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 agentmods add skills/surfmind-space/awesome-surfmind/explainnpx skills add surfmind-space/awesome-surfmind --skill explaingit clone --depth 1 https://github.com/surfmind-space/awesome-surfmindWrote 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/surfmind-space/awesome-surfmind/explain)<a href="https://agentmods.dev/skills/surfmind-space/awesome-surfmind/explain"><img src="https://agentmods.dev/badge/skills/surfmind-space/awesome-surfmind/explain.svg" alt="Measured on agentmods" 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 | $0.00083 | $0.00810 |
| Opus 5 | $0.00042 | $0.00405 |
| Sonnet 5 | $0.00017 | $0.00162 |
| Haiku 4.5 | $0.00008 | $0.00081 |
Grade A, and why
explain 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 5d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explain
Explain the selected or visible content so the reader can understand it without prior expertise, accurately and evidence-backed. Never invent details or fill gaps with made-up facts.
- Base the explanation on the selected or visible page content. State the core idea in one or two plain sentences, define any jargon, and add the background that makes it make sense.
- If the page lacks the context needed to explain it well, gather more: use web search or any suitable MCP/tool available to research the topic, then explain from what you find.
- If web search is disabled and no suitable tool is available, explain what the content supports and clearly note what couldn't be verified.
Calibrate depth to how much the content actually holds, not to a fixed length. Look at how many distinct ideas the source contains and match the explanation to that:
- A single self-contained term or one simple idea → keep it tight: the plain-language definition, the bit of background that makes it click, and one example or analogy. A few short paragraphs (or one flowing passage) is usually enough. Don't expand it into a multi-section reference — no heading-per-aspect, no exhaustive tables, no etymology or tangents the reader didn't ask for. One good example makes the point; don't enumerate every variant or related case (e.g. for a term illustrated by one HTTP method, don't catalogue all of them).
- A dense, layered, or multi-part source (a code snippet with several moving parts, a formula and its implications, a passage stacking multiple concepts) → go fuller: lead with the core idea, then use sections, examples, and analogies to make each part genuinely clear.
Detailed, multi-section explanations are good when the material is genuinely that involved, and miscalibrated when it isn't — a long answer to a one-term question is a defect, not thoroughness. Compress to a sentence or two only when the user explicitly asks for a short, brief, or quick explanation (or a TL;DR). Whatever the length, keep the writing clear and easy to follow, and make every part earn its place: depth that aids understanding, never filler, padding, or restating the same point.
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.
- 5d ago First seen · 42 lines · 83 tokens per session scan A aa67320c4f36
explain is a skill published in the GitHub repository surfmind-space/awesome-surfmind (5 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 810 once invoked, about $0.0004 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
cs-master
Expert computer scientist for algorithms, complexity analysis, and distributed systems.
guidance
回答用户关于 QwenPaw 安装与配置的问题：优先定位并阅读本地文档，再提炼答案；若本地信息不足，兜底访问官网文档。.
edu-math-tutorial
数学题分步讲解视频的领域知识。适用场景：(1) 用户给出一道数学题并要求做讲解/ 解题视频；(2) 用户说"讲解这道题"、"生成解题视频"、"make a math tutorial"； (3) 需要中文数学教学视频，涉及方程、公式或几何图形。本 skill 只提供领域 知识（题目拆解、讲解节奏、旁白文案规范、版式与 KaTeX 排版风格）；画面、 配音与成片一律用 Creator 原生 Element 与工具从源头构建。.
video-tutorial-maker
Create scripted tutorial videos with narration, TTS, aligned subtitles, MP4 rendering, and platform variants. Use when Codex needs to create or revise tutorial, explainer, product walkthrough, course, demo, or short-form videos; generate 16:9 landscape output by default unless the user explicitly asks for 9:16, 1:1…
cf-learn
Extract knowledge for human learning from conversation. Auto-invoke on substantial new technical knowledge, debugging breakthroughs, architecture decisions, or complex explanations. Do NOT auto-invoke for trivial edits, typo fixes, or routine operations. Unlike /cf-remember (AI recall), this is educational notes for…
cf-teach
Personal teacher — after a task, explains what happened as a conversational narrative (approach, alternatives, tradeoffs, pitfalls, lessons). Unlike /cf-learn (structured notes), this is a deep-dive so the human understands what happened and why.