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.
git clone --depth 1 https://github.com/Community-Access/accessibility-agentsWrote 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/agents/community-access/accessibility-agents/link-checker)<a href="https://agentmods.dev/agents/community-access/accessibility-agents/link-checker"><img src="https://agentmods.dev/badge/agents/community-access/accessibility-agents/link-checker/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/agents/community-access/accessibility-agents/link-checker"><img src="https://agentmods.dev/badge/agents/community-access/accessibility-agents/link-checker.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 | $0.00105 | $0.04404 |
| Opus 5 | $0.00053 | $0.02202 |
| Sonnet 5 | $0.00021 | $0.00881 |
| Haiku 4.5 | $0.00011 | $0.00440 |
Grade A, and why
Link Checker 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 — 470 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authoritative Sources
- WCAG 2.4.4 Link Purpose (In Context) — https://www.w3.org/WAI/WCAG22/Understanding/link-purpose-in-context.html
- WCAG 2.4.9 Link Purpose (Link Only) — https://www.w3.org/WAI/WCAG22/Understanding/link-purpose-link-only.html
- WCAG 3.2.5 Change on Request — https://www.w3.org/WAI/WCAG22/Understanding/change-on-request.html
- HTML Living Standard - element — https://html.spec.whatwg.org/multipage/text-level-semantics.html#the-a-element
You are the ambiguous link text checker. Links are one of the most common accessibility failures on the web. Screen reader users frequently navigate by pulling up a list of all links on a page - if every link says "Read more" or "Click here", the list is useless. You ensure every link communicates its purpose clearly, whether read in context or in isolation.
Using askQuestions
You MUST use the askQuestions tool to present structured choices to the user whenever you need to clarify scope, confirm actions, or offer alternatives. Do NOT type out choices as plain chat text -- always invoke askQuestions so users get a clickable, structured UI.
Use askQuestions when:
- Your initial assessment reveals multiple possible approaches
- You need to confirm which files, components, or areas to focus on
- Presenting fix options that require user judgment
- Offering follow-up actions after completing your analysis
- Any situation where the user must choose between 2+ options
Always mark the recommended option. Batch related questions into a single call. Never ask for information you can infer from the workspace or conversation history.
Your Scope
You own everything related to link text accessibility:
- Link text clarity and descriptiveness
- Ambiguous or generic link text detection
- Repeated identical link text pointing to different destinations
- Links that rely on surrounding context to make sense
- Links vs buttons (correct element usage)
- Link purpose communicated programmatically
- Adjacent duplicate links (image + text link to same destination)
- Links that open in new windows/tabs
- Links to non-HTML resources (PDFs, documents, files)
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 · 470 lines · 105 tokens per session scan A 9fafabbd517d
Link Checker is an agent published in the GitHub repository Community-Access/accessibility-agents (405 stars, last pushed 28d ago), licensed MIT. It adds 105 tokens to every session and 4,404 once invoked, about $0.0005 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 2026-09-03.
Other agents, from other repositories
axe
Audit and fix WCAG AA accessibility issues including keyboard navigation, ARIA patterns, focus management, and screen reader compatibility. Use when reviewing or remediating a UI for accessibility compliance. Trigger with "run an accessibility audit", "fix WCAG failures".
a11y-planner
Accessibility Design Planner — 9-phase protocol for designing accessible implementations before coding. Maps interactive patterns to WAI-ARIA APG patterns, plans focus management, state communication, visual accessibility, content strategy, and testing approach.
a11y-critic
Standalone accessibility design reviewer evaluating ARIA patterns, focus management, state communication, and multi-perspective access (screen reader, keyboard, low vision, cognitive). 8-phase investigation protocol with strict evidence requirements and calibrated severity ratings.
a11y-role-auditor
ARRM-based accessibility role auditor — reviews artifacts from responsibility-based team role perspectives (visual design, UX design, front-end dev, content authoring, business analysis, testing) to produce role-attributed findings.
ui-reviewer
Load when the user asks for a UI code review, animation critique, hover-state audit, component review, or "is this well-built?" on any CSS, motion, or component code. Returns a Before | After | Why markdown table per the required review-format and scans against the thirteen-row review-checklist before signing off.
Demonstrate
Agent for demonstrating VS Code features.