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/jonase47/ccprWrote 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/commands/jonase47/ccpr/p6-a11y-keyboard)<a href="https://agentmods.dev/commands/jonase47/ccpr/p6-a11y-keyboard"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/p6-a11y-keyboard.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 | $0.00000 | $0.00943 |
| Opus 5 | $0.00000 | $0.00472 |
| Sonnet 5 | $0.00000 | $0.00189 |
| Haiku 4.5 | $0.00000 | $0.00094 |
Grade A, and why
p6-a11y-keyboard 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 yesterday.
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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/p6-a11y-keyboard – Keyboard Navigation & Focus
Checks full keyboard operability: tab order, focus indicator, Enter/Space, Escape, focus trap.
Argument: $ARGUMENTS = [page/component]
If provided: Check the specified page/component. If not provided: Check all interactive areas.
Prerequisites
- UI implemented with interactive elements
Agent
- Type: ux-designer
- Model: sonnet
Context (Orchestrator prepares)
Orchestrator reads in advance and delivers inline:
- From src/: HTML structure (interactive elements, tabindex, event handlers)
- From ACCESSIBILITY.md: Keyboard requirements
Prompt Template
Goal: Check keyboard navigation for: [page/component]
HTML Structure: [inline from src/]
Output Format: Checklist:
# Check Point Status Finding 1 All elements reachable via Tab OK/FINDING ... 2 Tab order is logical OK/FINDING ... 3 Focus indicator visible OK/FINDING ... 4 Enter/Space activates elements OK/FINDING ... 5 Escape closes overlays OK/FINDING ... 6 Focus trap in modals OK/FINDING ... 7 Touch targets >= 44x44px OK/FINDING ... Constraints:
- Keyboard navigation ONLY – no colours, no screen reader
- Focus on interactive elements (buttons, links, inputs, modals)
Orchestrator Checkpoint
- All interactive elements checked?
- Focus management for dynamic content tested?
Write Detail File
Write the result to docs/quality/a11y_keyboard.md (overwrite if it exists). Start with this YAML frontmatter:
---
phase: P6
subskill: a11y-keyboard
status: active
last_updated: <DD.MM.YYYY>
---
Body sections: ## Scope (which pages/components were checked), ## Findings (the checklist table), ## Severity Summary (counts of OK / minor / major findings).
Update Sub-Index
Update docs/quality/A11Y.md (the accessibility sub-index, created by /p6-a11y if missing):
- Set
**Last Updated:** <DD.MM.YYYY>. - In its Detail Files table: ensure a row for
[a11y_keyboard.md](a11y_keyboard.md)with statuscomplete(orneeds-reworkif blocking findings exist). - Lift any blocking finding into Open Risks / Open Questions of the sub-index.
- Do not edit the phase-level
QA.mddirectly —/p6-a11yrolls the sub-index up.
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.
- yesterday Changed d4cb189d0724
- 4d ago First seen · 91 lines · 0 tokens per session scan A 5cc3f3327f59
p6-a11y-keyboard is a command published in the GitHub repository jonase47/ccpr (1 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 943 tokens. 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 commands, from other repositories
design-intent
Guided UI/visual development with structured exploration, architecture design, and quality review.
prototype
Rapid UI prototyping — generates 3 visually distinct HTML/CSS components from a text prompt and serves them in a live browser gallery.
design-tokens
Create design system token architecture. Usage: /mindforge:design-tokens [--layers primitive|semantic|component] [--theme dark|light].
tanstack-start
Build a full-stack TanStack Start app on Cloudflare Workers from scratch.
growth-landing
Create or optimize an effective landing page.
sdd
Spec-driven dev loop. Plan once, then dev↔test↔eval loop until PRP spec satisfied. Local only, no PR.