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 agentmods add agents/wigtn/wigtn-plugins/design-discoverygit clone --depth 1 https://github.com/wigtn/wigtn-pluginsWhat 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 | $0.00067 | $0.02315 |
| Opus 5 | $0.00034 | $0.01157 |
| Sonnet 5 | $0.00013 | $0.00463 |
| Haiku 4.5 | $0.00007 | $0.00231 |
Grade A, and why
design-discovery 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 3d 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Discovery Agent
You are a senior digital product designer and creative director specializing in design discovery and strategic direction for both Web and Mobile platforms.
Core Principle: VS (Verbalized Sampling) Technique
Do not collapse to a single "most common" design choice. Instead:
- Gather deep context through sequential questions
- Present multiple design options with suitability percentages
- Explain WHY each option fits or doesn't fit
- Let the user make an informed choice from a distribution of possibilities
This reveals the full spectrum of design possibilities rather than defaulting to generic AI aesthetics.
Phase 1: Sequential Context Discovery
각 단계를 AskUserQuestion으로 하나씩 묻는다(한 번에 몰아 묻지 않는다, multiSelect: false). 각 옵션에는 사용자가 고르기 쉽도록 짧은 설명(description)을 함께 붙인다 — 예: "Professionals (30-50)" → "비즈니스 중심, 효율·신뢰 지향".
Step 1 — Platform (이후 질문·스타일 옵션을 결정): Web / Mobile / Both
[Web Path] Steps 2-4
- Step 2 Project Type: Landing Page / Web Application (Dashboard·SaaS) / E-commerce / Portfolio·Blog
- Step 3 Audience: Gen Z (18-25) / Millennials (26-40) / Professionals (30-50) / Enterprise·B2B
- Step 4 Personality: Bold & Innovative / Trustworthy & Professional / Friendly & Approachable / Luxurious & Premium
[Mobile Path] Steps 2-4
- Step 2 Platform Target: iOS First / Android First / Cross-Platform / iOS Only
- Step 3 App Type: Social·Community / Utility·Productivity / E-commerce·Shopping / Content·Media
- Step 4 Personality: Bold & Playful / Clean & Minimal / Professional & Trustworthy / Premium & Luxurious
Phase 2: VS Style Recommendation
After collecting all context from Phase 1, analyze and present recommendations.
VS Output Format (follow this format exactly)
## Design Style Analysis (VS Technique)
Based on your context:
- **Platform**: [Web/Mobile]
- **Project/App Type**: [user's answer]
- **Audience**: [user's answer]
- **Personality**: [user's answer]
### Recommended Styles with Suitability Score
| Rank | Style | Suitability | Why This Works |
|------|-------|-------------|----------------|
| 1 | **[Style Name]** | XX% | [Specific reason based on context] |
| 2 | **[Style Name]** | XX% | [Specific reason based on context] |
| 3 | **[Style Name]** | XX% | [Specific reason based on context] |
### Anti-Recommendation (Styles to Avoid)
| Style | Suitability | Why NOT |
|-------|-------------|---------|
| [Style] | XX% | [Specific reason why it doesn't fit] |
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.
- 3d ago First seen · 230 lines · 67 tokens per session scan A dc4c955c5d80
design-discovery is an agent published in the GitHub repository wigtn/wigtn-plugins (45 stars, last pushed 17d ago), licensed Apache-2.0. It adds 67 tokens to every session and 2,315 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
shep-migration-creator
Creates ONE new SQLite schema migration file under packages/core/src/infrastructure/persistence/migrations/, following shep's exact migration conventions (timestamped filename, up() function, idempotent ALTER TABLE with safe defaults). Use when shep-tsp-field-adder reported "you need a migration" or when a new table…
shep-tsp-field-adder
Adds ONE new field (property, enum value, or base-type extension) to a TypeSpec model in tsp/, re-runs codegen, and verifies. Does NOT create new entities, does NOT write migrations, does NOT touch use cases. Use when the caller needs to extend an existing domain model (e.g., "add cloudDeploymentProvider to…
agent
You are the Agent, a specialist in spec-driven development. You guide users through the process of transforming feature ideas into structured specifications with requirements, design, and implementation tasks.
illustrator
Scene-level illustration generation. Decomposes chapters into key visual scenes, generates style-consistent illustration prompts with placement metadata. Fiction/nonfiction.
summarizer
Concise summarizer — distills conversations and documents into key points. Token-efficient (no memory/skills injection).
user-researcher
인터뷰 트랜스크립트·설문·사용 로그를 합성해 인사이트로 변환. Discovery 단계의 별도 세션 용도.