agentleFS
Sign inStart free
a-ng-da-ng-d/docs-ui-color-palette/claude/agents.md

docs-ui-color-palette / claude

AGENTS.md1 starsChanged 5 months agoMITView on GitHub

Specialized sub-agents that handle focused tasks within the UI Color Palette workflow

We split this agents.md into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Call generate_code with the right format and colorSpace

    line 73

≈ “Common” is an estimate: at least 1 in 5 of the 36,368 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
agents.md

Agents

The plugin ships six agents. uicper is the default orchestrator — it delegates to the five specialized agents when a task falls within their scope.

uicper

Default agent — configured in settings.json.
Model: Sonnet · Effort: high · Max turns: 30

Top-level orchestrator for multi-step workflows. It coordinates skills, delegates to specialized agents, and assembles results across the full 4-phase workflow.

Typical workflows it handles:

  • generate → audit → export
  • generate → preview → sync to design tool
  • retrieve from community → rebuild → audit → export

It does not perform heavy computation itself — it picks the right workflow and delegates.

palette-color-systemer

Model: Sonnet · Effort: medium · Max turns: 20

Specialized agent for guided semantic color system design. Walks the user through the full taxonomy → binding → submission workflow step by step.

Responsibilities:

  • Suggest taxonomy patterns (Role × State, Role × Prominence × State, Surface × Content, Custom)
  • Confirm members per group before proceeding
  • Propose intelligent default bindings derived from palette color ids and shade stops
  • Flag tokens that have no natural binding in the current palette
  • Batch all adjustments before calling get_color_system once
  • Display the resolved token matrix and route to the next deploy step

Hard prerequisite: PaletteData or base + themes must be in context. If missing, the agent stops and redirects to scale-palette first.

palette-auditor

Model: Sonnet · Effort: high · Max turns: 20

Specialized accessibility and quality auditor. Reads pre-computed WCAG and APCA scores from palette data — it never recalculates contrast from scratch.

Responsibilities:

  • WCAG 2.1 and APCA contrast audits across all shade/text color pairs
  • Global contrast score and risk level classification
  • Risky pair detection (fails AA, fails large text, borderline)
  • Actionable remediation recommendations (lightness adjustments, swap suggestions)

palette-codegen

Model: Sonnet · Effort: high · Max turns: 12

Specialized code and token export agent. Minimal questions, direct output.

Responsibilities:

  • Call generate_code with the right format and colorSpace
  • Optionally commit the generated file to the project repository
  • Handle both primitive-only and semantic (primitives + semantics) exports

palette-publisher

Model: Sonnet · Effort: high · Max turns: 18

Specialized palette lifecycle agent for the UI Color Palette platform.

Responsibilities:

  • Browse and search community palettes (list_published_palettes)
  • Retrieve a specific palette by ID and load it into session context
  • Publish, update, share, unshare, and delete palettes
  • Handle OAuth authentication flow for protected operations

palette-transitioner

Model: Sonnet · Effort: high · Max turns: 24

Specialized transition agent. Takes PaletteData and moves it into the right design-tool or file artifact.

Responsibilities:

  • Variables (Figma, Sketch, Penpot)
  • Tokens (Penpot, Sketch, Framer)
  • Styles (Figma, Framer, Sketch)
  • Swatch board / document previews
  • Semantic variable collections on top of primitive variables

It handles the transition logic — uicper handles the broader orchestration.

Download now (ZIP)

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 28,693 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free