zzon-doc: Instructions file for Claude Code

CLAUDE.md

zzon-doc CLAUDE.md is an instructions file for Claude Code from HOKlNG/zzon-doc. It costs 14,674 tokens per session, scanned A, original, MIT.

A set of instructions for the zzon-doc Claude Code plugin marketplace, covering project handovers, naming, structure, and documentation tools. Its tools can turn code into a standalone HTML file containing architecture diagrams, sequence diagrams, and a project wiki.

In plain words
What is it for?
Use it to create architecture or sequence diagrams, build a question-based project wiki, document Terraform infrastructure, and hand over work between Claude sessions.
Why use it?
It helps maintain the repository’s naming and structural rules and provides a consistent way to document how a codebase works.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions .claude-plugin; mentions CLAUDE.md; mentions Claude Code.

This is HOKlNG/zzon-doc's own configuration. It tells Claude Code how to work on zzon-doc itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything zzon-doc configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is cd ../...

Reuse

Borrowing it

Nothing to install: this file belongs to HOKlNG/zzon-doc. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/HOKlNG/zzon-doc/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/HOKlNG/zzon-doc

Made for: Claude Code.

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 zzon-doc CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hoklng/zzon-doc/claude-md/github.svg)](https://agentmods.dev/instructions/hoklng/zzon-doc/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/hoklng/zzon-doc/claude-md"><img src="https://agentmods.dev/badge/instructions/hoklng/zzon-doc/claude-md/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 zzon-doc CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/hoklng/zzon-doc/claude-md"><img src="https://agentmods.dev/badge/instructions/hoklng/zzon-doc/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14,674 This file is loaded in full into every session.
When invoked 14,674 The same file — it is already loaded in full.
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 $0.14674 $0.14674
Opus 5.5 $0.05870 $0.05870
Sonnet 5.5 $0.02935 $0.02935
Haiku 4.5 $0.01467 $0.01467

Measured 4d ago against content hash fb6d3940dbe1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

zzon-doc CLAUDE.md 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.

CLAUDE.md · 261 lines

How it starts

The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.

zzon-doc — 인수인계 (CLAUDE 세션용)

이 레포는 Claude Code 플러그인 마켓플레이스다. 코드를 분석해 인터랙티브 아키텍처·시퀀스 다이어그램과 프로젝트 문서 위키를 의존성 0짜리 단일 .html(산출물 기준)로 만들어 주는 스킬 4종을 담는다.

네이밍 (혼동 주의)

층 이름 비고
마켓플레이스 zzon .claude-plugin/marketplace.json (레포 루트)
플러그인(우산) zzon-doc zzon-doc/.claude-plugin/plugin.json
스킬 1 zzon-doc → /zzon-doc:zzon-doc (플러그인 스킬은 플러그인명:스킬명 네임스페이스). 다이어그램 메인(v0.9) — 선택 기준으로 뷰 13종·등급을 고르고, 시퀀스·Terraform은 형제 스킬 절차로 넘기며, 재진입 시 근거 대조로 갱신
스킬 2 zzon-wiki → /zzon-doc:zzon-wiki. 프로젝트 문서 위키 (질문 기반 채움 + 다이어그램 임베드)
스킬 3 zzon-seq → /zzon-doc:zzon-seq. 시퀀스 다이어그램 (액터 간 시간축 상호작용, kind:"sequence")
스킬 4 terra-form → /zzon-doc:terra-form. Terraform 클라우드 인프라 (*.tf → 엔진 DSL, AWS 공식 아이콘 838종)

설치: /plugin marketplace add <owner>/<repo> → /plugin install zzon-doc@zzon 호출: /zzon-doc:zzon-doc <대상> / /zzon-doc:zzon-wiki. 자연어 요청으로도 자동 동작.

구조

plugins-zzon-doc/
├── .claude-plugin/marketplace.json     # name: zzon, plugins:[zzon-doc → ./zzon-doc]
├── README.md / README.en.md
└── zzon-doc/
    ├── .claude-plugin/plugin.json      # name: zzon-doc
    ├── README.md
    ├── engine/                         # 내장 TS 다이어그램 엔진 (v0.8.1 통합 — 구조·데이터 다이어그램의 정본 렌더러)
    │   ├── CLAUDE.md / DESIGN.md       # 엔진 인수인계·설계 근거 — 레이아웃/라우팅 수정 전 필독 (§12 기각 대안 재제안 금지)
    │   ├── src/                        # TS DSL·ELK 자동배치·libavoid 직교 라우팅·렌더러·CLI (bun+TS)
    │   ├── examples/*.ts               # DSL API 정본 11종 (AWS 4 + msa/erd/flow + v0.9 표기 4: state/flowchart/screen-flow/domain-model)
    │   ├── src/quality/metrics.ts      # 등급별 품질 게이트(교차·꺾임·라벨 가림·색 그룹·흐름 방향·예산) — `bun ia check`
    │   ├── src/render/shapes.ts        # 표기 모양(상태·시작·종료·선택·처리·판단·터미널·화면·클래스·모듈)
    │   ├── src/model/semantics.ts      # 표기 의미 검사(상태 도달성·판단 라벨·상속 순환)
    │   ├── tests/                      # 불변식 검사(invariants.ts) 등 — bun test
    │   └── package.json / bun.lock     # elkjs·libavoid-js·resvg 등 (node_modules는 gitignore, bun install 1회)
    ├── skills/zzon-doc/                # 스킬 1 — 다이어그램 메인 (v0.9)
    │   ├── SKILL.md                    # 메인 허브: 분기(재진입 --status) → scan 신호 → 뷰·등급(rubric) → 위임(seq/terra-form)·views 저작 → bun ia check → build-docs → 보고(충실도 장부)
    │   ├── references/
    │   │   ├── selection-rubric.md     # ★ 선택 기준 정본 — 뷰(관심사 점수)·등급(T1/T2/T3)·축소 사다리·게이트 수치·근거 추적
    │   │   ├── views/*.md              # 뷰별 작도 문법 11종(엔진 DSL 용어) + README(공통 계약)
    │   │   ├── writing-style.md        # 독자용 문장 규칙 정본 — 필드명·내부 코드·번호·기호 나열 금지 (스킬 4종이 참조)
    │   │   ├── document-types.md       # (이전됨 안내) → selection-rubric + views
    │   │   ├── diagram-spec.md         # (레거시) DiagramSpec 스펙 + 레이아웃 가이드
    │   │   ├── viewer-frame-contract.md# 뷰어 프레임 계약 v1 (payload/adapter/셸 프로토콜/glyph/드릴다운)
    │   │   └── sample-*.json           # (레거시) DiagramSpec 모범 답안 14종 — 변환 내장으로 여전히 렌더됨
    │   └── scripts/
    │       ├── build-docs.mjs          # 여러 스펙 → 통합 문서 index.html (기본: 엔진 CLI(bun), sequence→render-seq, 폴백: legacy / wiki.json 있으면 index 양보) · --status(근거 대조) · --stamp · 게이트 수집
    │       ├── scan.mjs                # 코드 사실 스캐너(선택 기준 입력) — IaC·배포 단위·테이블·라우트·큐·상태·화면·에이전트·모듈
    │       ├── scan-deps.mjs           # 모듈 의존성 기계 추출 → DSL 생성(JS/TS·Python·Go·JVM, 순환·공용 모듈·추이 간선)
    │       ├── sources-lock.mjs        # diagrams.lock.json — 장별 근거 파일 해시·git 커밋·scan 요약(갱신 판정)
    │       ├── engine-cli.mjs          # bun 해석(Windows npm 셤 포함) + 엔진 호출 타임아웃 + fontFaceCss(셸용 Pretendard 서브셋)
    │       ├── design-tokens.mjs       # ★ 산출물 전체 디자인 토큰 정본 — 색(zinc)·글꼴·모서리·컨트롤 높이·폭 구간(서랍 960/휴대폰 640)
    │       ├── render.mjs              # (레거시 폴백) DiagramSpec JSON → 단일 .html — ZZON_LEGACY_RENDER=1·renderer:"legacy"·bun 부재 시
    │       ├── viewer-frame.js         # 공용 뷰어 프레임 (+ viewer-frame.test.mjs)
    │       ├── parity-check.mjs        # 레거시 vs 엔진 프레임 기능 패리티 게이트
    │       └── layout-lint.mjs         # (레거시 저작용) 배치 검사 — 엔진 경로에선 불변식 검사가 대체
    ├── skills/zzon-seq/                # 스킬 3 — 시퀀스 다이어그램
    │   ├── SKILL.md                    # 판별(vs data-flow)→코드 추적→SeqSpec 저작→렌더/빌드→위키 임베드
    │   ├── references/
    │   │   ├── seq-spec.md             # SeqSpec 정본 (kind:"sequence", actors/steps/fragments, essential 규칙)
    │   │   └── sample-seq-*.json       # 모범 답안 2종 (alt/else 결제 · loop/opt/par 배치)
    │   └── scripts/
    │       ├── render-seq.mjs          # SeqSpec 검증 + 템플릿 (seq-engine.js 인라인 주입)
    │       └── seq-engine.js           # 뷰어 엔진 (순수 JS 정본 — 수정 시 브라우저 재검증)
    ├── skills/terra-form/              # 스킬 4 — Terraform 클라우드 인프라
    │   └── SKILL.md                    # *.tf 판독 → 엔진 DSL 저작 → bun ia render + 불변식 게이트 → 패스스루 스펙으로 manifest 편입
    └── skills/zzon-wiki/               # 스킬 2 — 프로젝트 문서 위키
        ├── SKILL.md                    # 프로세스 강제: 스캔→티어 승인→섹션 루프(질문)→빌드, 재진입은 --status부터
        ├── references/
        │   ├── wiki-spec.md            # wiki.json 스키마 + md 규약(@diagram, ❓ 콜아웃) 정본
        │   ├── doc-catalog.md          # SI 12섹션 카탈로그 템플릿 (tier 태그·dynamic 규칙·질문 은행·seq-flows 슬롯)
        │   ├── sample-wiki.json        # 모범 답안 + 검증 픽스처
        │   └── sample-docs/            # 모범 문서 md (다이어그램 임베드·콜아웃 예시)
        └── scripts/
            └── build-wiki.mjs          # wiki.json+docs/*.md → self-contained 위키 index.html (--status 지원)

Read the full file on GitHub · 261 lines

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 Changed · +8 lines · +891 tokens per session fb6d3940dbe1
  2. 19d ago Changed · +55 lines · +4,777 tokens per session 2d07bc41977e
  3. 2mo ago First seen · 198 lines · 9,006 tokens per session scan A c25b17ae072a

Subscribe to this mod's changes

zzon-doc CLAUDE.md is an instructions file published in the GitHub repository HOKlNG/zzon-doc (2 stars, last pushed 5d ago), licensed MIT. It adds 14,674 tokens to every session, about $0.0587 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 2026-08-31.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens