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 lingxling/awesome-skills-cn --skill accesslint-auditgit clone --depth 1 https://github.com/lingxling/awesome-skills-cnWrote 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/lingxling/awesome-skills-cn/accesslint-audit)<a href="https://agentmods.dev/skills/lingxling/awesome-skills-cn/accesslint-audit"><img src="https://agentmods.dev/badge/skills/lingxling/awesome-skills-cn/accesslint-audit/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/lingxling/awesome-skills-cn/accesslint-audit"><img src="https://agentmods.dev/badge/skills/lingxling/awesome-skills-cn/accesslint-audit.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 | $0.00075 | $0.01710 |
| Opus 5 | $0.00037 | $0.00855 |
| Sonnet 5 | $0.00015 | $0.00342 |
| Haiku 4.5 | $0.00007 | $0.00171 |
Grade A, and why
accesslint-audit 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 12d 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.
This is a copy
100% identical to accesslint-audit — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You audit accessibility and optionally fix what's broken.
When to Use
- Use this skill when the task matches this description: Find and fix WCAG 2.2 accessibility issues. Two modes — report (sweep a codebase or page, produce a prioritized written report, no edits) and fix (audit→edit→verify loop on a target). Prefers direct-CDP live-DOM auditing; falls back to a browser-MCP composition or HTML-string audits.
Pick a mode from the user's intent
- Report mode — "audit my codebase", "review src/components/", "what's wrong with this page?", "give me an a11y report". You audit + write a report. You do not edit files.
- Fix mode — "fix the a11y issues in X", "audit and fix", "make this accessible", "verify the contrast fix landed", or hands you a violation report and asks to apply it. You audit → edit → verify.
If unsure, ask. Don't default-to-fix when the user only asked for an audit.
For very large sweeps where main-thread context cost matters, you can be invoked via Task (general-purpose agent) for context isolation. The recipe is the same either way.
Picking a flow
Three flows, in order of preference.
audit_live— try first for any URL. Connects to a running Chrome debug session, or auto-launches Chrome minimized — no user setup needed. Single call; IIFE bytes don't enter your context.audit-live-pageprompt — use when the user needs their existing browser session audited (authenticated app, specific state) and a browser MCP (chrome-devtools-mcp, playwright-mcp, puppeteer-mcp) is connected. Invoke viaSkillwithmode: "fix"ormode: "plan".audit_html— for raw HTML strings, files (Readfirst, thenaudit_html), or JSX you've rendered to a string. Pair withaudit_diff({ html })for fix-mode verification.
For non-URL targets, skip straight to flow 3. For URLs, try flow 1; on auto-launch failure, try flow 2 if a browser MCP is connected; otherwise fall back to flow 3 with a note that live-DOM coverage is limited.
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.
- 12d ago First seen · 116 lines · 75 tokens per session scan A bb18c5156d75
accesslint-audit is a skill published in the GitHub repository lingxling/awesome-skills-cn (281 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 1,710 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to accesslint-audit, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
accessibility-audit
A review guide for checking whether webpages, components, prototypes, or designs are accessible to people with different needs. It uses WCAG 2.2 AA, a widely used set of web-accessibility requirements, as its default standard.
frontend-aesthetic-direction
A skill for choosing a complete visual direction for a new frontend project with no existing brand or design system. It defines rules for typography, colors, spacing, shapes, components, imagery, icons, and motion.
interaction-states-pass
A review skill for checking whether interactive controls give appropriate feedback in their resting, focused, active, loading, successful, and error states. It applies only the states that make sense for each control.
polish-pass
A final review checklist for an interface before it is shown to customers, teammates, or other stakeholders. It checks accessibility, visual hierarchy, overly generic AI-style design, and interaction states such as hover, focus, loading, success, and failure.
make-a-prototype
A skill for building clickable prototypes with working navigation, inputs, validation, loading, and success or failure feedback. A prototype is a test version of a product flow, using local simulated data unless a real connection is separately approved.
make-tweakable
A hidden floating settings panel for a single-file HTML design or prototype. It lets someone adjust selected colors, fonts, spacing, text, layout options, or feature switches while comparing variations in the same file.