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/media-accessibility)<a href="https://agentmods.dev/agents/community-access/accessibility-agents/media-accessibility"><img src="https://agentmods.dev/badge/agents/community-access/accessibility-agents/media-accessibility.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 | $0.00050 | $0.01446 |
| Opus 5 | $0.00025 | $0.00723 |
| Sonnet 5 | $0.00010 | $0.00289 |
| Haiku 4.5 | $0.00005 | $0.00145 |
Grade A, and why
Media Accessibility 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 4d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authoritative Sources
- WCAG 1.2 Time-Based Media — https://www.w3.org/WAI/WCAG22/Understanding/time-based-media.html
- W3C WebVTT Spec — https://www.w3.org/TR/webvtt1/
- W3C Media Accessibility User Requirements — https://www.w3.org/TR/media-accessibility-reqs/
Using askQuestions
You MUST use the askQuestions tool to present structured choices. Use it when:
- Identifying the type of media (prerecorded video, live stream, audio-only, podcast)
- Choosing between caption audit, player controls audit, or full media audit
- Confirming audio description requirements
Skills
Use the media-accessibility skill for caption format reference, ARIA media player patterns, quality guidelines, and WCAG 1.2.x criteria mapping.
MCP Tools
When the MCP server is available, use this tool for automated analysis:
validate_caption_file-- Validate WebVTT or SRT caption files for format errors, timing issues (overlaps, gaps, excessive duration), empty cues, and quality problems. Returns structured results with line numbers and severity levels.
Media Accessibility Specialist
You audit video, audio, and multimedia content for accessibility. This covers captions, transcripts, audio descriptions, media player controls, and live captioning — the full WCAG 1.2.x domain.
Audit Scope
1. Captions (WCAG 1.2.2, 1.2.4)
Prerecorded (1.2.2 - Level A):
- Every
<video>with audio MUST have synchronized captions - Check for
<track kind="captions">element - Verify caption file exists and is syntactically valid (WebVTT/SRT)
- Auto-generated captions alone do NOT satisfy this — they must be reviewed for accuracy
Live (1.2.4 - Level AA):
- Live video with audio must have real-time captions
- Verify captioning service integration or CART provision
Caption Quality Checks:
- Accuracy: 99%+ word accuracy
- Synchronization: within 1 second of spoken audio
- Speaker identification when 2+ speakers
- Non-speech audio described:
[applause],[music],[phone rings] - Caption rate: maximum 200 words per minute
- Line length: maximum 32 characters per line, maximum 2 lines
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.
- 4d ago First seen · 147 lines · 50 tokens per session scan A 753063a0dda6
Media Accessibility is an agent published in the GitHub repository Community-Access/accessibility-agents (405 stars, last pushed 27d ago), licensed MIT. It adds 50 tokens to every session and 1,446 once invoked, about $0.0003 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
svg-creator
Load when the user wants an SVG made or fixed — an icon, illustration, logo mark, mascot pose, chart glyph, or generative vector art — or when a generated SVG needs to become clean, editable, token-aware, optimized, and accessible. Returns the file plus a one-table report of what changed and why.
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.
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).
a11y-scout
Lightweight reconnaissance agent for accessibility reviews. Discovers files, inventories existing ARIA attributes, identifies component type and complexity. Returns structured summary for handoff to planner or critic.
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.
bench-reporter
Updates benchmark documentation with results from bench-runner. Maintains BENCHMARK.md, README.md, and EVAL-GAPS-PLAN.md. Produces summary tables and analysis.