Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add toss/apps-in-toss-harness/plugin install aitWrote 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/toss/apps-in-toss-harness/new-miniapp)<a href="https://agentmods.dev/skills/toss/apps-in-toss-harness/new-miniapp"><img src="https://agentmods.dev/badge/skills/toss/apps-in-toss-harness/new-miniapp/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/toss/apps-in-toss-harness/new-miniapp"><img src="https://agentmods.dev/badge/skills/toss/apps-in-toss-harness/new-miniapp.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 | $0.00318 | $0.24118 |
| Opus 5.5 | $0.00127 | $0.09647 |
| Sonnet 5.5 | $0.00064 | $0.04824 |
| Haiku 4.5 | $0.00032 | $0.02412 |
Grade A, and why
new-miniapp scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
어느 인접 버전이 미러에 실재하는지는 후보 버전의 tarball URL을 `curl -I`로 How it starts
The opening of the file, as written. The whole thing — 1,123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
new-miniapp skill
목적
이 문서는 로드된 즉시 현재 턴에서 네가 직접 실행하는 지시문이다 — skill은 백그라운드에서 실행되지 않으며, 기다릴 완료 신호도 없다. 아래 Step을 지금 순서대로 직접 수행한다. ("skill이 실행 중이니 완료를 기다리겠다"는 판단은 오독이다 — 실측에서 약한 모델이 이 오독으로 scaffold를 시작조차 못 했다.)
/ait:new <app-name> 한 번으로 새 앱인토스 미니앱 프로젝트를 빈 상태에서
시작할 수 있게 한다. 사용자가 묻기 전에 답해야 할 것:
- scaffold는
toss/create-ait-app(공식 스캐폴더 CLI)을 비대화형(--inline)으로 호출해 만든다 — 버전은 항상@latest(명시 핀 없음, maintainer 결정 2026-08-10). 템플릿은 번들된 create-vite 프리셋에 위임한다. 스택(프레임워크·언어)은 사용자가 정한다 — 말하지 않았으면 기본react-ts, 말했으면--list-templates출력에서 그 스택의 프리셋을 고른다(아래 "스택 선택").--tds(TDS 컴포넌트 홈 + provider, React 18 전용,--template과 동시 지정 불가 — 아래 참조),--sample iap,iaa(인앱결제·인앱광고 예제)를 그대로 쓸 수 있다. @apps-in-toss/devtools배선과 번들 설정은 CLI가 한다 — create-ait-app이 scaffold 직후ait init을 호출해 devtools를 devDependency로 넣고 번들러 설정에 unplugin을 주입하며,apps-in-toss.config.ts와build/build:vite/deploy스크립트도,.gitignore의*.ait줄도 같은 실행이 만든다(실측 2026-08-07,[email protected]—*.ait줄은@apps-in-toss/cli3.1.1 dist 실측 2026-09-07, 0.2.8 재현 2026-10-14에서도 동일). 순정 create-vite 템플릿에는 SDK mock이 없어 브라우저에서 SDK 호출이 실패하지만(샘플 코드가 "샌드박스앱/토스앱에서 실행해주세요" alert를 띄운다) 이 배선 덕에 토스 앱 없이npm run dev로 바로 개발할 수 있다.ait init은 실패해도 CLI가 "완료"로 끝내므로 형상 가드(Step 3)가 실재를, Step 4가 배선을 확인하고 폴백한다.- 이건 토스 앱 WebView에서 도는 웹(DOM) 미니앱이지 React Native 앱이 아니다.
RN 네이티브 컴포넌트나
react-nativeimport를 쓰지 않는다(설치 시 SDK가 RN을 peer로 선언해 뜨는unmet peer react-native경고는 무시해도 된다). - 디자인 가이드도 함께 심는다(Step 5-B) — 토큰·기본 CSS·아이콘 6종·
docs/design-guide.md와 캐리어 문서(AGENTS.md·CLAUDE.md), 이모지 서체 Tossface가 들어간다. 나중에 어떤 세션이 화면을 만들어도 같은 기준(글자 크기 하한·터치 44px·하단 CTA safe area)을 따르게 하려는 것이다.--no-design-guide(전체)·--no-tossface(서체만)로 뺀다. - 다음 단계(
npm run dev→ 코드 수정 →/ait:design→npm run build(프로젝트build스크립트 — 끝이ait build)로 번들 생성 → console MCP 도구로 등록·업로드)가 명확히 안내된다.
이 skill은 **scaffold 호출 + 후처리(설치 상태 확인 · 형상 가드 · devtools 배선
확인/폴백 · .gitignore 보강(*.ait·실패 흔적 파일) · 디자인 가이드 주입)**만
담당한다. 콘솔 등록·번들 업로드는 console MCP 도구(miniapp_create/bundle_upload/
bundle_upload_complete)의 책임 — 여기서 자동 호출하지 않는다. 생성되는
README/UI/주석에 과장·홍보성 문구를 넣지 않는다.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 1,123 lines · 318 tokens per session scan A fae09882ddf0
new-miniapp is a skill published in the GitHub repository toss/apps-in-toss-harness (186 stars, last pushed 3d ago), licensed BSD-3-Clause. It adds 318 tokens to every session and 24,118 once invoked, about $0.0013 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-23.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…