plan

plan is a skill for Claude Code from toss/apps-in-toss-harness. It costs 191 tokens per session (5,180 once invoked), scanned A, original, BSD-3-Clause.

A planning guide that turns a mini-app idea into a lightweight product plan. It can shape an idea, record requirements in a PRD (a short product requirements document), and map needed SDK areas, permissions, and registration terms.

In plain words
What is it for?
Use it to explore an idea, write a PRD, and identify the platform features, user permissions, and console conditions needed before launch.
Why use it?
It reduces uncertainty before development by clarifying what the app should do and what setup or approvals it may need. It does not create the project or register anything.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the ait plugin — 11 skills, 4 commands shipped together

Good fit Use it to explore an idea, write a PRD, and identify the platform features, user permissions, and console conditions needed before launch.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/toss/apps-in-toss-harness/plan
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.

Any agent
npx skills add toss/apps-in-toss-harness --skill plan
Clone the repo
git clone --depth 1 https://github.com/toss/apps-in-toss-harness

Made for: Claude Code.

Or install ait, the plugin that ships this one along with the rest of its 11 skills, 4 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 plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/toss/apps-in-toss-harness/plan/github.svg)](https://agentmods.dev/skills/toss/apps-in-toss-harness/plan)
Your own site
<a href="https://agentmods.dev/skills/toss/apps-in-toss-harness/plan"><img src="https://agentmods.dev/badge/skills/toss/apps-in-toss-harness/plan/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.

agentmods 80×15 button for plan

Your own site · 80×15
<a href="https://agentmods.dev/skills/toss/apps-in-toss-harness/plan"><img src="https://agentmods.dev/badge/skills/toss/apps-in-toss-harness/plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 191 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,180 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00191 $0.05180
Opus 5.5 $0.00076 $0.02072
Sonnet 5.5 $0.00038 $0.01036
Haiku 4.5 $0.00019 $0.00518

Measured 6d ago against content hash 4d72723d4dc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

plan 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.

packages/agent-plugin/shared/skills/plan/SKILL.md · 303 lines

How it starts

The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.

plan skill

목적

/ait:plan은 아이디어가 없는 상태에서도 시작할 수 있는 기획 station이다. 사용자가 서 있는 지점에 따라 세 구간을 이어서 진행한다:

  1. 아이데이션 — 아이디어가 막연할 때 발산 → 실현성 필터 → 후보 1개로 수렴
  2. PRD 디스커션 — 미니앱용 경량 PRD 9섹션을 대화로 채워 PRD.md로 남김
  3. 매핑 — 그 PRD에서 출시까지 필요한 세 가지를 뽑는다:
    • SDK 도메인 — 어떤 @apps-in-toss/web-framework API 그룹이 필요한가
    • 권한(permissions) — 그 도메인들이 런타임에 사용자에게 요청하는 권한
    • 약관(terms) — 등록·배포 시 콘솔이 게이트하는 워크스페이스 약관

요구사항이 이미 또렷하면 1·2를 건너뛰고 3만 해도 된다(아래 "입력"의 모드 판정).

전제: 미니앱은 토스 앱 WebView에서 도는 웹(React DOM) 앱이지 React Native 앱이 아니다 — 계획·아키텍처를 웹 스택 기준으로 세우고 RN/네이티브 화면 경로를 전제하지 않는다. 이 전제와 검수 존재가 아이데이션의 실현성 필터를 이룬다.

이 skill은 harness의 첫 station이다(station 7 "plan"은 개발 순서상 마지막에 추가됐지만, 흐름상으로는 scaffold 앞에 온다). 빈 디렉토리에서 /ait:new로 프로젝트를 만들기 전에, 무엇을 쓰게 될지 미리 지도를 그려서 나중에 register/deploy에서 약관 게이트에 막혀 되돌아오는 일을 줄인다.

이 skill은 기획만 한다. CLI를 호출하지 않고, 아무것도 등록하지 않으며, 프로젝트를 만들지 않는다. 쓰는 파일은 PRD.md 하나뿐이다(아래 "산출물"). hand-off는 /ait:new다.

도메인·권한·약관 이름을 지어내지 않는다. 확신이 없으면 docs MCP (searchDocumentation/getPage)로 문서를 조회하거나 사용자에게 되묻는다. 산출하는 계획·안내에 과장·홍보성 문구는 넣지 않는다.

입력

$ARGUMENTS를 읽고 모드를 먼저 판정한다. 모드가 실행 순서의 진입점을 정한다.

모드 판정 기준 진입
A. 아이데이션 인자 없음, 또는 "뭘 만들지 모르겠다"류 1단계부터
B. PRD 아이디어 한 줄은 있으나 화면·범위가 안 잡힘 3단계부터
C. 매핑 기능이 문장으로 나열될 만큼 또렷하거나 PRD.md가 이미 있음 5단계부터
  • 모드 C의 <요구사항> 예:

    • "사용자 위치 기반으로 주변 매장을 보여주고, 로그인하면 즐겨찾기를 저장한다"
    • "디지털 아이템을 인앱 결제로 판매하는 게임"
  • 인자 없이 호출되면 모드를 한 줄로 확인한다:

    만들고 싶은 미니앱이 정해져 있나요?
      - 아직 막연하다 → 아이디어를 같이 좁혀갑니다
      - 한 줄로는 있다 → PRD를 같이 채웁니다
      - 기능이 정해져 있다 → 그대로 알려주시면 SDK 도메인·권한·약관으로 정리합니다
    

모드 C에서도 도메인·약관 분기를 가르는 모호함이 있으면(결제가 토스페이 체크아웃인지 인앱 디지털 재화(IAP)인지, 로그인이 필요한지) 그 부분만 짧게 되묻는다. 과도한 인터뷰는 하지 않는다.

산출물

  • PRD.md — 모드 A·B를 탄 경우 현재 디렉토리에 쓴다. 형식은 references/prd-template.md의 9섹션 고정. 이미 파일이 있으면 덮어쓰지 않고 이어서 갱신할지 묻는다. 모드 C(요구사항이 이미 또렷함)에서는 사용자가 요청할 때만 쓴다.
  • 계획 블록 — 대화 출력. SDK 도메인·권한·약관 + 다음 station seam(8단계).

/ait:plan은 scaffold 전에 도는 station이라 PRD.md는 보통 프로젝트 디렉토리가 생기기 전 위치에 놓인다. /ait:new <app-name> 후 <app-name>/으로 옮겨 두면 이후 station에서 참조하기 쉽다 — 옮기는 것은 사용자 몫이고 이 skill이 파일을 이동시키지 않는다.

Read the full file on GitHub · 303 lines

Files

What ships with it

3 files 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.

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. 6d ago First seen · 303 lines · 191 tokens per session scan A 4d72723d4dc5

Subscribe to this mod's changes

plan 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 191 tokens to every session and 5,180 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-10-23.

Related

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…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 83 tokens