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.
/plugin marketplace add eunji-jessi-jung/reef/plugin install reefWrote 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.
[](https://agentmods.dev/skills/eunji-jessi-jung/reef/init)<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.
<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>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 | $0.00009 | $0.04758 |
| Opus 5 | $0.00005 | $0.02379 |
| Sonnet 5 | $0.00002 | $0.00952 |
| Haiku 4.5 | $0.00001 | $0.00476 |
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.
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.
- Print the welcome (Step 0) — the ASCII art and orientation block. This is your FIRST output.
- Ask the name (Step 2) — "What should this reef be called?" STOP and wait.
- Ask what it covers (Step 3) — "Could you give a brief introduction of what this reef covers?" STOP and wait.
- Ask location and sources (Step 4) — "Where should the reef live? And where are the codebases?" STOP and wait.
- 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. - Scaffold and index (Steps 5-6) — automated, no user input.
- Service grouping (Step 7) — present best guess as table, ask user to correct. STOP and wait.
- 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
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.
- 9d ago First seen · 401 lines · 9 tokens per session scan A 2921f591b1e0
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…