A process for creating and maintaining a Korean-language project documentation wiki from code scans and interviews. It produces Markdown documents and a self-contained website, with diagrams for architecture and data flows.

Use it to document new or existing projects, organise developer guides, update a wiki, and embed architecture or interaction diagrams.

It separates facts found in the code from unanswered questions and requires agreement on the documentation scope before writing files.

zzon-wiki — Skill for Claude Code by HOKlNG

Install

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.

Claude Code

/plugin marketplace add HOKlNG/zzon-doc

Claude Code

/plugin install zzon-doc

Made for: Claude Code.

Or install zzon-doc, the plugin that ships this one along with the rest of its 4 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/hoklng/zzon-doc/zzon-wiki/github.svg)](https://agentmods.dev/skills/hoklng/zzon-doc/zzon-wiki)

Your own site

<a href="https://agentmods.dev/skills/hoklng/zzon-doc/zzon-wiki"><img src="https://agentmods.dev/badge/skills/hoklng/zzon-doc/zzon-wiki/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/hoklng/zzon-doc/zzon-wiki"><img src="https://agentmods.dev/badge/skills/hoklng/zzon-doc/zzon-wiki.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,157 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.

Model	Per session	Once invoked
Fable 5.1	$0.00119	$0.02157
Opus 5	$0.00060	$0.01078
Sonnet 5	$0.00024	$0.00431
Haiku 4.5	$0.00012	$0.00216

Measured 11d ago against content hash 5529a8aacae3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

zzon-wiki 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 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/build-wiki.mjs), 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.

zzon-doc/skills/zzon-wiki/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

프로젝트 문서 위키 만들기

코드/인터뷰에서 wiki.json(단일 상태 소스)과 docs/*.md를 저작하고 scripts/build-wiki.mjs로 의존성 0짜리 self-contained 위키 사이트(index.html)를 만든다. 산출물은 대상 프로젝트의 docs/zzon-doc/ 하위에 기존 다이어그램 산출물과 공존한다(구버전 기본값인 루트 zzon-doc/가 이미 있으면 그걸 유지).

계약 정본: references/wiki-spec.md(스키마·md 규약) · references/doc-catalog.md(문서 카탈로그·질문 은행). 아키텍처·데이터 다이어그램은 zzon-doc 스킬 절차(유형 판별→스펙→layout-lint→render)로, 시간축 상호작용(요청/응답 왕복·분기)은 zzon-seq 스킬 절차(SeqSpec 저작→render-seq)로 그린다. 둘 다 같은 specs/→diagrams/→manifest 파이프라인이라 위키 임베드 방법(@diagram)은 동일하다.

0. 분기 — 첫 행동을 정한다

docs/zzon-doc/wiki.json(또는 구버전 경로 루트 zzon-doc/wiki.json)이 있으면 → 재진입 모드(§4). 첫 행동은 무조건 --status 실행이다. 이후 명령의 <docsDir>는 wiki.json이 발견된 그 폴더다.
없으면 → 신규. 코드가 있는 프로젝트면 projectMode: "existing"(스캔 우선), 빈/초기 프로젝트면 "greenfield"(인터뷰 우선).
기존 docs/zzon-doc/manifest.json(다이어그램 — 구버전은 루트 zzon-doc/)이 있으면 → 승격: 기존 다이어그램을 아키텍처/데이터 문서로 자동 편입 제안에 포함한다.

1. 스캔 → 제안 → 승인 (게이트 — 어기지 마라)

순서를 반드시 지킨다: ① 스캔 → ② "티어·섹션" 제안·승인 → ③ 작성. 승인 전에는 wiki.json도 docs/의 어떤 파일도 만들지 마라.

스캔: README·패키지 구조·라우터·스키마·CI/IaC를 훑어 "코드에서 읽힌 것"과 "물어야 하는 것"을 분리한다. (greenfield면 이 단계는 "무엇을 만들려는지" 인터뷰 3~5문으로 대체.)
제안은 반드시 이 형태로 — 티어 3택 + 제외 섹션 + 개수 근거 (시퀀스 후보를 반드시 센다 — 인증·결제·대표 유스케이스처럼 왕복이 본질인 프로세스는 "시퀀스 M장"으로 제안에 명시):

"코드에서 서비스 3·테이블 12·API 24개, 시퀀스 후보 3(인증·공유·다이제스트)을 확인했다. 어느 티어로 갈까? ① 라이트(~15장) — 개요+아키텍처+데이터+API+퀵스타트+운영 핵심 ② 표준(~35장) — ①에 요구·기획·규약·운영 상세 추가 ③ 풀 SI(~90장) — 발주·감리용 전체 그리고 UX 섹션은 Figma 관리로 보여 제외를 제안한다 — 맞나?"
승인받은 구성으로 wiki.json을 인스턴스화한다(카탈로그는 템플릿 — doc-catalog.md의 인스턴스화 절차 6개를 따른다. dynamic 노드는 실제 도메인명으로, summary는 프로젝트 문맥으로 재작성, 카탈로그 그대로 복사 금지, 섹션 code는 포함분 기준 00부터 연속 재부여).

2. 섹션 루프 — 작성은 이 리듬으로

섹션 하나씩: 초안 → 질문 → 빌드 → 마감 확인. 전 섹션 일괄 자동 생성 금지.

초안: 코드에서 읽힌 것만으로 문서를 쓴다. 못 읽은 값을 추측으로 채우지 마라 — 그 자리는 ❓ 콜아웃으로 남긴다.
질문은 섹션당 한 묶음(3~5개), 번호 목록으로, 각 질문에 "모름/스킵 가능"을 명시한다. 10개 이상 몰아 묻기 금지. 무응답·모름은 즉시 wiki.json 질문 대장(q-NNN) + 본문 > ❓ 미확인(q-NNN): … 콜아웃으로 남기고 진행을 막지 마라.
다이어그램 노드(architecture/data의 @diagram 표시)는 zzon-doc(구조·ERD·플로우) 또는 zzon-seq(시퀀스) 스킬 절차로 스펙을 저작해 specs/에 두고, 문서에는 @diagram(slug) 한 줄만 쓴다. HTML 직접 작성 금지. 시퀀스 판별을 건너뛰지 마라: 문서가 다루는 프로세스가 "누가 누구에게 순서대로 주고받는가"(왕복·활성 구간·alt/loop)면 zzon-seq가 정본이고, seq-flows/usecase/authn 문서는 시퀀스 임베드를 기본값으로 한다. 구조 관점(data-flow)과의 병행은 중복이 아니라 보완이다.
섹션을 마치면 빌드하고(아래 명령) 결과를 보여준 뒤 "이 섹션에 빠진 내용은 없나?"를 반드시 묻는다. 다음 섹션은 그 답을 반영한 후에.
todo 문서는 빈 md를 만들지 않는다 — wiki.json 엔트리로만 둔다.

Read the full file on GitHub · 77 lines

Files

What ships with it

11 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.

11d ago First seen · 77 lines · 119 tokens per session scan A 5529a8aacae3

Subscribe to this mod's changes

zzon-wiki is a skill published in the GitHub repository HOKlNG/zzon-doc (2 stars, last pushed 1mo ago), licensed MIT. It adds 119 tokens to every session and 2,157 once invoked, about $0.0006 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.

Claude Code Project management Writing and docs anthropic architecture-diagram claude claude-code-marketplace claude-code-plugin

ticket-lifecycle

The ticket-as-control-plane rulebook — the single home for the tracker-operations contract, tracker resolution, the type/priority taxonomy, human-only trigger authorization, derived status, and trust boundaries. INVOKE when reading or writing tickets in a queue-driven flow, resolving a repo's tracker, or deciding…

PrabhdeepSingh/claude-plugins · 105 tokens

classify-tickets

Backlog hygiene as a sweep — exactly one type and one evidence-based priority per open ticket, and nothing else changes. INVOKE when grooming or prioritizing a backlog, when classifications have drifted, or when /sonu:factory runs a classify pass. Not per-ticket spec work ([[ticket-triage]]) or defect discovery…

PrabhdeepSingh/claude-plugins · 101 tokens

work-planning

Design the complete work hierarchy for a Paperclip company — Goals, Projects, and Tasks as a unified top-down planning workflow. Produces .planning.json for deterministic generation of goals/, projects/, and tasks/ directories. Use when creating a new company's work plan, reorganizing work structure, or linking goals…

lukaskellerstein/claude-my-marketplace · 70 tokens

traction-eos

Implement the Entrepreneurial Operating System (EOS) to align vision and execution across a company. Use when the user mentions "EOS", "Entrepreneurial Operating System", "V/TO", "quarterly rocks", "Level 10 meetings", "accountability chart", "IDS process", "my company feels chaotic", "we keep having the same…

wondelai/skills · 147 tokens

team-topologies

Organize business and technology teams for fast flow using Skelton & Pais's "Team Topologies". Use when the user mentions "team topologies", "Conway's law", "platform team", "stream-aligned team", "team boundaries", "cognitive load", "how should we split teams", "who owns this service", "team dependencies", or…

wondelai/skills · 155 tokens

glab

Expert guidance for using the GitLab CLI (glab) to manage GitLab issues, merge requests, CI/CD pipelines, repositories, and other GitLab operations from the command line. Use this skill when the user needs to interact with GitLab resources or perform GitLab workflows.

NikiforovAll/claude-code-rules · 59 tokens