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 skills add Owl-Listener/inclusive-design-skills --skill colour-independencegit clone --depth 1 https://github.com/Owl-Listener/inclusive-design-skillsWrote 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/owl-listener/inclusive-design-skills/colour-independence)<a href="https://agentmods.dev/skills/owl-listener/inclusive-design-skills/colour-independence"><img src="https://agentmods.dev/badge/skills/owl-listener/inclusive-design-skills/colour-independence/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/skills/owl-listener/inclusive-design-skills/colour-independence"><img src="https://agentmods.dev/badge/skills/owl-listener/inclusive-design-skills/colour-independence.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 | $0.00095 | $0.00808 |
| Opus 5 | $0.00048 | $0.00404 |
| Sonnet 5 | $0.00019 | $0.00162 |
| Haiku 4.5 | $0.00010 | $0.00081 |
Grade A, and why
colour-independence 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 12d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Colour Independence
Design so that every piece of information conveyed by colour is also conveyed by something else — shape, text, pattern, position, or icon. 8% of men and 0.5% of women have colour vision deficiency. That's roughly 1 in 12 of your male users.
Core Principle
Colour can enhance meaning. Colour must never be the only carrier of meaning.
Common Failures
Status Indicators
- Bad: green dot = online, red dot = offline (colour only)
- Good: green dot + "Online" label, red dot + "Offline" label
- Better: green dot with tick + "Online", grey dot with x + "Offline"
Form Validation
- Bad: red border on invalid fields (colour only)
- Good: red border + error icon + error text message
- The error message does the real work — the colour is reinforcement
Data Visualisation
- Bad: line chart with 5 coloured lines, legend uses colour swatches
- Good: different line styles (solid, dashed, dotted) + labels + distinct colours that work in greyscale
- Good: bar chart with patterns (stripes, dots, solid) alongside colour
- Always test charts in greyscale — can you still read them?
Links
- Bad: links distinguished from body text only by colour
- Good: links are coloured AND underlined
- The underline is the accessible indicator — colour is the enhancement
Alerts and Badges
- Bad: red badge = urgent, yellow = warning, green = ok
- Good: red badge + "Urgent" label, yellow + "Warning" label, green + "OK" label
- Icons reinforce: ⚠ for warning, ✓ for success, ✕ for error
Maps and Diagrams
- Bad: regions coloured to show data (choropleth with no labels)
- Good: colours + patterns + values displayed on each region
- Good: interactive with values on hover/focus AND a data table alternative
Design Patterns
Double Encoding
Every colour meaning gets a second encoding:
- Colour + icon
- Colour + text label
- Colour + pattern or texture
- Colour + shape
- Colour + position
Accessible Colour Palettes
- Choose colours that are distinguishable in all types of colour vision deficiency (not just red-green)
- Use a colour blindness simulator to test your palette
- Blue and orange are generally safe for most types
- Avoid red/green as the only pair distinguishing two states
- Ensure sufficient contrast between adjacent colours in charts
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.
- 12d ago First seen · 91 lines · 95 tokens per session scan A 4a24e41dabfb
colour-independence is a skill published in the GitHub repository Owl-Listener/inclusive-design-skills (98 stars, last pushed 3mo ago), licensed MIT. It adds 95 tokens to every session and 808 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.