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)<a href="https://agentmods.dev/commands/jonase47/ccpr/p6-a11y"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/p6-a11y/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/commands/jonase47/ccpr/p6-a11y"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/p6-a11y.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 | $0.00000 | $0.00810 |
| Opus 5.5 | $0.00000 | $0.00324 |
| Sonnet 5.5 | $0.00000 | $0.00162 |
| Haiku 4.5 | $0.00000 | $0.00081 |
Grade A, and why
p6-a11y 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/p6-a11y – Accessibility Check
Systematically checks the application for accessibility. Each A11y dimension is a separate sub-command.
Argument: $ARGUMENTS = [page/component]
If provided: Check the specified page/component. If not provided: Check all critical screens.
Flow
0. Ensure Sub-Index Exists
Make sure docs/quality/A11Y.md exists as a sub-index with the standard header (Status / Last Updated / Key Decisions / Open Risks / Detail Files / Gate Notes — see ~/.claude/docs/PROJECT_PHASES.md). If missing, create it with empty placeholders. The three p6-a11y-* sub-commands below each refresh their own row in this sub-index's Detail Files table.
1. Visual Accessibility
/p6-a11y-visual $ARGUMENTS – Contrast, colours, dark mode, red-green colour blindness.
2. Keyboard Navigation
/p6-a11y-keyboard $ARGUMENTS – Tab order, focus, Enter/Space, Escape.
3. Screen Reader Compatibility
/p6-a11y-screenreader $ARGUMENTS – ARIA, semantics, alt texts, live regions.
4. Roll Up Sub-Index to Phase Index
After all p6-a11y-* sub-commands have run, summarise the A11Y sub-index into the phase index docs/quality/QA.md:
- Add an entry in the phase-index Detail Files table for
[A11Y.md](A11Y.md)(the sub-index itself), statuscompleteonce all three sub-skill rows arecomplete(orneeds-reworkif blocking findings remain). - Lift any unmitigated A11y blocker into the phase-index Open Risks.
Notes
- All three sub-commands can run in parallel (no dependencies)
- Detail files:
a11y_visual.md,a11y_keyboard.md,a11y_screenreader.mdunder theA11Y.mdsub-index - WCAG 2.1 AA as minimum standard
- Always account for red-green colour blindness
Handover Epilogue
Before writing. docs/HANDOVER.md is capped — the file states its own limit in its header
(default: ≤5 KB / ~150 lines). Two rules follow from that, and neither is optional:
- Replace this command's previous epilogue block, do not append a second one. Stacking is what pushes the file over; one command run has been measured adding 1021 B, ~20 % of the cap.
- If the file is already near its cap, shorten before you add. Reading the cap sentence is not
the same as measuring: check the actual size, and when there is no room, condense existing content
or hand the user
/cleanupinstead of growing the file further.
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 Changed · +1 lines 284429d7296e
- 1mo ago Changed 1bc1afc843de
- 1mo ago First seen · 57 lines · 0 tokens per session scan A c099c1b68ac3
p6-a11y is a command published in the GitHub repository jonase47/ccpr (1 stars, last pushed 28d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 810 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.
prompt
Generate Google Stitch-ready prompts from briefs or spec files using the authoring skill.
stitch-generate
Full Stitch pipeline — author prompts, generate screens via MCP, fetch images and code.
prototype
Rapid UI prototyping — generates 3 visually distinct HTML/CSS components from a text prompt and serves them in a live browser gallery.
stitch-setup
Guided setup and verification of Stitch MCP server connection.
kenspc-prototype
Explicit entry point for the prototype skill — answer one open question from a brief with a throwaway prototype (原型).