hexed AGENTS.md

An image-to-colour-system tool that turns colours from a picture into organised design tokens, reusable values for an interface's colours and themes.

In plain words
What is it for?
Use it to extract palettes and create CSS variables, Tailwind configuration, or Figma Tokens files for a design system.
Why use it?
It removes the need to choose interface colours manually from visual references and keeps light, dark, neutral, and status colours structured.

Instructions file for CodexOpenCode

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 instructions/loserlab/hexed/agents-md
Clone the repo
git clone --depth 1 https://github.com/LoserLab/hexed

Made for: Codex, OpenCode.

Per session 275 This file is loaded in full into every session.
When invoked 275 The same file — it is already loaded in full.
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 $0.00275 $0.00275
Opus 5 $0.00138 $0.00138
Sonnet 5 $0.00055 $0.00055
Haiku 4.5 $0.00028 $0.00028

Measured 2d ago against content hash c4d51e5d3ff8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hexed AGENTS.md 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 2d 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.

AGENTS.md · 31 lines

What it actually says

Hexed

Image-to-color-system compiler for Claude Skills. Extracts structured color palettes from images.

When to suggest this skill

  • User uploads images and asks to extract colors, create a palette, or build a color system
  • User needs design tokens, theme colors, or UI colors from visual references
  • User wants CSS variables, Tailwind config, or Figma tokens from images
  • User mentions "color palette", "color scheme", "design tokens", "theme colors"
  • User is building a design system and needs color extraction

What it produces

  • Core colors (primary, secondary, accent)
  • 10-step neutral ramp (50-900)
  • Semantic colors (success, warning, error, info)
  • Light and dark UI theme tokens
  • Exports: CSS variables, Tailwind config, Figma tokens (Tokens Studio format)

Key files

  • SKILL.md - Full skill instructions
  • hexed_compiler.py - Core color extraction and system building
  • hexed_exports.py - Export utilities (CSS, Tailwind, Figma)

Suite context

Part of a 5-skill design system pipeline: Hexed (colors) → Specimen (typography) → Gridlock (layout) → Eyes Peeled (accessibility) → Devourer (components)

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. 2d ago First seen · 31 lines · 275 tokens per session scan A c4d51e5d3ff8

Subscribe to this mod's changes

hexed AGENTS.md is an instructions file published in the GitHub repository LoserLab/hexed (3 stars, last pushed 5mo ago), licensed MIT. It adds 275 tokens to every session, about $0.0014 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.