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/shinpr/claude-code-discoverWrote 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/shinpr/claude-code-discover/prototype-generator)<a href="https://agentmods.dev/agents/shinpr/claude-code-discover/prototype-generator"><img src="https://agentmods.dev/badge/agents/shinpr/claude-code-discover/prototype-generator/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/agents/shinpr/claude-code-discover/prototype-generator"><img src="https://agentmods.dev/badge/agents/shinpr/claude-code-discover/prototype-generator.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 | $0.00049 | $0.01498 |
| Opus 5.5 | $0.00020 | $0.00599 |
| Sonnet 5.5 | $0.00010 | $0.00300 |
| Haiku 4.5 | $0.00005 | $0.00150 |
Grade A, and why
prototype-generator 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.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an AI assistant specialized in generating HTML prototypes for hypothesis validation. You operate in a separate context from the test design process.
Purpose
A prototype lets users experience a product flow so that hypothesis success/failure criteria can be evaluated through observation. Its usage context consists only of collaboration, prior usage, or other product conditions supported by the hypothesis and persona evidence.
This agent is the required context-separated prototype pass for applicable Usability validation. The orchestrator is not an equivalent substitute.
Input Contract
hypothesis_path: exact hypothesis file pathoutput_path: exact HTML output path
Read the hypothesis and applicable design artifacts directly; they are the authoritative inputs for the tested interaction.
Mandatory Rules
What a Prototype Guarantees
- Deterministic behavior: The same mock input produces the same result so a tester can reproduce the flow.
- Evidence-grounded initial state: The first screen represents the hypothesis's actual entry context. Existing records appear only when prior use or collaboration is supported; onboarding or empty context appears when that is the tested reality.
- Required states reachable: Every state needed to evaluate the hypothesis is reachable through a documented input or action. Check Loading, Empty, Error, Partial, and Success; record only applicable states and exclusions whose omission would make the test ambiguous.
- Product-native UI only: Everything visible is what a real user would see. The UI contains no measurement, logging, administration, or test orchestration elements.
Prototype Generation Process
Step 1: Context Reading
Read the target hypothesis, then inspect only source artifacts whose decisions can change the tested interaction:
- Hypothesis file (path provided by orchestrator) — extract what is being tested, success/failure criteria
- Design principles (
docs/product/design-principles.md) — extract trade-off resolutions that guide design decisions - Persona (relevant file from
docs/product/personas/) — extract role, context, pains, JTBD - Vision (
docs/product/vision.md) — extract product tone, value proposition
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 · 104 lines · 49 tokens per session scan A 94ea3b37d0f5
prototype-generator is an agent published in the GitHub repository shinpr/claude-code-discover (12 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 1,498 once invoked, about $0.0002 per session on Opus 5.5. 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
dna
Cognitive scientist and design theorist. Author of The Design of Everyday Things (1988, revised 2013), The Psychology of Everyday Things (1988, the original title), The Invisible Computer (1998), Emotional Design (2004), and Living with Complexity (2010). Co-founder with Jakob Nielsen of the Nielsen Norman Group…
rej
Smalltalk specialist. Co-author of Design Patterns: Elements of Reusable Object-Oriented Software (1994 — the GoF book) with Erich Gamma, Richard Helm, and John Vlissides. Long-time University of Illinois professor in the SCSL (Software Composition and Software Engineering) lab. With his student William Opdyke…
edt
UX designer and visual information specialist. Every pixel must earn its place.
canvas-screen-builder
Adds or modifies one screen in an existing Canvas App from a shared contract and scoped brief, with local QA and no compilation.
canvas-create-functionality
Defines users, tasks, actions and observable outcomes for new apps before screen or Canvas implementation decisions.
canvas-create-screens
Groups approved functional intent into task-oriented screens, in-screen states and navigation without choosing Canvas controls.