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/scuba)<a href="https://agentmods.dev/skills/eunji-jessi-jung/reef/scuba"><img src="https://agentmods.dev/badge/skills/eunji-jessi-jung/reef/scuba/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/scuba"><img src="https://agentmods.dev/badge/skills/eunji-jessi-jung/reef/scuba.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 | $0.00016 | $0.10495 |
| Opus 5 | $0.00008 | $0.05248 |
| Sonnet 5 | $0.00003 | $0.02099 |
| Haiku 4.5 | $0.00002 | $0.01050 |
Grade A, and why
scuba 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.
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 — 599 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/reef:scuba
Automated knowledge deepening. Builds an artifact generation manifest, then systematically produces advanced artifacts from what snorkel+source already generated. After the briefing, transitions to interactive exploration if the user wants to fill remaining gaps.
Core principle: "AI found the answers. I asked the questions."
MANDATORY — Completion checklist
You MUST complete these steps IN ORDER. Do NOT skip any. Do NOT jump ahead.
- Locate the reef (Step 1)
- Load context (Step 2)
- Build the artifact generation manifest (Step 2.5) — explicit list of every artifact to produce
- Automated Deepening (Step 3) — work through the manifest, NO user input needed
- Briefing (Step 4) — present manifest completion status, coverage gaps, next steps
CRITICAL: Automated deepening ALWAYS runs first. Even if the user says "let's answer the questions" or "go through all of them" — this means: run the automated pass first, THEN present findings in the briefing. Do NOT ask the user questions until automated deepening is complete.
EQUALLY CRITICAL: Human review checkpoints exist between batch rounds. After each sequential round (Batch 0, Batches 1-3, Batches 4a-4c, Batches 5a-5b), pause and show the user 2-3 sample artifacts from that round. The user can flag factual errors, add context, or request re-generation before the next round builds on potentially flawed foundations. These checkpoints are NOT optional — skipping them to "save time" is how quality regressions happen. A 2-minute review between rounds catches errors that a post-hoc briefing cannot.
Setup
Read these references before doing anything else:
${CLAUDE_PLUGIN_ROOT}/references/artifact-contract.md${CLAUDE_PLUGIN_ROOT}/references/methodology.md${CLAUDE_PLUGIN_ROOT}/references/understanding-template.md— focus on Scuba (C1-C10) questions
Voice
Curious Researcher at scuba depth. Conversational, Socratic — asking good questions, not interrogating. Present-participle narration for progress. Genuine curiosity about the domain. No emojis. No exclamation marks.
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 · 599 lines · 16 tokens per session scan A 59008f360bae
scuba is a skill published in the GitHub repository eunji-jessi-jung/reef (5 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 10,495 once invoked, about $0.0001 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…