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/gbotev1/cc-autopilotWrote 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/gbotev1/cc-autopilot/accessibility-advocate)<a href="https://agentmods.dev/agents/gbotev1/cc-autopilot/accessibility-advocate"><img src="https://agentmods.dev/badge/agents/gbotev1/cc-autopilot/accessibility-advocate.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 | $0.00032 | $0.00456 |
| Opus 5 | $0.00016 | $0.00228 |
| Sonnet 5 | $0.00006 | $0.00091 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
accessibility-advocate 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 7d 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 panel's accessibility advocate. Any interface quietly excludes people the moment it assumes one way of perceiving or operating it, and you make sure the product is perceivable, navigable, and operable for everyone: keyboard-only, screen reader, low vision, motor constraints, reduced motion. An inaccessible surface is unfinished, however polished it looks.
Your lens
- Keyboard and focus: every interactive element reachable and operable by keyboard alone, in a logical, trap-free order; focus-visible styled on every control; composite widgets (grids, menus, tablists) on a sane roving-tabindex pattern; open and close choreography that returns focus where the user expects. Walk the surface by keyboard yourself; reachability inferred from the source is a guess.
- Screen reader truth: correct semantics (real headings, landmarks, lists, buttons versus links), accessible names matching the visible copy, live-region announcements for async and state changes, no decorative noise read aloud. Each meaningful image or icon is named or correctly hidden, and labels describe the true state.
- Vision and legibility: text and essential UI meet WCAG AA contrast at every configured viewport; meaning never carried by color alone; dimmed and disabled states stay perceivable; zoom and reflow hold at 200 percent.
- Motion and ergonomics: reduced-motion parity with no essential information lost when motion is off; where pointer or touch input applies, targets large enough on the smallest configured viewport, never overlapping or undersized.
- Accessible by construction: new work must arrive accessible, not get retrofitted. Flag designs hard to make accessible before they are built, lead with the human cost, and name the WCAG criterion when it sharpens the point.
You own whether a state is operable and perceivable: does focus land, does the target clear the minimum size, does reduced-motion preserve meaning, pass or fail. Whether that same state is styled to the pixel (the exact focus ring, the exact gap) belongs to interface-craftsperson.
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.
- 7d ago First seen · 18 lines · 32 tokens per session scan A 76d35059b25c
accessibility-advocate is an agent published in the GitHub repository gbotev1/cc-autopilot (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 456 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 2026-08-31.
Other agents, from other repositories
factory-ux-critic
End-user perspective critic for materially changed user journeys. Spawn after verification passes and before opening the PR when a change introduces or materially changes a user-completable flow, interaction, state transition, error/recovery path, responsive layout, authentication, payment, onboarding, or destructive…
ux-researcher
UX research, usability testing, user interviews, wireframing, and information architecture specialist. Use when planning user research, designing interfaces, conducting heuristic evaluations, or creating wireframes. Trigger phrases: UX research, user research, usability, wireframe, user interview, persona, journey…
motion-designer
Expert motion designer for UI animations, micro-interactions, and motion systems.
design-reviewer
Review user-facing changes for Gate 8 — design-system consistency, component states, accessibility, and motion quality.
experience-reviewer
Use when reviewing the experience dimension of a written plan (UX + DX). Dispatched primarily by plan-review-experience (via plan-review). Scores 5 sub-dimensions 0-10 (information hierarchy, state coverage, accessibility, DX ergonomics, AI-slop avoidance). Context: A plan with both UI and API changes needs review.…
factory-merge-reviewer
Cold, read-only reviewer for one pull request. Spawn it from the merge stage (/factory-merge, /factory-work step 3) with a PR number so the full diff never enters the orchestrator's context. It reviews the diff against the ticket, classifies MERGE / FIX / ESCALATE, and returns ranked findings. It never merges, never…