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.
npx agentmods add instructions/0martinez/get-design-done/claude-mdgit clone --depth 1 https://github.com/0martinez/get-design-doneWrote 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.
[](https://agentmods.dev/instructions/0martinez/get-design-done/claude-md)<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>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.
| Model | Per session | Once 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 |
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.
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 systemBRIEF.md— Product context and directionROADMAP.md— Phase breakdownSTATE.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
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.
- 6d ago First seen · 39 lines · 387 tokens per session scan A b9853b8d8c3c
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.
Other instructions, from other repositories
MasterGo2Figma AGENTS.md
AGENTS.md instructions for AaronXu-Lab/MasterGo2Figma, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
MasterGo2Figma CLAUDE.md
Claude Code instructions for AaronXu-Lab/MasterGo2Figma: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
apm python.instructions.md
Python development guidelines.
Commit Message
Comprehensive Conventional Commits guidelines for openwebui-extensions.
SwarmAI CLAUDE.md
Claude Code instructions for xg-gh-25/SwarmAI, covering claude.md, before you push — the local quality gate, commit identity, dev commands and conventions & invariants.
sdd-pilot sddp-bootstrap.instructions.md
Instructions for attilaszasz/sdd-pilot: These are project-level bootstrap documents. Edit each via its owning skill.