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 commands/ooiyeefei/ccc/turn-into-appgit clone --depth 1 https://github.com/ooiyeefei/cccWrote 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/commands/ooiyeefei/ccc/turn-into-app)<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>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 | $0.00027 | $0.01615 |
| Opus 5 | $0.00014 | $0.00807 |
| Sonnet 5 | $0.00005 | $0.00323 |
| Haiku 4.5 | $0.00003 | $0.00161 |
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.
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.
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.
- 5d ago First seen · 147 lines · 27 tokens per session scan A af7f2bfec88d
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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.