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/kreek/consult/accessibilitynpx skills add kreek/consult --skill accessibilitygit clone --depth 1 https://github.com/kreek/consultWrote 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/kreek/consult/accessibility)<a href="https://agentmods.dev/skills/kreek/consult/accessibility"><img src="https://agentmods.dev/badge/skills/kreek/consult/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 | $0.00023 | $0.01170 |
| Opus 5 | $0.00012 | $0.00585 |
| Sonnet 5 | $0.00005 | $0.00234 |
| Haiku 4.5 | $0.00002 | $0.00117 |
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 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility
Iron Law
WCAG 2.2 AA IS THE FLOOR; NATIVE SEMANTICS COME FIRST.
When to Use
- Building, changing, or reviewing user-facing UI, forms, navigation, modals, custom controls, interactive states, animation, color, typography, or content structure.
- Testing keyboard flow, focus order, screen-reader behavior, contrast, reduced motion, forced colors, or accessible names.
When NOT to Use
- Backend-only changes with no user-facing output.
- Visual hierarchy or brand direction without implementation; use
ui-designfirst, then return here for accessibility constraints. - Performance-only UI work; use
performance, then verify accessibility if rendering behavior changed.
Core Ideas
- Prefer native HTML controls and semantics before ARIA.
- Every interactive element needs name, role, value, state, and keyboard behavior.
- Focus must be visible: at least a 2px outline at 3:1 contrast
against both adjacent surfaces, with a transparent fallback for
Forced Colors. Focus order must be logical. Focus must be restored
after modal or overlay close. Do not trap focus by hand inside a
<dialog>. - Color cannot be the only signal; contrast must satisfy WCAG 2.2 AA.
- Motion, transparency, dark mode, high contrast, and forced colors follow user preferences.
- Forms need explicit labels, grouped controls, errors tied to fields, and no placeholder-only instructions.
- Automated checks catch only part of the problem; manual keyboard and screen-reader checks are required for meaningful UI changes.
Workflow
- Identify the affected user journey, controls, and content structure. Use semantic HTML first; add ARIA only when native elements cannot express the interaction.
- Define keyboard behavior and focus management before styling custom controls. Check labels, accessible names, headings, landmarks, form errors, status messages, and live regions.
- Verify contrast, reflow, target size, reduced motion, forced colors, text spacing, dragging alternatives, redundant entry, and authentication flows. Authentication must not depend on cognitive tests.
- Run automated checks, then perform manual keyboard testing. Add screen-reader testing for custom controls, dialogs, menus, tabs, forms, and live updates. Record remaining accessibility risks as explicit blockers or deferred work.
What ships with it
2 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.
- 3d ago First seen · 107 lines · 23 tokens per session scan A c1ead7f8e884
accessibility is a skill published in the GitHub repository kreek/consult (1 stars, last pushed 8d ago), licensed MIT. It adds 23 tokens to every session and 1,170 once invoked, about $0.0001 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
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.
qa
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
systematic-debugging
4-phase root cause analysis: observe, hypothesize, verify, fix. Enforces investigation before any code changes. Emergency stop after 2 failed fixes. Prevents shotgun debugging and fix cascades.
claude-code-session-broker
Use when running Arcgentic V2 in Claude Code and fixed Planner, Developer, and Auditor role sessions must be coordinated through a broker.