colorize

colorize is a command for coding agents from Dragoon0x/canon. It costs 21 tokens per session (507 once invoked), scanned A, original, MIT.

A command for creating or auditing a user-interface color system with named design tokens and required WCAG contrast levels for accessibility.

In plain words
What is it for?
Use it to build neutral, brand, and status-color scales; define component color tokens; create dark mode; and check text, controls, and focus-ring contrast.
Why use it?
It replaces ad-hoc color picking with defined light and dark palettes, semantic roles, and measurable contrast checks.

Command

Install

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.

agentmods
npx agentmods add commands/dragoon0x/canon/colorize
Clone the repo
git clone --depth 1 https://github.com/Dragoon0x/canon

Wrote 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.

agentmods badge for colorize

README.md
[![agentmods](https://agentmods.dev/badge/commands/dragoon0x/canon/colorize.svg)](https://agentmods.dev/commands/dragoon0x/canon/colorize)
Your own site
<a href="https://agentmods.dev/commands/dragoon0x/canon/colorize"><img src="https://agentmods.dev/badge/commands/dragoon0x/canon/colorize.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 507 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00021 $0.00507
Opus 5 $0.00010 $0.00253
Sonnet 5 $0.00004 $0.00101
Haiku 4.5 $0.00002 $0.00051

Measured 4d ago against content hash a85b542e385b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

colorize 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 4d 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.

source/commands/colorize.md · 44 lines

What it actually says

/colorize

Construct a color system, or audit an existing one. Not "pick pretty colors" — perceptual scales, contrast math, semantic layering.

What this does

  1. Load canon-color.
  2. Work in OKLCH. Hex is fine for final output; reasoning happens in OKLCH.
  3. Build the base palette:
    • Neutrals: 10–12 step tinted ramp. Never #000000 or #ffffff as the extremes. Start at L=7–10% and end at L=96–99%. Add 2–5% chroma toward the brand hue to avoid dead gray.
    • Brand: full 10-step ramp, L=15% to L=95%, chroma following the curve (peaks near L=60%).
    • Semantic: success, warning, danger, info. Each gets a 10-step ramp.
  4. Layer into tokens:
    • Primitive: raw scale values (--blue-500).
    • Semantic: intent names (--color-brand-primary, --color-text-default).
    • Component: contextual (--button-primary-bg).
  5. Enforce contrast:
    • Body text on background: 4.5:1 minimum (WCAG AA).
    • Large text (18pt+ or 14pt+ bold): 3:1.
    • UI components and focus rings: 3:1.
    • Disabled state: exempt but must look unmistakably disabled.
  6. Build dark mode by inverting lightness roles, not by shifting hues. Text that was L=10% in light becomes L=90% in dark.
  7. Banned pairings:
    • Gray text on a color (always fails contrast at light grays).
    • Pure black shadows (use tinted neutral darkest).
    • Red/green as the only signal for status.

Output

  • OKLCH source definitions.
  • Hex fallbacks.
  • CSS custom properties for all three layers.
  • Contrast audit table for critical pairings.
  • Light and dark mode declarations.

Success criteria

Every semantic pair passes WCAG AA. No token uses a raw hex outside the primitive layer. Dark mode isn't a hue shift; it's a lightness inversion.

Changes

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.

  1. 4d ago First seen · 44 lines · 21 tokens per session scan A a85b542e385b

Subscribe to this mod's changes

colorize is a command published in the GitHub repository Dragoon0x/canon (5 stars, last pushed 4mo ago), licensed MIT. It adds 21 tokens to every session and 507 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.