turn-into-app

turn-into-app is a command for coding agents from ooiyeefei/ccc. It costs 27 tokens per session (1,615 once invoked), scanned A, original, MIT.

A command that turns a completed survey design into a working web-app starting point. It supports several web-development setups, including hosted storage or local storage.

In plain words
What is it for?
Use it to generate a runnable survey app from a Markdown design or another finalized survey specification.
Why use it?
It removes the need to build the initial survey screens, data handling, and project structure from scratch after the questions are finalized.

Command

Part of the rethink-surveys plugin — 1 skill, 3 commands shipped together

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 commands/ooiyeefei/ccc/turn-into-app
Clone the repo
git clone --depth 1 https://github.com/ooiyeefei/ccc

Or install rethink-surveys, the plugin that ships this one along with the rest of its 1 skill, 3 commands.

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 turn-into-app

README.md
[![agentmods](https://agentmods.dev/badge/commands/ooiyeefei/ccc/turn-into-app.svg)](https://agentmods.dev/commands/ooiyeefei/ccc/turn-into-app)
Your own site
<a href="https://agentmods.dev/commands/ooiyeefei/ccc/turn-into-app"><img src="https://agentmods.dev/badge/commands/ooiyeefei/ccc/turn-into-app.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,615 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 $0.00027 $0.01615
Opus 5 $0.00014 $0.00807
Sonnet 5 $0.00005 $0.00323
Haiku 4.5 $0.00003 $0.00161

Measured 5d ago against content hash af7f2bfec88d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

turn-into-app 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 5d 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.

plugins/rethink-surveys/commands/turn-into-app.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Turn Survey Into App

Take a finalized survey design (output from /design-survey or a Markdown spec the user provides) and emit a working app scaffold the user can npm install && npm run dev immediately.

Usage

/turn-into-app

Or with a path to a design doc:

/turn-into-app from survey-design-2026-04-29.md

Process

Always invoke the rethink-surveys skill first. Then load references/multimodal-ux.md for stack and code-pattern guidance.

Step 1 — Confirm the design is final

Ask if not obvious: "Is this the final question set? If you're still iterating on questions, run /design-survey first — it's harder to fix questions after the app exists."

Step 2 — Stack selection

Ask the user to pick:

Stack Best for
TanStack Start + Supabase Production-grade, voice support, multilingual, mobile web. (Proxymate stack — battle-tested.)
Next.js + Supabase Team already on Next.js. Roughly equivalent capability.
Static HTML + Supabase Edge Functions One-off survey, no team, minimal infra.
Reboot.ai AI-interviewer is the primary modality.

Default if user hasn't picked: TanStack Start + Supabase (Proxymate-style).

Step 3 — Storage selection

Ask:

Storage When
Supabase (managed Postgres + Storage + Edge Functions) Production. Standard.
Local JSON file + simple express server Hackathon prototype, no online deps.
Bring your own DB User has an existing schema/host they want to write into.

Default: Supabase.

Step 4 — Voice + AI mode

If the design includes voice or AI-interviewer mode, ask for relevant credentials:

  • Deepgram API key for transcription (voice). Free tier covers $200, no card needed.
  • Anthropic API key for AI-interviewer. Use Claude Haiku 4.5 for extraction, Claude Sonnet 4.6 for the conversation loop.

Don't bake credentials into code; emit env-var references and a .env.example file.

Read the full file on GitHub · 147 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. 5d ago First seen · 147 lines · 27 tokens per session scan A af7f2bfec88d

Subscribe to this mod's changes

turn-into-app is a command published in the GitHub repository ooiyeefei/ccc (483 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 1,615 once invoked, about $0.0001 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.