get-design-done CLAUDE.md

get-design-done CLAUDE.md is an instructions file for Claude Code from 0martinez/get-design-done. It costs 387 tokens per session, scanned A, original, MIT.

A design-planning framework for Claude Code that guides developers through design questions and organizes design work into project documents and phases.

In plain words
What is it for?
Starting design projects, defining design-system tokens, planning phases, creating specifications, rendering designs, and running structured critiques.
Why use it?
It helps turn vague design ideas into documented plans, specifications, reviews, and work for connected design tools.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions Claude Code.

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/0martinez/get-design-done/claude-md
Clone the repo
git clone --depth 1 https://github.com/0martinez/get-design-done

Made for: Claude Code.

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 get-design-done CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/0martinez/get-design-done/claude-md.svg)](https://agentmods.dev/instructions/0martinez/get-design-done/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/0martinez/get-design-done/claude-md"><img src="https://agentmods.dev/badge/instructions/0martinez/get-design-done/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 387 This file is loaded in full into every session.
When invoked 387 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 5.1 $0.00387 $0.00387
Opus 5 $0.00193 $0.00193
Sonnet 5 $0.00077 $0.00077
Haiku 4.5 $0.00039 $0.00039

Measured 6d ago against content hash b9853b8d8c3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

get-design-done CLAUDE.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 6d 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.

CLAUDE.md · 39 lines

What it actually says

Get Design Done (GDD)

A meta-prompting, context engineering and design system framework for Claude Code. The design counterpart to Get Shit Done.

What this is

GDD encodes expert design knowledge into structured reference files and guides developers through the questions a designer would ask — producing design systems and production-quality designs through any MCP-connected design tool.

Architecture

  • .claude/get-design-done/ — Framework core (adapters, references, templates, workflows)
  • .claude/agents/gdd-*.md — Specialized agent prompts
  • .claude/commands/gdd/*.md — Slash command entry points
  • .design/ — Project artifacts (created per-project by /gdd:new-design)

Key Commands

  • /gdd:new-design — Initialize a new design project
  • /gdd:explore-phase N — Discuss vision for phase N
  • /gdd:spec-phase N — Create detailed design spec
  • /gdd:render-phase N — Execute design in connected tool
  • /gdd:critique-phase N — Structured design review
  • /gdd:help — Full command reference

Key Files

  • TOKENS.md — Single source of truth for design system
  • BRIEF.md — Product context and direction
  • ROADMAP.md — Phase breakdown
  • STATE.md — Session memory

Conventions

  • Phase 1 is always "Design System Foundation"
  • All visual values resolve from TOKENS.md
  • Adapters are markdown files mapping abstract ops to MCP calls
  • No design jargon in user-facing interactions
  • Critique uses severity levels (critical/major/minor/note), not pass/fail
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. 6d ago First seen · 39 lines · 387 tokens per session scan A b9853b8d8c3c

Subscribe to this mod's changes

get-design-done CLAUDE.md is an instructions file published in the GitHub repository 0martinez/get-design-done (5 stars, last pushed 6mo ago), licensed MIT. It adds 387 tokens to every session, about $0.0019 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.