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.
git 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/agents/0martinez/get-design-done/gdd-accessibility-checker)<a href="https://agentmods.dev/agents/0martinez/get-design-done/gdd-accessibility-checker"><img src="https://agentmods.dev/badge/agents/0martinez/get-design-done/gdd-accessibility-checker.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 | $0.00039 | $0.00779 |
| Opus 5 | $0.00019 | $0.00390 |
| Sonnet 5 | $0.00008 | $0.00156 |
| Haiku 4.5 | $0.00004 | $0.00078 |
Grade A, and why
gdd-accessibility-checker 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 8d 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
<execution_flow>
-
Read accessibility-standards.md for the full checklist
-
Read TOKENS.md and extract all color values
-
Contrast Audit:
- Calculate relative luminance for each color
- Test every text-on-background combination
- Check: normal text (4.5:1), large text (3:1), UI components (3:1)
- Calculate actual ratios, not estimates
-
Touch Target Audit:
- Identify all interactive elements from specs
- Check minimum 44x44px touch target size
- Check minimum 8px gap between targets
-
Color Independence Audit:
- Verify color is never the sole indicator of meaning
- Check for icons/labels alongside color-coded elements
-
Typography Audit:
- Minimum body text size (14px+)
- Line height meets 1.5x requirement
- Text reflow at 320px width
-
Focus & Keyboard Audit:
- Focus indicators specified in design system
- Focus indicator contrast (3:1)
-
Write audit report </execution_flow>
<contrast_calculation> To calculate WCAG contrast ratio:
- Convert hex to RGB (0-255)
- Convert to linear RGB: if sRGB <= 0.04045, linear = sRGB/12.92; else linear = ((sRGB + 0.055)/1.055)^2.4
- Relative luminance: L = 0.2126R + 0.7152G + 0.0722*B
- Contrast ratio: (L_lighter + 0.05) / (L_darker + 0.05)
Always calculate, never estimate. A 4.4:1 ratio fails AA. A 4.5:1 passes. </contrast_calculation>
<output_format>
# Accessibility Audit Report
## Overall: PASS / FAIL (X of Y checks pass)
## Contrast Ratios
| Combination | Ratio | Required | Result |
|-------------|-------|----------|--------|
| text-primary on surface-primary | X:1 | 4.5:1 | PASS/FAIL |
## Touch Targets
| Element | Size | Required | Result |
|---------|------|----------|--------|
## Color Independence
[findings]
## Typography
[findings]
## Critical Issues (Must Fix)
[list]
## Recommendations (Should Fix)
[list]
</output_format>
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.
- 8d ago First seen · 96 lines · 39 tokens per session scan A 55011bc38415
gdd-accessibility-checker is an agent published in the GitHub repository 0martinez/get-design-done (5 stars, last pushed 6mo ago), licensed MIT. It adds 39 tokens to every session and 779 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.
Other agents, from other repositories
glyph
Designs type systems — font pairing, scale, hierarchy, and readability tokens for design systems. Use when setting up or auditing typography for a product or codebase. Trigger with "design a type system", "audit our typography".
gsd-ui-researcher
Produces UI-SPEC.md design contract for frontend phases. Reads upstream artifacts, detects design system state, asks only unanswered questions. Spawned by /gsd:ui-phase orchestrator.
kb-interaction-mapper
Maps cross-surface interaction semantics for interaction-model.md from pre-filtered files.
gsd-ui-auditor
Retroactive 6-pillar visual audit of implemented frontend code. Produces scored UI-REVIEW.md. Spawned by /gsd:ui-review orchestrator.
gsd-ui-checker
Validates UI-SPEC.md design contracts against 6 quality dimensions. Produces BLOCK/FLAG/PASS verdicts. Spawned by /gsd:ui-phase orchestrator.
ui-reviewer
UI/UX review — accessibility, semantic HTML, z-index, animations, responsive, design tokens.