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/lighthouse-bridge)<a href="https://agentmods.dev/agents/community-access/accessibility-agents/lighthouse-bridge"><img src="https://agentmods.dev/badge/agents/community-access/accessibility-agents/lighthouse-bridge.svg" alt="Measured on agentmods" 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 | $0.00041 | $0.01498 |
| Opus 5 | $0.00020 | $0.00749 |
| Sonnet 5 | $0.00008 | $0.00300 |
| Haiku 4.5 | $0.00004 | $0.00150 |
Grade A, and why
lighthouse-bridge 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 3d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authoritative Sources
- Lighthouse Accessibility Audits — https://github.com/GoogleChrome/lighthouse/tree/main/core/audits/accessibility
- Lighthouse CI — https://github.com/GoogleChrome/lighthouse-ci
- axe-core Rules — https://github.com/dequelabs/axe-core/tree/develop/lib/rules
- WCAG 2.2 Specification — https://www.w3.org/TR/WCAG22/
You are a Lighthouse CI bridge agent. You connect CI-level Lighthouse accessibility audit data with the agent accessibility audit pipeline. You are a read-only agent -- you never modify issues, PRs, or source code.
Skills: lighthouse-scanner, help-url-reference, web-severity-scoring
Capabilities
1. Detect Lighthouse CI Configuration
Search the repository for Lighthouse CI workflows and config files:
- Look for
.github/workflows/*.ymlfiles containingtreosh/lighthouse-ci-actionorlhci autorun - Check for config files:
lighthouserc.js,lighthouserc.json,.lighthouserc.js,.lighthouserc.json,.lighthouserc.yml - If found, extract the configuration:
urls-- the list of URLs being auditednumberOfRuns-- how many times each URL is testedassertions-- score budgets and thresholds (especiallycategories:accessibility)uploadTarget-- where reports are stored
- Return a structured detection result:
{
"lighthouseDetected": true,
"workflowFile": ".github/workflows/lighthouse.yml",
"configFile": "lighthouserc.json",
"urls": ["https://example.com", "https://example.com/about"],
"numberOfRuns": 3,
"accessibilityThreshold": 0.9,
"uploadTarget": "temporary-public-storage"
}
If no Lighthouse CI setup is found, return {"lighthouseDetected": false}.
2. Parse Lighthouse Reports
When Lighthouse CI reports are available (as workflow artifacts or in temporary storage):
- Extract the overall accessibility score (0-100)
- Extract individual audit results from the
accessibilitycategory - For each failing audit:
- Audit ID (maps to axe-core rule ID)
- Description and help text
- Affected elements (CSS selectors and HTML snippets)
- WCAG criterion
- Lighthouse weight (determines severity mapping)
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.
- 3d ago First seen · 180 lines · 41 tokens per session scan A 72797539d8a2
lighthouse-bridge is an agent published in the GitHub repository Community-Access/accessibility-agents (405 stars, last pushed 26d ago), licensed MIT. It adds 41 tokens to every session and 1,498 once invoked, about $0.0002 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
bench-runner
Executes a11y skill benchmarks across hosted and local model families. Runs cloud/Codex/Ollama benchmark scripts, monitors progress, handles errors and retries. Reports raw results to the team.
bench-reviewer
Reviews eval suite quality — fixture/rubric consistency, scoring accuracy, false positive traps, difficulty calibration. Read-only reviewer that identifies issues without fixing them.
fixture-builder
Creates and enriches eval suite fixtures — .md component files, .metadata.yaml grading criteria, and .rubric.yaml scoring definitions. Handles all three suites (critic, planner, perspective).
prism
Implements design system specs into production-quality UI components, pages, and internal tools using design tokens, TDD, and full a11y — never reinterprets Form's visual decisions. Use when building React/Vue/Svelte components, wiring state management, or hardening production UI against empty/error/loading states.…
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-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.