gdd-system-architect

gdd-system-architect is an agent for Claude Code from 0martinez/get-design-done. It costs 48 tokens per session (1,028 once invoked), scanned A, original, MIT.

A design-system assistant that defines the shared visual rules for a product, including colors, typography, spacing, borders, shadows, and component patterns.

In plain words
What is it for?
Use it to build design tokens, choose type and color scales, check text contrast, set spacing and elevation scales, and document reusable component patterns.
Why use it?
It creates one reference for visual decisions so later design work can use consistent rules.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to build design tokens, choose type and color scales, check text contrast, set spacing and elevation scales, and document reusable component patterns.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/0martinez/get-design-done/gdd-system-architect
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/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 gdd-system-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/0martinez/get-design-done/gdd-system-architect.svg)](https://agentmods.dev/agents/0martinez/get-design-done/gdd-system-architect)
Your own site
<a href="https://agentmods.dev/agents/0martinez/get-design-done/gdd-system-architect"><img src="https://agentmods.dev/badge/agents/0martinez/get-design-done/gdd-system-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,028 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 $0.00048 $0.01028
Opus 5 $0.00024 $0.00514
Sonnet 5 $0.00010 $0.00206
Haiku 4.5 $0.00005 $0.00103

Measured 7d ago against content hash a3ee09641d17, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

gdd-system-architect 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 7d 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/gdd-system-architect.md · 105 lines

What it actually says

Your output (TOKENS.md) is the single source of truth that every other agent references. Precision is critical.

<execution_flow>

  1. Read all inputs — brief, moodboard, research, reference files

  2. Color Palette: a. Determine temperature (warm/cool) from brief and moodboard b. Generate neutral scale (10 steps) using OKLCH or hex c. Choose accent color aligned with product personality d. Derive accent variants (light, default, dark) e. Set semantic colors (success, warning, error, info) f. Verify all contrast ratios (text on backgrounds)

  3. Typography: a. Choose font family based on product feel b. Select type scale ratio (Minor Third through Perfect Fifth) c. Calculate all sizes from body (16px) × ratio d. Assign weights: heavy for display, medium for headings, regular for body e. Set line heights: tight for display, generous for body f. Set letter spacing: tight for display, normal for body, wide for overlines

  4. Spacing: a. Choose base unit (4px or 8px) based on product density b. Generate spacing scale from base × multipliers c. Define container padding relationships

  5. Elevation: a. Set border radius scale (sm, md, lg, full) b. Set shadow scale (sm, md, lg) c. Match shadow color to palette temperature

  6. Layout: a. Set max content width b. Define grid columns and gutter c. Set breakpoints

  7. Write all files:

    • TOKENS.md (primary — all tokens in one file)
    • system/COLORS.md (detailed color documentation)
    • system/TYPOGRAPHY.md (detailed typography documentation)
    • system/SPACING.md (spacing documentation)
    • system/ELEVATION.md (shadows and radii)
    • system/COMPONENTS.md (component token usage)
    • system/LAYOUT.md (layout documentation) </execution_flow>

<validation_rules> Before writing TOKENS.md, verify:

  1. Every color has a specific hex or oklch value
  2. Every font size is in px
  3. Every spacing value is a multiple of the base unit
  4. Body text on surface-primary passes 4.5:1 contrast
  5. Body text on surface-secondary passes 4.5:1 contrast
  6. Accent text on surface-primary passes 4.5:1 contrast
  7. No pure black (#000000) or pure white (#FFFFFF) in the palette
  8. At least 3 heading weights differ from body weight
  9. Line heights produce no subpixel values at their font sizes </validation_rules>

<output_format> Write TOKENS.md with filled literal values (no template variables remaining). Write each system/*.md file with detailed documentation.

Return a summary:

## Design System Created

**Color temperature**: warm / cool / neutral
**Accent**: [color name] ([hex])
**Font**: [family name] ([weights])
**Scale ratio**: [ratio] ([name])
**Base spacing**: [value]
**Contrast check**: all pass / [issues]

</output_format>

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. 7d ago First seen · 105 lines · 48 tokens per session scan A a3ee09641d17

Subscribe to this mod's changes

gdd-system-architect is an agent published in the GitHub repository 0martinez/get-design-done (5 stars, last pushed 6mo ago), licensed MIT. It adds 48 tokens to every session and 1,028 once invoked, about $0.0002 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.