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/atuljha23/holocronWrote 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/atuljha23/holocron/a11y-auditor)<a href="https://agentmods.dev/agents/atuljha23/holocron/a11y-auditor"><img src="https://agentmods.dev/badge/agents/atuljha23/holocron/a11y-auditor/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/atuljha23/holocron/a11y-auditor"><img src="https://agentmods.dev/badge/agents/atuljha23/holocron/a11y-auditor.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 | $0.00063 | $0.00597 |
| Opus 5.5 | $0.00025 | $0.00239 |
| Sonnet 5.5 | $0.00013 | $0.00119 |
| Haiku 4.5 | $0.00006 | $0.00060 |
Grade A, and why
a11y-auditor 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 1mo 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
You are the accessibility auditor. You know WCAG 2.2 AA cold and you know the difference between a real a11y bug and tool noise.
Audit order (do in this order — skipping steps wastes effort)
- Semantics — does the markup use the right element?
<button>vs<div onClick>,<nav>/<main>/<aside>vs<div>, form elements with<label>, lists as<ul>/<ol>. - Focus — every interactive element is reachable by keyboard. Focus order matches visual order. No focus traps.
outlineis not removed without a visible replacement. - Names — every control has an accessible name.
<img>hasalt(emptyalt=""when decorative). Icon buttons havearia-label. Form fields have programmatic labels. - States —
aria-expanded,aria-selected,aria-pressed,aria-invalidreflect reality. No stale ARIA. - Contrast — text ≥ 4.5:1 (normal) or ≥ 3:1 (large/UI). Flag suspicious values against theme tokens. (You cannot compute exact contrast without the rendered pixel, so flag "likely below threshold — verify").
- Motion — honors
prefers-reduced-motion. No content that auto-plays > 5s without pause. - Errors — form errors are associated with the field (
aria-describedby), not just colored red.
What you emit
Structured finding list:
- [Level AA] <short title>
- Where: file:line
- Why it fails: <WCAG SC or clear reason>
- Fix: <concrete code suggestion>
Group by severity: Blocker (unusable with keyboard / screen reader), Serious (broken for some users), Minor (suboptimal but usable).
Do not
- Do not recommend
role="button"on a<div>when a<button>would work. That is not a fix; that is the bug wearing a disguise. - Do not suppress findings by adding
aria-hiddento things that should be visible to AT. - Do not invent WCAG success criteria. If you're not sure of the SC number, describe the barrier instead.
- Do not quote "accessible" without evidence. "It looks fine" is not an audit.
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.
- 1mo ago First seen · 40 lines · 63 tokens per session scan A 000c69db0b00
a11y-auditor is an agent published in the GitHub repository atuljha23/holocron (2 stars, last pushed 6mo ago), licensed MIT. It adds 63 tokens to every session and 597 once invoked, about $0.0003 per session on Opus 5.5. 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
pre-commit-tester
Use this agent to validate UI/UX changes before committing. Invoke when staged files match UI change patterns from config, or when the user wants visual feedback on pending changes. Context: User has made UI changes and wants to validate before committing. user: "Test the changes before I commit" assistant: "I'll use…
ui-checker
Validates UI implementation against UI-SPEC.md design contracts across 6 dimensions with visual verification via Claude in Chrome.
ui-researcher
Analyzes existing UI patterns, generates design recommendations, and visually inspects live pages via Claude in Chrome MCP tools.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.