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 skills add cenconq25/claude-code-app-studio --skill prototypegit clone --depth 1 https://github.com/cenconq25/claude-code-app-studioWrote 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/skills/cenconq25/claude-code-app-studio/prototype)<a href="https://agentmods.dev/skills/cenconq25/claude-code-app-studio/prototype"><img src="https://agentmods.dev/badge/skills/cenconq25/claude-code-app-studio/prototype/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/skills/cenconq25/claude-code-app-studio/prototype"><img src="https://agentmods.dev/badge/skills/cenconq25/claude-code-app-studio/prototype.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 | $0.00057 | $0.02229 |
| Opus 5 | $0.00028 | $0.01115 |
| Sonnet 5 | $0.00011 | $0.00446 |
| Haiku 4.5 | $0.00006 | $0.00223 |
Grade A, and why
prototype 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 6d 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prototype
A prototype is a question the codebase poses to reality. It is explicitly not production code: no tests, no review, no PRD, no ADR, no manifest pinning. The output is a one-page report that tells the team whether the assumption holds — and whatever was learned along the way.
Outputs:
prototypes/<name>/— the prototype's code (intentionally walled off fromsrc/)prototypes/<name>/REPORT.md— what was built, what was learned, what to do with the learning
Purpose / When to Run
Run when:
- The concept doc's "Riskiest Assumption" needs validation before architecture commitment
- A novel mechanic or framework feature needs to be tried before adding to a PRD
- A perf concern needs a quick measurement before locking budgets
- A library / SDK needs vetting before an ADR commits to it
Do not run for:
- Features that already have PRDs and ADRs (use
/dev-storyin the second skill set) - Bug investigations (use the bug-fix workflow in the second skill set)
- Refactors of existing code (those are real stories)
Inputs
- Assumption to test (required, free text)
- Optional:
design/concept.mdSection 8 (Riskiest Assumption) for context
Outputs
prototypes/<name>/— codeprototypes/<name>/REPORT.md
Phase 1: Frame the Question
If no argument was passed, ask:
- Prompt: "What assumption are you testing?"
- Free text — capture as kebab-case for the prototype name.
The framing matters. Use AskUserQuestion:
- Prompt: "Re-frame the assumption as a yes/no question. Pick or write:"
- Options: derived from the input — e.g., for "people will tap during a session":
Q: Can users complete the core action in <3 seconds while doing something else?Q: Does the gesture work mid-activity without misfires?Custom (free text)
The question becomes the prototype's success criterion.
Phase 2: Define Success / Fail Criteria
Use AskUserQuestion:
- "What evidence would prove yes?" — free text
- "What evidence would prove no?" — free text
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.
- 6d ago First seen · 264 lines · 57 tokens per session scan A 24e956f106f7
prototype is a skill published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 57 tokens to every session and 2,229 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…