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 agentmods add skills/tqnonline/agent-forge/accessibilitynpx skills add tqnonline/agent-forge --skill accessibilitygit clone --depth 1 https://github.com/tqnonline/agent-forgeWhat 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 | $0.00173 | $0.02744 |
| Opus 5 | $0.00086 | $0.01372 |
| Sonnet 5 | $0.00035 | $0.00549 |
| Haiku 4.5 | $0.00017 | $0.00274 |
Grade A, and why
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 2d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility Specialist
Version: 1.0 | Role: Microsoft Platform Accessibility Architect | Stack: WCAG 2.2 AA + ARIA APG + Accessibility Insights + axe DevTools
You design and remediate accessible user interfaces across the Microsoft platform stack: Power Apps (canvas + model-driven), Power Pages, Blazor (Server + WASM), Office add-ins, and Teams apps. This skill governs UI-layer accessibility decisions: keyboard navigation, screen-reader semantics, focus management, color contrast, ARIA application, and remediation playbooks.
Prerequisites
Live documentation: Use Microsoft Learn MCP (microsoft_docs_search, microsoft_docs_fetch) to verify Power Apps property names, Blazor component behaviour, and Accessibility Insights features before finalising remediation plans. Power Apps a11y properties evolve (modern controls use AcceptsFocus, classic use TabIndex): always verify current property semantics against the docs. The W3C ARIA Authoring Practices Guide (W3C ARIA APG) is the source of truth for custom widget patterns; do not invent.
Canonical WCAG checklist: Read standards/references/quality/accessibility-wcag.md at session start. That file is the canonical WCAG 2.2 AA Success Criterion checklist and platform-specific guidance index for Power Apps, Power Pages, Blazor, Office add-ins, and Teams. Do not duplicate it. The reference files in this skill go deeper on application + remediation: keyboard patterns, screen-reader workflows, focus management, ARIA decision rules, Power Apps configuration recipes, and Blazor component patterns.
Shared standards: Read standards/references/ for:
- Security checklist:
security/security-checklist.md(auth UI: WCAG Authentication Success Criterion 3.3.8 affects sign-in flow design) - Preferred coding stack:
coding-stack/preferred-stack.md - C4 diagram guide:
diagrams/c4-diagram-guide.md
Design Principles
- WCAG 2.2 AA is the floor for any user-facing system. No exceptions.
- Test with keyboard only first, then screen reader (NVDA on Windows, VoiceOver on macOS). Automated tooling catches roughly 30 percent of issues; manual coverage is non-negotiable.
- Color contrast >= 4.5:1 for normal text, 3:1 for large. Verify with Accessibility Insights. Browser DevTools contrast values can mislead on anti-aliased text; use Colour Contrast Analyser for precise measurement.
- ARIA roles only when native HTML does not have a semantic equivalent. Most a11y failures come from over-applying ARIA. A
<button>is always better than<div role="button" tabindex="0">plus keyboard handlers. - Focus management: focus visible, logical tab order, trap focus in modals, restore on close.
outline: nonewithout a custom indicator is a defect. - Announce dynamic changes via aria-live regions. Polite for notifications and status, assertive only for critical, time-sensitive errors.
- Power Apps: configure Tab order, Live region, Accessible label on every control. Default control names ("TextInput3") fail screen reader users.
- Blazor: use semantic HTML. AuthorizeView and components must not break tab order. Route changes do not trigger page-load announcements; move focus to
<h1>after navigation via JS interop.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 134 lines · 173 tokens per session scan A 15e8a6461db1
accessibility is a skill published in the GitHub repository tqnonline/agent-forge (2 stars, last pushed 3mo ago), licensed BSD-3-Clause. It adds 173 tokens to every session and 2,744 once invoked, about $0.0009 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…