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 skills add modu-ai/moai-cowork --skill design-iteration-loopgit clone --depth 1 https://github.com/modu-ai/moai-coworkWrote 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/skills/modu-ai/moai-cowork/design-iteration-loop)<a href="https://agentmods.dev/skills/modu-ai/moai-cowork/design-iteration-loop"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/design-iteration-loop/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/skills/modu-ai/moai-cowork/design-iteration-loop"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/design-iteration-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00136 | $0.02470 |
| Opus 5 | $0.00068 | $0.01235 |
| Sonnet 5 | $0.00027 | $0.00494 |
| Haiku 4.5 | $0.00014 | $0.00247 |
Grade A, and why
design-iteration-loop 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.
How it starts
The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚠️ 개발 런타임 전용 — 이 스킬은 MoAI-ADK(Claude Code) 환경을 전제한다. Claude Cowork(Desktop)에서는
.moai/config의존으로 동작하지 않을 수 있다. Desktop 사용자는 자체 체크리스트 기반 QC(예:moai-story:story-webtoon-qc같은 자체 QC 경로)를 사용한다.
design-iteration-loop
Implements the Builder-Evaluator GAN loop for iterative design quality improvement. Absorbed from the retired v2.x design constitution Section 11 and Section 12 (per the design constitution absorption policy). Integrates Sprint Contract Protocol, 4-dimension scoring, stagnation detection, and Evaluator Leniency Prevention.
All loop parameters are read from .moai/config/sections/design.yaml. Do not hardcode thresholds.
Quick Reference
Loop Parameters (from design.yaml)
design.gan_loop:
max_iterations: 5 # Maximum Builder-Evaluator cycles
pass_threshold: 0.75 # Score >= this value to exit loop
escalation_after: 3 # Escalate to user after N iterations without passing
improvement_threshold: 0.05 # Minimum score delta per iteration
strict_mode: false # If true, each dimension must pass individually
sprint_contract:
enabled: true
required_harness_levels: [thorough]
optional_harness_levels: [standard]
artifact_dir: ".moai/sprints"
max_negotiation_rounds: 2
4-Dimension Scoring Weights
| Dimension | Weight | Description |
|---|---|---|
| Design Quality | 30% | Visual consistency, brand token compliance, WCAG AA |
| Originality | 25% | Not generic, not AI-slop, unique brand expression |
| Completeness | 25% | All BRIEF sections present, copy matches contract |
| Functionality | 20% | Responsive, accessible, all interactions work |
Overall score = weighted average of all four dimensions.
Pass condition: overall_score >= pass_threshold AND (if strict_mode: true) each dimension score >= pass_threshold.
Implementation Guide
GAN Loop Execution Flow
Phase 1: Sprint Contract (when required by harness level)
Required when harness_level == thorough.
Optional when harness_level == standard and user opts in.
Skipped when harness_level == minimal.
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 · 265 lines · 136 tokens per session scan A 911553ca95d9
design-iteration-loop is a skill published in the GitHub repository modu-ai/moai-cowork (298 stars, last pushed 6d ago), licensed Apache-2.0. It adds 136 tokens to every session and 2,470 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
excalidraw
Create visual presentations, slide decks, and explanatory diagrams in Excalidraw. Use when user asks to create a presentation, slide deck, visual explainer, pitch deck, comparison diagram, process flow, or any multi-slide visual content. Supports two output modes — generating .excalidraw JSON files OR injecting slides…
infographic-old
Basic infographic generator. Just tell me what you want and I'll make it.
carousel-builder
Build a Ben AI image-first carousel (Type B) from provided source content and export it as a PDF. Give it a newsletter, a YouTube transcript, a LinkedIn post, or a raw brief; it picks the slide count (3-10), writes the copy in Ben's voice, renders every slide with Higgsfield GPT Image 2, composites the real-logo brand…
design-system-creator
Produces a complete, Claude-Design-compatible design system folder for any brand, ready to upload to Claude Design's "Set up your design system" flow and use across every future asset (websites, landing pages, pitch decks, Instagram/LinkedIn carousels, infographics, emails, ads). Handles two paths: building a brand…
instant-ui
Build a BenAI-branded HTML page in the neo-brutalist instant-ui design language (cream background, near-black ink, 3px hard borders, 6px zero-blur shadows, a blue/green/amber gradient stripe, system font plus SF Mono, weight-900 headings). Use for any BenAI landing page, offer, sales, or pricing page, onboarding or…
infographic
Generate professional infographics using Nano Banana MCP (Gemini AI image generation). Follows a guided flow — analyze content, suggest visualizable concepts, propose visualization approaches, then generate on-brand images. USE THIS SKILL WHEN user says "create infographic", "make a visual", "design an infographic"…