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/Fmarzochi/EGCWrote 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/commands/fmarzochi/egc/gan-design)<a href="https://agentmods.dev/commands/fmarzochi/egc/gan-design"><img src="https://agentmods.dev/badge/commands/fmarzochi/egc/gan-design/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.
<a href="https://agentmods.dev/commands/fmarzochi/egc/gan-design"><img src="https://agentmods.dev/badge/commands/fmarzochi/egc/gan-design.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00018 | $0.00392 |
| Opus 5.5 | $0.00007 | $0.00157 |
| Sonnet 5.5 | $0.00004 | $0.00078 |
| Haiku 4.5 | $0.00002 | $0.00039 |
Grade A, and why
gan-design 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 1mo 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.
This is a copy
92% identical to gan-design — 12 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Parse the following from $ARGUMENTS:
brief: the user's description of the design to create--max-iterations N: (optional, default 10) maximum design-evaluate cycles--pass-threshold N: (optional, default 7.5) weighted score to pass (higher default for design)
GAN-Style Design Harness
A two-agent loop (Generator + Evaluator) focused on frontend design quality. No planner: the brief IS the spec.
This mode emphasises rapid creative iteration on visual design quality.
Setup
- Create
gan-harness/directory - Write the brief directly as
gan-harness/spec.md - Write a design-focused
gan-harness/eval-rubric.mdwith extra weight on Design Quality and Originality
Design-Specific Eval Rubric
### Design Quality (weight: 0.35)
### Originality (weight: 0.30)
### Craft (weight: 0.25)
### Functionality (weight: 0.10)
Note: Originality weight is higher (0.30 vs 0.20) to push for creative breakthroughs. Functionality weight is lower since design mode focuses on visual quality.
Loop
Same as /project:gan-build Phase 2, but:
- Skip the planner
- Use the design-focused rubric
- Generator prompt emphasizes visual quality over feature completeness
- Evaluator prompt emphasizes "would this win a design award?" over "do all features work?"
Key Difference from gan-build
The Generator is told: "Your PRIMARY goal is visual excellence. A stunning half-finished app beats a functional ugly one. Push for creative leaps: unusual layouts, custom animations, distinctive color work."
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.
- 1mo ago First seen · 40 lines · 18 tokens per session scan A cf80ef426942
gan-design is a command published in the GitHub repository Fmarzochi/EGC (67 stars, last pushed today), licensed Apache-2.0. It adds 18 tokens to every session and 392 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 92% identical to gan-design, differing in 12 lines, and is treated as a copy.
Other commands, from other repositories
ux-image-to-code
Take a design reference image (PNG/JPG/WebP), extract its dominant palette + canvas polarity + type signal via pure Pillow CV, match the result against the v2 palettes/styles manifests, and run the recommender on the synthetic brief. Returns the closest palette, the closest style, and a full recommended design system…
extract-foundations-from-screens
Extract canonical foundations docs (color, typography, spacing, radii) from a batch of existing SCREENSPECs. Re-runs only add new tokens and route conflicts to a Review queue. Use when SCREENSPECs already document raw values and need converging into role tokens. Do not use when foundations are already curated and…
design-thinking
Guide human-centered design processes using empathy-driven methodologies. This workflow walks through the design thinking phases - Empathize, Define, Ideate, Prototype, and Test - to create solutions deeply rooted in user needs.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.