launch

launch is a skill for Claude Code from toss/apps-in-toss-harness. It costs 204 tokens per session (3,659 once invoked), scanned A, original, BSD-3-Clause.

A pre-release checker and rejection-response guide for an Apps in Toss mini-app. It compares the project with the official app review rules, where review means checking whether an app may be released, not reviewing source code.

In plain words
What is it for?
Use it to check an app before review, prepare a review request, or respond to a rejection. It can inspect SDK versions, user identification, and features that require special setup.
Why use it?
It helps find release blockers before submitting the app and gives a code-based way to investigate review rejections. It avoids guessing when the cause cannot be found in the project.

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 check an app before review, prepare a review request, or respond to a rejection. It can inspect SDK versions, user identification, and features that require special setup.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/toss/apps-in-toss-harness/launch"><img src="https://agentmods.dev/badge/skills/toss/apps-in-toss-harness/launch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 204 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,659 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 $0.00204 $0.03659
Opus 5.5 $0.00082 $0.01464
Sonnet 5.5 $0.00041 $0.00732
Haiku 4.5 $0.00020 $0.00366

Measured 6d ago against content hash 1face63220c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

launch 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/launch-scan.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/launch/SKILL.md · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

launch skill

목적

검수에 넣기 전 점검과 반려 뒤 대응을 맡는다. 검수 기준 문장은 docs MCP로 읽는 개발자센터 문서가 정본이다. 이 skill은 그 문장을 코드와 맞춰 보는 순서, 코드 스캔, 원인을 코드에서 못 찾았을 때 고치지 않고 멈추는 지점을 더한다. 화면 수정은 /ait:design, 문구는 /ait:ux-writing, 폰 확인은 /ait:test-on-device, 기획은 /ait:plan이 맡는다.

판단 규약

  1. 작업 디렉터리부터 읽는다. 읽기 전에 "비어 있다", "소스가 없다"고 말하지 않는다.
  2. 판정 근거는 docs MCP getPage 원문이다. 검색 결과 조각이나 askQuestion 요약으로 판정하지 않는다.
  3. 설치된 SDK부터 본다(web-framework 버전, 설정 파일은 3.x apps-in-toss.config.ts·2.x granite.config.ts). 설치된 .d.ts에 없는 키나 API는 권하지 않고, 2.x용 문단을 3.x에 쓰지 않는다. Unity나 엔진 프로젝트는 Packages/manifest.json의 SDK 항목과 패키지 안 문서로 버전과 API를 확인한다. 스택을 가정하지 말고 프로젝트의 package.json scripts·설정 파일·README에서 읽는다. 모호하면 사용자에게 묻는다.
  4. 쓰지 않는 기능의 항목은 해당 없음이다. '(선택 사항)' 항목, '~하는 경우' 항목, 기능 절(토스 로그인, 인앱 결제, 토스페이, 인앱 광고, 웹보드 게임)이 여기에 든다. '사용자 식별키 발급' 절은 조건 없이 공통 절 사이에 있으니 모든 앱에 적용한다.
  5. 사용자 식별은 두 가지를 본다. 앱이 SDK 식별키 API로 값을 받아 저장하는지(API 이름은 설치된 .d.ts와 docs로 확인한다). 서버가 사용자를 확인해야 하면 클라이언트가 보낸 식별키를 그대로 믿지 않고 인증 코드 교환으로 받는지. 설치된 SDK에 인증 코드 API가 없으면 필요한 버전만 알린다. 앱 안의 사용자별 데이터만 다루면 발급과 저장으로 충분하다. 문서는 lookup-map의 사용자 식별 행이다.
  6. 스캔 출력은 후보다. 파일을 열어 확인한 것만 보고한다.
  7. 도구는 한 턴에 묶어 부른다. 턴이 하나 늘 때마다 앞의 내용을 전부 다시 읽는다. 파일은 Bash 한 번으로 함께 읽고, 체크리스트 밖 문서는 판정에 꼭 필요한 것만 2쪽까지 읽는다.

실행 순서

0. 범위

  • 반려 사유가 함께 왔으면 1 다음 4로 간다. 검수 요청을 원하면 바로 5로 간다. 그 밖에는 1~3을 하고 6으로 보고한다.
  • 게임인지 비게임인지 정한다. 코드로 알 수 없으면 한 번 묻는다.

1. 첫 턴: 프로젝트 읽기와 스캔

아래 둘을 같은 턴에 부른다.

  • ToolSearch 한 번으로 docs MCP getPage를 불러온다. 콘솔을 읽을 거면 3의 도구도 같은 호출에 넣는다.
  • Bash 한 번. base directory는 이 skill을 로드할 때 표시된 문자열을 그대로 쓴다. 반려 대응이면 사유에 나온 낱말(API 이름, 문자열, 설정 키)을 찾는 grep을 덧붙인다.
ls -la; cat package.json apps-in-toss.config.ts granite.config.ts Packages/manifest.json 2>/dev/null
grep '"version"' node_modules/@apps-in-toss/web-framework/package.json 2>/dev/null
find . \( -name node_modules -o -name .git -o -name dist -o -name build -o -name Library -o -name Temp \) -prune -o -type f -print | head -100
bash "<이 skill의 base directory>/scripts/launch-scan.sh" .

Read the full file on GitHub · 217 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 · 217 lines · 204 tokens per session scan A 1face63220c2

Subscribe to this mod's changes

launch 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 204 tokens to every session and 3,659 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

vendor-review

Evaluate a vendor — cost analysis, risk assessment, and recommendation. Use when reviewing a new vendor proposal, deciding whether to renew or replace a contract, comparing two vendors side-by-side, or building a TCO breakdown and negotiation points before procurement sign-off.

anthropics/knowledge-work-plugins · 54 tokens

entity-compliance

Entity compliance tracker — initialize, report upcoming deadlines, update status, run health audit, export to CSV. Maintains a compliance-tracker.yaml built from the entity table, calculates filing deadlines by entity and jurisdiction, and surfaces what's due in the next 30/60/90 days. Use when user says "entity…

anthropics/claude-for-legal · 98 tokens

portfolio

Track the IP portfolio — registrations, renewals, maintenance fees, and use declarations. Use when checking what's renewing, adding or updating an asset, recording a maintenance filing, or auditing the register for gaps, lapses, and use-in-commerce questions. Receives handoffs from prosecution and clearance work.

anthropics/claude-for-legal · 62 tokens

launch-review

Full launch review against your framework and risk calibration. Use when the user says "review this launch", "legal review for [feature]", "can we ship this", "what are the legal issues with [product]", or references a launch tracker ticket or PRD that needs a category-by-category review memo.

anthropics/claude-for-legal · 64 tokens

gap-surfacer

Reference: shared gap- and comment-tracker framework backing /regulatory-legal:gaps and /regulatory-legal:comments. Tracks open policy gaps with remediation status, ingests gaps from policy-diff, surfaces what's open and aging, routes to owners, and notifies gap owners via Slack with per-send confirmation. Loaded by…

anthropics/claude-for-legal · 82 tokens

client-intake

Structured intake — practice-area templates, cross-area issue spotting, conflict flags, and triage classification. Produces a formatted case summary the student analyzes and the professor reviews. Does NOT decide case acceptance. Use when starting a new client intake, running an intake interview, or writing up a new…

anthropics/claude-for-legal · 65 tokens