design-intent

design-intent is a command for Claude Code from joaquimscosta/arkhe-claude-plugins. It costs 16 tokens per session (2,252 once invoked), scanned A, original, MIT.

A command for planning and reviewing UI work through seven phases, from understanding requirements and existing design patterns to implementation, quality review, and documentation. UI means the visible parts of an application that people use.

In plain words
What is it for?
For building or changing interfaces, checking existing components and design tokens, resolving visual and responsive questions, implementing with a specialist skill, and documenting reusable patterns.
Why use it?
It helps prevent visual inconsistencies and missed requirements by making exploration, design decisions, accessibility, and review part of the workflow.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: names the TodoWrite tool.

Part of the design-intent plugin — 4 skills, 5 commands, 3 agents shipped together

Good fit For building or changing interfaces, checking existing components and design tokens, resolving visual and responsive questions, implementing with a specialist skill, and documenting reusable patterns.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/joaquimscosta/arkhe-claude-plugins/design-intent
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.

Clone the repo
git clone --depth 1 https://github.com/joaquimscosta/arkhe-claude-plugins

Made for: Claude Code.

Or install design-intent, the plugin that ships this one along with the rest of its 4 skills, 5 commands, 3 agents.

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 design-intent

README.md
[![agentmods](https://agentmods.dev/badge/commands/joaquimscosta/arkhe-claude-plugins/design-intent/github.svg)](https://agentmods.dev/commands/joaquimscosta/arkhe-claude-plugins/design-intent)
Your own site
<a href="https://agentmods.dev/commands/joaquimscosta/arkhe-claude-plugins/design-intent"><img src="https://agentmods.dev/badge/commands/joaquimscosta/arkhe-claude-plugins/design-intent/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.

agentmods 80×15 button for design-intent

Your own site · 80×15
<a href="https://agentmods.dev/commands/joaquimscosta/arkhe-claude-plugins/design-intent"><img src="https://agentmods.dev/badge/commands/joaquimscosta/arkhe-claude-plugins/design-intent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,252 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00016 $0.02252
Opus 5 $0.00008 $0.01126
Sonnet 5 $0.00003 $0.00450
Haiku 4.5 $0.00002 $0.00225

Measured 9d ago against content hash 6687bb387448, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

design-intent 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 9d 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.

plugins/design-intent/commands/design-intent.md · 286 lines

How it starts

The opening of the file, as written. The whole thing — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Intent Development

You are helping a developer implement UI/visual work while maintaining design consistency. Follow a systematic 7-phase approach: understand requirements, explore existing patterns, ask clarifying questions, design architecture, implement with the design-intent-specialist skill, review quality, and document patterns.

Core Principles

  • Visual fidelity matters: Match visual references accurately, flag conflicts with existing patterns
  • Ask clarifying questions: Identify all visual ambiguities, responsive needs, accessibility requirements
  • Explore before building: Understand existing components, tokens, and patterns first
  • Read files identified by agents: After agents complete, read identified files to build detailed context
  • Use TodoWrite: Track all progress throughout the 7 phases
  • Invoke design-intent-specialist: Use the skill during implementation phase for visual accuracy

Quick Mode

If invoked with --quick in the arguments, skip Phases 2 (Exploration) and 4 (Architecture):

  • Go directly from Discovery to Questions
  • After Questions, proceed to Implementation
  • Still perform Review and Patterns phases

Use --quick for small changes, single components, or when patterns are already well-known.


Phase 1: Discovery

Goal: Understand what UI/visual work needs to be done

Initial request: $ARGUMENTS

Actions:

  1. Create todo list with all 7 phases
  2. Check if design-intent structure exists at /design-intent/
    • If not found, suggest running /setup first
  3. Analyze the request type:
    • Screenshot/image reference provided
    • Figma URL provided
    • Text description of UI to build
    • Lightweight brief or notes (inline or file)
    • Existing spec from /develop or other workflow (read if present)
  4. If visual reference provided, perform initial visual analysis:
    • Layout structure
    • Key components visible
    • Color palette impression
    • Typography observations
  5. If requirements unclear, ask user:
    • What UI problem are they solving?
    • What should it look like/do?
    • What framework/design system are they using?
    • Any constraints (accessibility, mobile-first, performance)?
  6. Summarize understanding and confirm with user before proceeding

Read the full file on GitHub · 286 lines

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. 9d ago First seen · 286 lines · 16 tokens per session scan A 6687bb387448

Subscribe to this mod's changes

design-intent is a command published in the GitHub repository joaquimscosta/arkhe-claude-plugins (21 stars, last pushed 26d ago), licensed MIT. It adds 16 tokens to every session and 2,252 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 2026-08-30.