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.
npx skills add vmobifystudio/app-dev-team --skill accessibility-gategit clone --depth 1 https://github.com/vmobifystudio/app-dev-teamWrote 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/skills/vmobifystudio/app-dev-team/accessibility-gate)<a href="https://agentmods.dev/skills/vmobifystudio/app-dev-team/accessibility-gate"><img src="https://agentmods.dev/badge/skills/vmobifystudio/app-dev-team/accessibility-gate/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/skills/vmobifystudio/app-dev-team/accessibility-gate"><img src="https://agentmods.dev/badge/skills/vmobifystudio/app-dev-team/accessibility-gate.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 | $0.00074 | $0.00636 |
| Opus 5.5 | $0.00030 | $0.00254 |
| Sonnet 5.5 | $0.00015 | $0.00127 |
| Haiku 4.5 | $0.00007 | $0.00064 |
Grade A, and why
accessibility-gate 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.
How it starts
The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility gate
The studio's position, from the plan: accessibility does not need a specialist role, it needs a gate that can fail. This is that gate. It runs on the diff, not on the finished app, because a retrofit is an order of magnitude more expensive than doing it in the ticket.
Where a platform auditor exists, spawn it first and fold its findings in — axiom:accessibility-auditor
on iOS, ui-design:accessibility-audit elsewhere. Both are external and optional (separate
plugins, not this one's skills/). Missing → record N/A: <tool> — not installed, walk the list by
hand, never file the absence as a defect.
The gate
Each item is PASS or FAIL: <what and where>. There is no partial credit and no "minor".
- Every interactive element has an accessible label that says what it does — not its icon name. An unlabelled icon button is a control that does not exist for a screen-reader user.
- Reading order matches visual order, and grouped content is grouped for the screen reader too.
- Every state change is announced — loading finished, error appeared, item deleted. A silent state change strands the user in the previous screen.
- Touch targets are at least 44pt (iOS) / 48dp (Android), including in dense lists.
- Contrast: 4.5:1 body text, 3:1 large text and non-text indicators. Checked against the token, in both light and dark.
- Colour is never the only signal. Error, selection and status carry a shape, an icon or text.
- Dynamic Type / font scaling to the largest supported size does not clip, truncate meaning, or overlap. Test at the maximum, not at 120%.
- Keyboard and switch access reach every action, focus is always visible, and focus is never
trapped. On web this includes a skip link and a visible
:focus-visiblestyle. - Reduce-motion is honoured and still gives the user feedback (
interaction-motion). - Media has an alternative — alt text, caption, or transcript.
Verdict
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 · 46 lines · 74 tokens per session scan A d34ae3a93cd1
accessibility-gate is a skill published in the GitHub repository vmobifystudio/app-dev-team (4 stars, last pushed 4d ago), licensed MIT. It adds 74 tokens to every session and 636 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 2026-09-03.
Other skills, from other repositories
design
Design and front-end specialist (IRC handle @design) dispatched to create, refine, and validate user interface layouts and end-to-end user experience flows.
polish
Autonomous act-then-review convergence loop: iterate /self-review passes, draining every action disposition (Auto-applicable and Agent-resolvable applied, Needs-sign-off applied on the branch) until only irreducible Needs-human-judgment forks remain, then hand off a projection of the audit record plus the…
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
triage
GitHub issue and PR investigator. Pulls open issues/PRs, classifies them, searches the codebase for root cause or reviews contributed code, proposes fixes with file:line references, and optionally implements fixes. Use for investigating GitHub issues and reviewing PRs; do NOT use for general code review unrelated to…
cinematic-shot
Shoot software UI like a film. A sequence of hero shots, each a steep, oblique, extreme close-up of the interface floating in black, with a razor-thin focal plane, a slow motivated camera drift, and UI that acts on its own, hard-cut on the action, ending on one line of copy and a still logo. Use when asked for a…