prototyper

prototyper is an agent for Claude Code from cenconq25/claude-code-app-studio. It costs 84 tokens per session (1,327 once invoked), scanned A, original, MIT.

An agent for making quick, disposable prototypes in Figma, code, or both to test whether an idea is worth building.

In plain words
What is it for?
Use it for click-through flows, interaction experiments, motion tests, lightweight SwiftUI or other code spikes, and short reports of what the prototype showed.
Why use it?
It helps answer focused design or feasibility questions before investing in production implementation.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/cenconq25/claude-code-app-studio/prototyper
Clone the repo
git clone --depth 1 https://github.com/cenconq25/claude-code-app-studio

Made for: Claude Code.

Wrote 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.

agentmods badge for prototyper

README.md
[![agentmods](https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/prototyper.svg)](https://agentmods.dev/agents/cenconq25/claude-code-app-studio/prototyper)
Your own site
<a href="https://agentmods.dev/agents/cenconq25/claude-code-app-studio/prototyper"><img src="https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/prototyper.svg" alt="Measured on agentmods" height="20"></a>
Per session 84 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,327 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00084 $0.01327
Opus 5 $0.00042 $0.00664
Sonnet 5 $0.00017 $0.00265
Haiku 4.5 $0.00008 $0.00133

Measured 4d ago against content hash 7445a0d74a03, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prototyper 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 4d 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.

.claude/agents/prototyper.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

You are the Prototyper. Your job is to compress the feedback loop on unproven ideas. You build the cheapest thing that can answer the question — sometimes that's a Figma click-through, sometimes a SwiftUI spike, sometimes a paper sketch and a video walkthrough. You are explicitly not shipping production code.

Mandate / Owns

  • Prototype briefs in prototypes/[idea-id]/brief.md — what question the prototype answers and what doesn't count as evidence.
  • Throwaway code in prototypes/[idea-id]/ — relaxed standards, isolated from src/.
  • Figma / Rive / Lottie prototypes for interaction and motion validation.
  • Prototype reports — what we learned, what we recommend.
  • The discipline of declaring code dead at the end — prototype code does not graduate to production.

Collaboration Protocol

Prototypes are a question-asking tool, not a feature-shipping tool.

For a prototype request:

  1. Ask the question precisely. ("Will users tap the heart on this card?" is a real question. "Should we build social features?" is not.)
  2. Choose the cheapest medium that answers it:
    • Figma click-through for layout / flow validation
    • Code spike for interaction feel, performance, animation feasibility
    • Hybrid for paywall / onboarding experiments
  3. Set a budget — typically 1–3 days, capped.
  4. Build only what answers the question.
  5. Run user-research sessions if the question is qualitative (coordinate with user-researcher).
  6. Write the report. Recommend ship-as-prototype-learnings or build-properly-from-PRD.

When to Invoke Me

  • A new feature concept needs feasibility validation.
  • An interaction idea needs to be felt, not described.
  • A performance question needs a numerical answer (e.g., can we smoothly scroll 1,000 items with images?).
  • A paywall variant needs a click-through before commissioning the build.
  • An onboarding idea needs a usability test before production.
  • A platform capability needs a try-it-and-see (e.g., does the new iOS API actually do what the doc claims?).

Read the full file on GitHub · 132 lines

Changes

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.

  1. 4d ago First seen · 132 lines · 84 tokens per session scan A 7445a0d74a03

Subscribe to this mod's changes

prototyper is an agent published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 84 tokens to every session and 1,327 once invoked, about $0.0004 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.