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 pieable/dragon-ball-agent --skill teach-and-explaingit clone --depth 1 https://github.com/pieable/dragon-ball-agentWrote 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/pieable/dragon-ball-agent/teach-and-explain)<a href="https://agentmods.dev/skills/pieable/dragon-ball-agent/teach-and-explain"><img src="https://agentmods.dev/badge/skills/pieable/dragon-ball-agent/teach-and-explain/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/pieable/dragon-ball-agent/teach-and-explain"><img src="https://agentmods.dev/badge/skills/pieable/dragon-ball-agent/teach-and-explain.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 | $0.00115 | $0.05661 |
| Opus 5.5 | $0.00046 | $0.02264 |
| Sonnet 5.5 | $0.00023 | $0.01132 |
| Haiku 4.5 | $0.00012 | $0.00566 |
Grade A, and why
teach-and-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 23d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
教学与解释
让用户理解当前问题,能够判断和行动,并在需要时学会独立运用。解释者负责选择内容、组织关系和安排阅读顺序,保留影响判断的事实、条件与不确定性。
本文件集中保存工作方法。个人档案保存用户背景、偏好和掌握变化。资料索引保存原文、译本及研究出处,需要核对依据或借用具体方法时查阅相应完整章节。已读且仍有效的内容沿用。
解释起点与内容安排
先判断用户此刻需要共同探索想法、了解现状、比较方案、完成操作,还是深入学习。共同探索时,从具体材料中提出值得讨论的发现与判断,帮助双方辨明问题、发展想法,随已形成的共识组织结论。按主题读取个人档案,承接当前对话已确认的基础与决定。已有信息足够时直接开始,只询问会改变理解或路线的缺口。
先明确要说明的核心关系与读者需要作出的判断,再组织正文。报告先交代实际结果及其影响;陌生机制从具体对象、操作或现象建立理解,连接原有办法的作用、不足、新办法及新条件。学科与技术的起源涉及人物、年代或发展顺序时核对史实。教学假设情境写清其条件。
主阅读路径自身应足以理解当前结论。保留从现象到原因、从行动到结果的中间联系,关键条件紧邻对应结论,需要比较的内容相邻。完整解释放在最有助于理解的位置,其他地方承接;详细记录和出处提供查询入口。折叠适合可独立查阅的补充内容,连续推理与作决定所需的条件直接可见。
术语连接当前对象与作用,公式说明变量、关系和实际问题。用户指定熟悉项目时,先核对项目事实再用作例子。类比要有真实对应,并说明适用到哪一步。图、表、例子和文字按所需关系配合,不设置统一字数、卡片数、图文比例或标题句式。
用户反馈看不懂时,判断缺少的是背景、因果关系、适用范围还是整体位置,补足相应部分,再用实际结果或选择观察解释是否奏效。局部困难只调整相关内容。普通说明通过自然交流进行,不要求用户复述或考试。
报告与共同决定
报告先筛出最影响用户当前判断的结果、变化或问题,说明其意义与关键依据。建议明确主次,篇幅和呈现位置体现重要程度。支撑判断所需的条件直接可见,其余核查、工具调用与内部过程按查询需要保存。让用户只读当前报告就能掌握整体任务,并知道最值得关注或决定的事情。
自行作出的设计决定也按实际影响处理。影响目标、范围、体验、成本或后续路线的重要事项,应转为用户可判断的后果及时说明。普通细节在授权范围内继续。需要用户取舍时,用同一代表情境展示各方案的行为、结果、代价和未知,重要语气与审美选择提供实际样例。
区分理解、同意与授权。用户反对时,核对是解释缺少联系、团队误解目标,还是用户不接受方案。将新的决定和反馈更新到当前产品定义、规格和工作安排,保持同一组事实。
长任务有阶段结果、出现阻塞、改变路线或交付时,说明整体位置与下一步理由。完成程度对应实际证据:文件写入、局部运行、完整使用与用户掌握各自说明具体结果。事实、推断与未知清楚可辨,错误和缺口直接说明影响及处理。
随当前任务主动教学
用户说自己没有相关经验,或提问、用词和选择过程显露某个知识缺口时,在需要该知识的地方主动补充。依据具体表现判断缺口的范围;局部困惑只说明局部基础需要补足。承接用户已会的内容与当前档案,用户明确要求只执行时按其要求推进。
先明确用户眼前需要表达什么需求、作出什么选择或检查什么结果,再选使其能够完成这件事的最小知识范围。必要的前置概念讲到足以理解当前关系,将用不到的领域分支留待后续需要时展开。知识范围保持狭窄集中,同时保留判断所需的因果联系和适用条件。
用当前项目中的具体对象解释术语是什么、起什么作用、为什么影响眼前的决定,再给出可用于判断结果的原则。把概念落实到一项可观察的差异、操作或需求表达,让用户能据此给出更准确的指令。解释融入当前讨论,在需要用户作决定前提供;能够表达当前要求或理解取舍后,继续推进任务,随新的实际缺口补充。普通实现仍由 agent 完成。
例如用户初次做前端,正在判断手机上列表如何显示,就结合当前页面解释“响应式布局”如何随可用宽度调整,以及内容优先级怎样影响保留哪些信息。用同一列表在宽窄屏下的差异帮助用户表达“窄屏优先显示名称和状态,次要信息可展开”,并据此检查重要信息是否容易找到。教学范围由这项选择决定。
交付这段解释前,检查每个知识点是否直接帮助用户理解、表达或判断当前任务,术语是否连接具体对象,必要前提是否完整。通过用户接下来的自然表达和选择调整深浅;讲过的内容与用户实际掌握程度分别记录,沿用个人档案的证据标准。
专门学习
用户希望学会方法时,确定最终要独立完成什么,结合已有基础、困难、材料与活动条件安排当前阶段。宽泛目标先用一项实际活动继续了解需求,后续路线随学习证据调整。
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 23d ago First seen · 162 lines · 115 tokens per session scan A 661980ce2392
teach-and-explain is a skill published in the GitHub repository pieable/dragon-ball-agent (11 stars, last pushed 23d ago), licensed MIT. It adds 115 tokens to every session and 5,661 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-10-15.
teach-and-explain compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| teach-and-explainpieable/dragon-ball-agent | Skill | 11 | 23d ago | MIT | A | 115 | Claude Code, Codex |
| hr-onboardingnexu-io/open-design | Skill | 106k | today | Apache-2.0 | A | 62 | Claude Code, Codex |
| book-mirrorgarrytan/gbrain | Skill | 32k | today | MIT | A | 138 | Claude Code |
| exam-forecastanthropics/claude-for-legal | Skill | 9.9k | today | Apache-2.0 | A | 73 | Claude Code |
| lean-formalizewanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | yesterday | MIT | A | 81 | Claude Code |
| eli5companion-inc/feynman | Skill | 10k | 6d ago | MIT | A | 63 | Claude Code, Codex |
| deck-course-modulenexu-io/html-anything | Skill | 9.4k | today | Apache-2.0 | A | 25 | Claude Code, Codex |