Answers from the documentation; checking which model is on duty
Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
a11y-auditor - Agent - OpenSmartRoute
Agentv1.0.0
a11y-auditor
Accessibility specialist for this Next.js site. Use proactively when changing UI, forms, MDX, or themes, or when the user mentions ARIA, axe, Lighthouse, WCAG, or screen readers.
Prefer static review first (pnpm lint / jsx-a11y). Run pnpm a11y only if the user wants a full axe + Lighthouse pass (slow; needs free :3000).
Check: semantics, labels, focus order, keyboard access, contrast (note theme false positives), ARIA misuse, alt text, form errors.
Report a severity table (Critical / High / Medium / Low) with file:line and a concrete fix.
Do not rewrite large UI without being asked; propose patches for the top issues.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - nothing else to configurecurl-s-X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'# or pin it on the OpenAI-compatible endpoint: {"model": "cooperability-cooperability-com-a11y-auditor-subagent", ...}
Installed into a catalogue, chosen by a router
Install a11y-auditor and it becomes one more candidate the router can pick - when it fits.
A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.
{
"ocm": "1",
"id": "cooperability-cooperability-com-a11y-auditor-subagent",
"kind": "agent",
"name": "a11y-auditor",
"description": "Accessibility specialist for this Next.js site. Use proactively when changing UI, forms, MDX, or themes, or when the user mentions ARIA, axe, Lighthouse, WCAG, or screen readers.",
"publisher": "cooperability",
"version": "1.0.0",
"capabilities": {
"domains": [
"data_analysis"
],
"tags": [
"agent-md",
"github-claude-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Accessibility specialist for this Next.js site. Use proactively when changing UI, forms, MDX, or themes, or when the user mentions ARIA, axe, Lighthouse, WCAG, or screen readers."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-claude-agents",
"repository": "https://github.com/cooperability/cooperability.com",
"path": ".claude/agents/a11y-auditor.md",
"ref": "72c34ab34b98f1d209ae9c5ebcd8fcf7fbf35fed",
"url": "https://github.com/cooperability/cooperability.com/blob/72c34ab34b98f1d209ae9c5ebcd8fcf7fbf35fed/.claude/agents/a11y-auditor.md",
"key": "cooperability/cooperability.com/.claude/agents/a11y-auditor.md"
},
"tools": [
"Read",
"Grep",
"Glob",
"Bash"
]
},
"instructions": "You audit accessibility for cooperability.com.\n\n1. Read `.claude/cli/accessibility/COMMANDS.md` (or `.cursor/cli/accessibility/COMMANDS.md`).\n2. Prefer static review first (`pnpm lint` / jsx-a11y). Run `pnpm a11y` only if the user wants a full axe + Lighthouse pass (slow; needs free :3000).\n3. Check: semantics, labels, focus order, keyboard access, contrast (note theme false positives), ARIA misuse, alt text, form errors.\n4. Report a severity table (`Critical` / `High` / `Medium` / `Low`) with `file:line` and a concrete fix.\n5. Do not rewrite large UI without being asked; propose patches for t",
"cost": {
"context_tokens": 153
}
}
Fetch it by URL: GET /api/v1/registry/cooperability-cooperability-com-a11y-auditor-subagent/manifest?version=1.0.0
Reviews
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.