init-claude

init-claude is a skill for Claude Code, Codex from goddaehee/init-claude-plugin. It costs 158 tokens per session (5,417 once invoked), scanned A, original, MIT.

A documentation initializer for Claude Code projects that creates or improves project guidance files such as CLAUDE.md and AGENTS.md.

In plain words
What is it for?
Use it to analyze a project, draft or improve its agent documentation, and evaluate the drafts through repeated quality-review cycles.
Why use it?
It gives coding agents documented information about the project's technology, structure, rules, and working practices instead of leaving them to infer everything from the code.

Skill for Claude CodeCodex

Part of the init-claude plugin — 1 skill shipped together

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.

agentmods
npx agentmods add skills/goddaehee/init-claude-plugin/init-claude
Any agent
npx skills add goddaehee/init-claude-plugin --skill init-claude
Clone the repo
git clone --depth 1 https://github.com/goddaehee/init-claude-plugin

Made for: Claude Code, Codex.

Or install init-claude, the plugin that ships this one along with the rest of its 1 skill.

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 init-claude

README.md
[![agentmods](https://agentmods.dev/badge/skills/goddaehee/init-claude-plugin/init-claude.svg)](https://agentmods.dev/skills/goddaehee/init-claude-plugin/init-claude)
Your own site
<a href="https://agentmods.dev/skills/goddaehee/init-claude-plugin/init-claude"><img src="https://agentmods.dev/badge/skills/goddaehee/init-claude-plugin/init-claude.svg" alt="Measured on agentmods" height="20"></a>
Per session 158 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,417 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00158 $0.05417
Opus 5 $0.00079 $0.02708
Sonnet 5 $0.00032 $0.01083
Haiku 4.5 $0.00016 $0.00542

Measured 4d ago against content hash 4986a5d046ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init-claude 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 4d 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.

skills/init-claude/SKILL.md · 300 lines

How it starts

The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.

init-claude Skill

Multi-agent team으로 프로젝트를 분석하고 Claude Code 문서 초안을 생성/개선한다 (최종 확정은 사용자 검증 후). P4 관계: 이 스킬은 "자동 생성 금지" 원칙의 예외가 아니라, 검증 가능한 초안 생성 + 사용자 승인 워크플로우. 22개 원칙(references/guide-principles.md) 기준, 3-5회 적응형 PDCA 평가 루프로 9.0/10+ 달성.

vs deepinit: deepinit은 모든 디렉토리에 AGENTS.md 생성. init-claude는 루트 문서 품질 최적화.

실행 모드: standard (기본, 3에이전트 병렬) | lightweight (단일 에이전트, no-MCP, 소규모 프로젝트용)

즉시 실행 프로토콜

  1. PROJECT_PATH 확인 (인수 없으면 현재 디렉토리)
  2. 기술 스택 자동 감지 (아래 참조)
  3. Phase 1: Discovery — 3개 Agent tool 호출을 하나의 메시지에서 병렬 실행
  4. 3개 에이전트 완료 알림 수신 후 Discovery Report 통합
  5. Phase 2: Architect — 3계층 문서 초안 생성
  6. Phase 3: 3-5 적응형 PDCA — 매 라운드 3개 Agent tool 병렬 호출
  7. 최종 리포트 출력

기술 스택 자동 감지

Glob tool로 프로젝트 루트 파일을 검색하여 스택 판별:

  • package.json → Node.js/TypeScript (pnpm-workspace.yaml → monorepo)
  • build.gradle / pom.xml → Java/Kotlin
  • Cargo.toml → Rust
  • pyproject.toml / setup.py → Python
  • go.mod → Go

감지 결과를 모든 에이전트 프롬프트의 컨텍스트로 전달.

Language Policy

Default: 팀의 주 언어. 교차 도구(Copilot/Cursor) 사용 시 영어 권장. 코드 예시의 BAD/GOOD 주석은 항상 영어. Details: references/language-policy.md

문서 소유권 모델

채점 전에 소유권을 확인한다. 소유권이 명확해야 C3/C4/C5가 충돌하지 않는다.

파일 소유 범위 허용 내용
AGENTS.md trap 설명 + BAD/GOOD 유일한 trap 소스. 다른 파일에서 복사 금지
CLAUDE.md (root) 구조 + 포인터 trap은 AGENTS.md 참조만. 한줄 제약 요약 허용
.claude/CLAUDE.md 규칙 인덱스 rules 파일 목록 + 프로젝트 고유 규칙
.claude/rules/*.md 도메인별 action trap은 AGENTS.md #N 참조만. BAD/GOOD 복사 금지

7가지 평가 기준 + 채점 루브릭

# 기준 가중치
C1 Line Budget 2
C2 Non-discoverability 2
C3 Single Source of Truth 2
C4 Trap Reference Coverage 1
C5 Practical Completeness 2
C6 Guide Compliance 2
C7 Consistency 1

채점 보간 규칙: 앵커(10/8/5/0) 사이 소수점 점수 허용. 보간 기준: 앵커 조건 충족 여부 + 경미한 개선/결함 수. 예: C1이 148 lines면 10, 155 lines면 9 (8 앵커 충족 + 여유 있으므로 +1).

C1: Line Budget (w2)

wc -l CLAUDE.md AGENTS.md .claude/CLAUDE.md의 합계. (guide-principles의 "≤200 lines" 예산 기준)

  • 10: ≤150 lines (여유 있음)
  • 8: 151-200 lines (예산 내)
  • 5: 201-250 lines (초과)
  • 0: >250 lines

Read the full file on GitHub · 300 lines

Files

What ships with it

5 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. 4d ago First seen · 300 lines · 158 tokens per session scan A 4986a5d046ab

Subscribe to this mod's changes

init-claude is a skill published in the GitHub repository goddaehee/init-claude-plugin (2 stars, last pushed 5mo ago), licensed MIT. It adds 158 tokens to every session and 5,417 once invoked, about $0.0008 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

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

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 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