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 commands/jonase47/ccpr/p6-a11y-visualgit 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-visual)<a href="https://agentmods.dev/commands/jonase47/ccpr/p6-a11y-visual"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/p6-a11y-visual.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 | $0.00000 | $0.00956 |
| Opus 5 | $0.00000 | $0.00478 |
| Sonnet 5 | $0.00000 | $0.00191 |
| Haiku 4.5 | $0.00000 | $0.00096 |
Grade A, and why
p6-a11y-visual 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 today.
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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/p6-a11y-visual – Contrast, Colours & Dark Mode
Checks colour contrast (WCAG AA), colour-independence of information presentation, and dark mode conformance.
Argument: $ARGUMENTS = [page/component]
If provided: Check the specified page/component. If not provided: Check all critical screens.
Prerequisites
- UI implemented
- ACCESSIBILITY.md with WCAG target present
Agent
- Type: ux-designer
- Model: sonnet
Context (Orchestrator prepares)
Orchestrator reads in advance and delivers inline:
- From src/: CSS/styles (colour definitions, dark mode variables)
- From ACCESSIBILITY.md: WCAG target and colour requirements
- From UX_CONCEPT.md: Colour palette, dark mode concept
Prompt Template
Goal: Check visual accessibility for: [page/component]
Styles/Colours: [inline from CSS]
WCAG Requirements: [inline from ACCESSIBILITY.md]
Output Format: Contrast table:
# Element Foreground Background Ratio WCAG Status Colour independence:
# Element Colour-only info? Alternative present? Status Dark mode checks:
# Element Light OK? Dark OK? Finding Constraints:
- Visual check ONLY – no keyboard, no screen reader
- WCAG 2.1 AA: text >= 4.5:1, large text >= 3:1, UI elements >= 3:1
- Account for red-green colour blindness (blue/orange instead of red/green)
Orchestrator Checkpoint
- All colour combinations checked (light + dark)?
- Red-green colour blindness accounted for?
- Contrast ratios correctly calculated?
Write Detail File
Write the result to docs/quality/a11y_visual.md (overwrite if it exists). Start with this YAML frontmatter:
---
phase: P6
subskill: a11y-visual
status: active
last_updated: <DD.MM.YYYY>
---
Body sections: ## Scope, ## Contrast Checks (the contrast-ratio table), ## Colour Independence, ## Dark Mode Checks, ## Severity Summary.
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.
- today First seen · 99 lines · 0 tokens per session scan A ee627cd97a40
p6-a11y-visual 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 956 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
Early-stage design exploration — settle the shape of a feature/recipe/system before scoping its implementation. Re-entrant; agent-judged writes.
devteam-design
Command: /devteam:design [target] [options].
devteam-design-drift
Command: /devteam:design-drift [scope] [options].
cli
Design CLI command structure and UX. Usage - /mindforge:cli [app-name] [--style verb-noun|git-style].