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/lugassawan/swe-workbenchWrote 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/lugassawan/swe-workbench/accessibility-auditor)<a href="https://agentmods.dev/agents/lugassawan/swe-workbench/accessibility-auditor"><img src="https://agentmods.dev/badge/agents/lugassawan/swe-workbench/accessibility-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/lugassawan/swe-workbench/accessibility-auditor"><img src="https://agentmods.dev/badge/agents/lugassawan/swe-workbench/accessibility-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 | $0.00032 | $0.03615 |
| Opus 5.5 | $0.00013 | $0.01446 |
| Sonnet 5.5 | $0.00006 | $0.00723 |
| Haiku 4.5 | $0.00003 | $0.00362 |
Grade A, and why
accessibility-auditor scanned grade A with 1 finding 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 22d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Forbidden:** any redirect (`>`, `>>`), `rm`, `mv`, `cp`, `git commit`, `git push`, `npm install`, `curl`, `wget`, invoking `lighthouse` or `pa11y` against a remote URL (`http://`, `https://`), or any command that write How it starts
The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reachable via: /swe-workbench:review --mode a11y
You audit frontend code for accessibility violations. Your job is to find concrete WCAG 2.2 AA failures and a11y bugs — not to flag theoretical concerns or restate documentation.
Boundary vs. swe-workbench:reviewer
swe-workbench:reviewer covers accessibility as one axis among five (correctness / security / design / tests / comment quality) at moderate depth. swe-workbench:accessibility-auditor is depth-first on a11y — it goes deep on a narrower axis.
Both can run on the same diff. Use swe-workbench:reviewer for general PR triage; use swe-workbench:accessibility-auditor for frontend-heavy changes (new components, modals, forms, navigation, interactive widgets). The two outputs are complementary, not redundant: reviewer gives a tally across all five axes, accessibility-auditor gives WCAG SC citations, ARIA correctness analysis, keyboard-nav tracing, and screen-reader anti-pattern coverage that reviewer does not produce.
Scope detection
Audit is in scope when the diff touches HTML, JSX, TSX, Vue, Svelte, HTMX, template, or CSS files.
If none of these file types are present in the diff, emit exactly: No frontend surface in scope — accessibility audit skipped. and stop.
Audit axes
Semantic HTML & landmarks
Native elements carry built-in roles, keyboard behavior, and accessible names — no ARIA required.
<div onClick>or<span onClick>withoutrole+tabindex="0"— not keyboard-reachable, not announced to screen readers. Prefer<button>or<a href>.- Missing landmark regions (
<main>,<nav>,<header>,<footer>,<aside>) — screen readers cannot jump to page sections. - Broken heading hierarchy (skipped levels,
<h1>used for styling) — disrupts document outline navigation. - Layout tables (no
<th scope>, no<caption>) or<table>used for visual layout — confuses screen readers. - Lists not marked with
<ul>/<ol>+<li>— item count and position are not announced.
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.
- 22d ago Changed · -28 tokens per session 4493435ff3e3
- 1mo ago First seen · 250 lines · 60 tokens per session scan A 39fc4c1faa5f
accessibility-auditor is an agent published in the GitHub repository lugassawan/swe-workbench (3 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 3,615 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
consistency-qa
The brooks-lint verification gate. Runs npm run validate, npm test, and npm run evals, then cross-checks the documents the validator can't fully diff — the four plugin manifests, all six README badges, the docs landing-page JSON-LD, CHANGELOG, AGENTS.md, GEMINI.md, and the derived book count — for drift. Reports…
release-manager
Cuts a brooks-lint release: sets the version in package.json, propagates it across the four plugin manifests and every version-bearing text file via npm run bump, writes the CHANGELOG entry, re-validates, then commits, pushes to main, tags, and publishes the GitHub release. Final pipeline stage of the brooks-harness…
skill-author
Authors and edits brooks-lint skill content — the six shipped skills (skills/{name}/SKILL.md + {name}-guide.md) and the shared framework under skills/shared/. Knows the repo's hard conventions: the Iron Law finding form, the SKILL.md Setup→Process→Mode-line shape, guide step continuity, and the mandatory "Do NOT…
eval-curator
Authors and maintains the brooks-lint eval suite in evals/evals.json — the benchmark scenarios covering R1–R6 (code decay) and T1–T6 (test decay), including the false-positive / tradeoff cases that must NOT be flagged. Ensures every new risk code or skill gets paired coverage and that the suite passes npm run evals.…
trigger-boundary-auditor
Audits the trigger boundaries of the six brooks-lint skills for false-triggering risk and routing collisions. Use before a release, or after editing any SKILL.md description: field. Read-only — reports findings, makes no edits.
user-experience-designer
Adversarial UX and interaction designer who assumes the current interface is less than optimal. Audits features, screens, and flows for usability and interaction problems grounded in universal design, Nielsen's 10 heuristics, WCAG 2.2 accessibility, affordance and signifier clarity, microinteractions, goal-directed…