init

init is a skill for Claude Code from eunji-jessi-jung/reef. It costs 9 tokens per session (4,758 once invoked), scanned A, original, Apache-2.0.

A setup guide that creates a new Reef wiki from a codebase. A Reef wiki is a structured knowledge base for documenting and navigating software projects.

In plain words
What is it for?
Use it when starting documentation for one or more codebases. It can find Git repositories, check for monorepo signals, group services, and build the initial index after collecting the required choices.
Why use it?
It helps establish the wiki’s name, scope, location, source repositories, project groupings, and discovery process before indexing code.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions CLAUDE.md; positional $N argument.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the reef plugin — 11 skills, 1 agent shipped together

Good fit Use it when starting documentation for one or more codebases. It can find Git repositories, check for monorepo signals, group services, and build the initial index after collecting the required choices.

Compare 6 skills from other repositories ↓
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 eunji-jessi-jung/reef
Claude Code
/plugin install reef

Made for: Claude Code.

Or install reef, the plugin that ships this one along with the rest of its 11 skills, 1 agent.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/eunji-jessi-jung/reef/init/github.svg)](https://agentmods.dev/skills/eunji-jessi-jung/reef/init)
Your own site
<a href="https://agentmods.dev/skills/eunji-jessi-jung/reef/init"><img src="https://agentmods.dev/badge/skills/eunji-jessi-jung/reef/init/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 init

Your own site · 80×15
<a href="https://agentmods.dev/skills/eunji-jessi-jung/reef/init"><img src="https://agentmods.dev/badge/skills/eunji-jessi-jung/reef/init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 9 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,758 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 $0.00009 $0.04758
Opus 5 $0.00005 $0.02379
Sonnet 5 $0.00002 $0.00952
Haiku 4.5 $0.00001 $0.00476

Measured 9d ago against content hash 2921f591b1e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

init 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 9d 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/SKILL.md · 401 lines

How it starts

The opening of the file, as written. The whole thing — 401 lines — stays where its author put it; the contents beside it link to each section on GitHub.

reef:init

MANDATORY — Read this first

You MUST complete these interactions with the user IN ORDER. Do NOT skip any. Do NOT combine them into one message. Each requires a separate user response.

  1. Print the welcome (Step 0) — the ASCII art and orientation block. This is your FIRST output.
  2. Ask the name (Step 2) — "What should this reef be called?" STOP and wait.
  3. Ask what it covers (Step 3) — "Could you give a brief introduction of what this reef covers?" STOP and wait.
  4. Ask location and sources (Step 4) — "Where should the reef live? And where are the codebases?" STOP and wait.
  5. Scan for repos — Run find <directory> -name .git -type d 2>/dev/null | sed 's|/.git||' | sort — this is the ONLY correct way to find repos. Do NOT use ls, glob, or manual directory listing. Check each repo for monorepo signals and expand sub-projects if detected. Present results as a numbered list and ask user to select by number.
  6. Scaffold and index (Steps 5-6) — automated, no user input.
  7. Service grouping (Step 7) — present best guess as table, ask user to correct. STOP and wait.
  8. Discovery plan (Step 8) — show what snorkel+source will do, estimated time/tokens. STOP and wait for confirmation.

Only after ALL interactions are complete, launch snorkel+source (Step 9).


Step 0 — Welcome

This must be your first output. Before reading any other files, before doing anything else, print the following to the user:

    ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~
    ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─

                ~ reef ~
     structured knowledge from source code

    source code  →  questions  →  artifacts
         ↑                            |
         └────── update cycle ────────┘

Then print a compact orientation block:

- Best with Opus (Sonnet works, but Opus finds richer connections)
- Built for codebases with services, data, and interfaces
  (Not for: pure mobile, game engines, firmware, ML notebooks)
- Sweet spot: 3-15 repos that form one domain or team ecosystem
  (Bigger org? One reef per team — not one reef for everything)
- 3 quick questions from you, then full automation

Estimated cost (one-time):
  3-5 repos   ~10 min   ~80-100k tokens   Pro plan works well
  6-10 repos  ~15 min   ~150-200k tokens   Pro plan, may hit rate limits
  10-15 repos ~20 min   ~250-300k tokens   Max recommended
  (On API: roughly $3-5 for small, $10-20 for large)

- Output: draft artifacts + API specs + ERDs + question bank
- After init: /reef:scuba to deepen artifacts with domain knowledge
- Anytime: /reef:help for skill list, reef status, and what to do next

Read the full file on GitHub · 401 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. 9d ago First seen · 401 lines · 9 tokens per session scan A 2921f591b1e0

Subscribe to this mod's changes

init is a skill published in the GitHub repository eunji-jessi-jung/reef (5 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 9 tokens to every session and 4,758 once invoked, about $0.0000 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

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

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

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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens