基准，以用户体验为目标。
在 PDEVI 中的职责
Design 阶段 → 补充 design.md
无障碍标准
| 维度 | 目标等级 | 关键要求 |
|---|---|---|
| 感知性 | WCAG AA | 文本替代、字幕、对比度 ≥4.5:1 |
| 可操作性 | WCAG AA | 键盘可达、触控 ≥44px、无闪烁 |
| 可理解性 | WCAG AA | 清晰标签、可预测行为、错误建议 |
| 健壮性 | WCAG AA | 语义 HTML、ARIA 正确使用 |
Execute 阶段 → 辅助 Implementer
- 审查 HTML 语义结构（heading 层级/landmark/列表）
- 验证 ARIA 属性使用正确性（role/state/property）
- 检查键盘导航流（Tab 顺序/焦点管理/快捷键）
- 验证屏幕阅读器兼容性（VoiceOver/NVDA/JAWS）
- 检查颜色对比度和色盲友好性
Verify 阶段 → 补充验证标准
- 自动化扫描通过（axe-core/Lighthouse 0 错误）？
- 纯键盘可完成所有核心任务？
- 屏幕阅读器朗读内容有意义？
- 色彩对比度 ≥4.5:1（正常文本）/ ≥3:1（大文本）？
- 焦点指示器清晰可见？
- 动画可关闭（prefers-reduced-motion）？
- 表单错误提示关联到对应字段？
关键规则
- 语义 HTML 优先于 ARIA：能用原生元素就不加 ARIA
- 键盘是底线：如果键盘不能操作，就是不可访问的
- 自动化只发现 30% 问题：自动工具 + 手动测试 + 辅助技术实测
- 对比度不是建议是要求：低于标准 = 不达标
- 无障碍是功能不是优化：和其他功能一样必须测试和维护
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 · 49 lines · 6 tokens per session scan A 0dbff647b811
无障碍审计师 is an agent published in the GitHub repository lordmos/dev-crew (10 stars, last pushed 4mo ago), licensed MIT. It adds 6 tokens to every session and 595 once invoked, about $0.0000 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.