Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add eunji-jessi-jung/reef --skill helpgit clone --depth 1 https://github.com/eunji-jessi-jung/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/help)<a href="https://agentmods.dev/skills/eunji-jessi-jung/reef/help"><img src="https://agentmods.dev/badge/skills/eunji-jessi-jung/reef/help/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/help"><img src="https://agentmods.dev/badge/skills/eunji-jessi-jung/reef/help.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 | $0.00011 | $0.01168 |
| Opus 5 | $0.00005 | $0.00584 |
| Sonnet 5 | $0.00002 | $0.00234 |
| Haiku 4.5 | $0.00001 | $0.00117 |
Grade A, and why
help 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 10d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/reef:help
Show the user what reef can do, where they are, and what to do next.
Step 1 — Skill reference
Print this skill list:
reef skills:
Setup
/reef:init Bootstrap a new reef from your codebase
Discovery (progressive depth)
/reef:snorkel Auto-discover draft artifacts from source code
/reef:source Extract full API specs and ERDs from source repos
/reef:scuba Deepen knowledge — automated analysis + Socratic Q&A
/reef:deep Exhaustive line-by-line tracing of specific areas
Maintenance
/reef:update Pull sources, detect changes, generate update report for review
/reef:artifact Explore a topic, capture knowledge, or update an artifact
/reef:health Validate artifacts and report freshness
/reef:test Test the reef against your question bank
Help
/reef:help This screen
Tip: Artifacts are wikilinked — open the reef directory as an Obsidian vault for graph visualization.
Tip: Have PRDs, SOPs, meeting notes, or design docs? Drop them in sources/context/ and scuba will use them.
Step 2 — Reef status
Look for a .reef/ directory in cwd or parent directories.
If no reef found:
No reef detected in this directory.
Run /reef:init to get started.
Stop here. Do not proceed to Step 3.
If reef found: Read .reef/project.json, scan artifacts/, sources/apis/, sources/schemas/, and .reef/scuba-manifest.json (if exists). Present a compact status:
Reef: {name} ({path})
Artifacts: N total
SYS-: a SCH-: b API-: c CON-: d
PROC-: e DEC-: f GLOSSARY-: g RISK-: h PAT-: i
Sources:
API specs: N extracted (services: {list})
Schemas: N extracted (services: {list})
Questions: N total, M answered, K unanswered
Scuba manifest: {not found | N/M completed, K remaining}
2.5 — New context alert
Scan sources/context/ and sources/raw/ for files not referenced by any artifact's sources field. If new unreferenced files exist, append an alert to the status:
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.
- 10d ago First seen · 133 lines · 11 tokens per session scan A 556e66710e49
help is a skill published in the GitHub repository eunji-jessi-jung/reef (5 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 11 tokens to every session and 1,168 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…