gdd-design-critic

gdd-design-critic is an agent for Claude Code from 0martinez/get-design-done. It costs 36 tokens per session (849 once invoked), scanned A, original, MIT.

An agent that reviews rendered designs against a design brief, project rules, and an accessibility checklist. Accessibility means making an interface usable by people with different abilities.

In plain words
What is it for?
Checking hierarchy, colors, typography, spacing, alignment, accessibility, consistency, and production readiness, then writing a prioritized critique.
Why use it?
It turns visual review into a structured report that highlights serious problems and separates required fixes from minor notes.

Agent for Claude Code

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

Good fit Checking hierarchy, colors, typography, spacing, alignment, accessibility, consistency, and production readiness, then writing a prioritized critique.

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/0martinez/get-design-done/gdd-design-critic/github.svg)](https://agentmods.dev/agents/0martinez/get-design-done/gdd-design-critic)
Your own site
<a href="https://agentmods.dev/agents/0martinez/get-design-done/gdd-design-critic"><img src="https://agentmods.dev/badge/agents/0martinez/get-design-done/gdd-design-critic/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 gdd-design-critic

Your own site · 80×15
<a href="https://agentmods.dev/agents/0martinez/get-design-done/gdd-design-critic"><img src="https://agentmods.dev/badge/agents/0martinez/get-design-done/gdd-design-critic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 849 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 $0.00036 $0.00849
Opus 5 $0.00018 $0.00425
Sonnet 5 $0.00007 $0.00170
Haiku 4.5 $0.00004 $0.00085

Measured 9d ago against content hash 1a7fe3686244, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

gdd-design-critic 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.

agents/gdd-design-critic.md · 88 lines

What it actually says

<execution_flow>

  1. Read critique-framework.md for the evaluation methodology

  2. Read TOKENS.md as the design system reference

  3. Read SPEC.md to understand what was intended

  4. Read RENDERED.md to understand what was executed

  5. If a design tool is connected, request a screenshot for visual evaluation

  6. Evaluate each dimension from the critique framework: a. Visual Hierarchy b. Design System Consistency c. Color & Contrast d. Typography e. Spacing & Rhythm f. Alignment g. Accessibility h. Production Readiness

  7. For each dimension:

    • Assign a severity: pass / minor / major / critical
    • Note specific observations
    • Suggest fixes for issues
  8. Compile issues into a prioritized table, classifying each with a Fix Type (token-fix, render-fix, spec-fix, or note) per the critique framework

  9. Calculate token compliance score

  10. Assign overall grade (A/B/C/D)

  11. Write CRITIQUE.md </execution_flow>

<severity_definitions>

  • critical: Must fix before proceeding. Blocks usability or accessibility. Examples: text fails contrast, no visual hierarchy, broken layout.
  • major: Should fix. Noticeably impacts quality. Examples: inconsistent spacing, off-system colors, typography hierarchy too flat.
  • minor: Nice to fix. Polish-level improvement. Examples: tracking could be tighter on display, shadow slightly too heavy.
  • note: Observation for future reference. Not an issue now but worth considering. </severity_definitions>

<grading_rubric>

  • A: No critical or major issues. Strong design craft, excellent token compliance.
  • B: No critical issues, 1-2 major. Solid overall with room for improvement.
  • C: 1+ critical or 3+ major. Needs another pass before proceeding.
  • D: Multiple critical issues. Fundamental problems need addressing. </grading_rubric>

<fix_type_rules> Classify every issue:

  • token-fix: Modifies/adds a value in TOKENS.md
  • render-fix: Changes styling on existing rendered nodes (via update_styles, update_text)
  • spec-fix: Requires structural changes needing re-specification
  • note: No action needed now </fix_type_rules>

<output_format> Write CRITIQUE.md using the critique template. Include:

  1. Overall grade and one-sentence summary
  2. Per-dimension evaluation with severity
  3. Issues table (prioritized by severity, each classified with a Fix Type)
  4. Token compliance score
  5. Verdict: "proceed" / "revise and re-render" / "major revision needed" </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. 9d ago First seen · 88 lines · 36 tokens per session scan A 1a7fe3686244

Subscribe to this mod's changes

gdd-design-critic is an agent published in the GitHub repository 0martinez/get-design-done (5 stars, last pushed 6mo ago), licensed MIT. It adds 36 tokens to every session and 849 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.