learning-companion

learning-companion is a skill for Claude Code, Codex from zts212653/clowder-ai. It costs 136 tokens per session (2,523 once invoked), scanned A, original, MIT.

A guided reading helper for exploring papers, interviews, articles, and book chapters together. It keeps the source material, explanations, and discussion connected.

In plain words
What is it for?
Use it to prepare reading scripts or spoken versions, explain difficult ideas, trace an author's claims and evidence, and discuss open questions while reading.
Why use it?
It prevents a summary or lesson from replacing what the original author actually said. It also helps keep corrections, evidence, and the version being read aligned.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to prepare reading scripts or spoken versions, explain difficult ideas, trace an author's claims and evidence, and discuss open questions while reading.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zts212653/clowder-ai/learning-companion
About the project

Clowder AI is a self-hosted workspace where AI agents from different model families work together as a persistent team, retaining identities, shared evidence, and memory across tasks. It is for people who want to coordinate multiple AI agents without repeatedly rebuilding their context.

zts212653/clowder-ai · 3,471 stars · on GitHub

Install

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.

Any agent
npx skills add zts212653/clowder-ai --skill learning-companion
Clone the repo
git clone --depth 1 https://github.com/zts212653/clowder-ai

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for learning-companion

README.md
[![agentmods](https://agentmods.dev/badge/skills/zts212653/clowder-ai/learning-companion/github.svg)](https://agentmods.dev/skills/zts212653/clowder-ai/learning-companion)
Your own site
<a href="https://agentmods.dev/skills/zts212653/clowder-ai/learning-companion"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/learning-companion/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.

agentmods 80×15 button for learning-companion

Your own site · 80×15
<a href="https://agentmods.dev/skills/zts212653/clowder-ai/learning-companion"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/learning-companion.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 136 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,523 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00136 $0.02523
Opus 5.5 $0.00054 $0.01009
Sonnet 5.5 $0.00027 $0.00505
Haiku 4.5 $0.00014 $0.00252

Measured 8d ago against content hash b168f0798d30, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

learning-companion 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 8d 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.

cat-cafe-skills/learning-companion/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Learning Companion · 陪伴学习

为什么需要这份 skill

家里曾把约好的访谈重读换成概念课:概念与算例都能讲通,人却认不回作者说了什么。 另一次,讨论里纠正了事实,正在听的稿子却还留着旧说法。猫冷读说“懂了”,也未必代表人的理解。 本 skill 保住来源、实际阅读入口与共同探索之间的连接;初版供新材料试用,不宣称已证明普遍教学收益。 具体原件和一个成稿小样见 实战与示例。

接住这一次共读

  • 从已经给出的材料、追问和熟悉程度开始;已有上下文能回答的,不重新采访一遍。
  • 判断这次想认回原文、补一个概念、迁移到新场景,还是一起找新问题。几种目的可以并存,随讨论调整。
  • 用户只要短摘要、逐段翻译或一个事实时,直接完成那项请求;不额外发起共读流程。
  • 单猫也能陪读。已有伙伴时轮换主讲、查证、挑战的位置;人数和轮次不固定,不为使用 skill 自动召集全家。
  • 学习可以在一段解释、一张图或一场讨论里发生;是否写稿、先导读还是先原文,按本轮用途选择。

先读材料,保留它自己的问题

找到并读取可用原材料;旧笔记和同伴转述用来定位,不能替代本轮采用的关键原文。 已有可读入口就自己读取,不把原本能完成的取材工作退给人。来源不完整时,说明实际读到哪里,沿可用材料继续。

抓住作者的问题、主张、理由、反驳与尚未回答的部分。保留不同发言者的归属、条件和证据强度: “相关”不能讲成“导致”,“愿意继续试”不能讲成“已经证明有效”。 也不要为了制造顺畅的转折,替作者编一个更强的旧主张,再写成他后来“收回”了它。 外部高风险事实按 source-audit 查证;核验深度跟实际采用的主张走。

原文入口、译述、概念解释和猫自己的判断要能辨认。尤其听读时,归属直接进入正文: “这里作者认为……”/“下面我换个例子……”/“这个联系是我的猜想……”。 不靠末尾一张来源表承担所有区分,也不把概念导读称作完整原文。

按阅读方式成稿

材料 帮助人做什么 写作时保住什么
原材料与入口 回查、细读、挑战转述 来源与章节定位、实际覆盖范围;按来源权限使用,不默认复制整部作品
正式阅读稿 人猫共同阅读、批注和回看 问题如何展开、因果与分歧、关键例子、来源;图表和术语解释放在需要的位置
口播稿 不盯屏幕也能跟上 顺着听得懂的段落、具体例子、自然转场与回扣、观点归属和关键限定

用户要一篇材料的完整共读稿时,展开它的论证与交锋;目录、结论清单或几个讨论题不能顶替正文。 按主题选读时说清取舍。先用导读搭直觉可以,但仍给原材料留出明确入口。

口播稿要重写成可听的语言:把表格讲成关系,把公式讲清变量含义,首次出现的术语解释后尽量保持叫法稳定。 正文不朗读 URL、引用编号、代码路径或大段英文;将查证入口留给阅读稿。 长一点但因果完整,优于只剩关键词;也不因追求口语就删掉决定结论的条件。

成稿沿当前项目约定保存;Clowder AI 通常放在 docs/study/,阅读稿和 -listen.md 互相指向。 用 workspace-navigator 把所需文件交到 Workspace,回报真实投递状态。 已有 Workspace 听读偏好时直接支持那个入口,不自动合成长语音;明确需要语音成品才走 rich-messaging。讨论本身已足够时,不额外制造三套文件。

陪着讨论,猫也带来自己的问题

接住批注、类比和反驳,先弄清对方连接的是哪条因果。概念混在一起时,用实际例子拆开; 人提出疑问时,先检查自己的解释是否遗漏前提或造成误导,不急着判断“他没学会”。

猫主动提供有内容的看法、反例或新联系,并说明什么证据会让自己改口。 可以从材料外找一段不同经验、一项相反观察,或一个能揭穿当前解释的小实验;把它与原文的关系说清。 不要只列问题交给人作答,也不为显得独立而表演反对。

PK 围绕一个确实可争的主张展开。各方先说理由,再回原文或新证据;同意票、模型家族或一串 review 通过, 都不能替代证据。分歧可以保留为不同适用条件,不必每轮决出胜负。 观点改变时,说清哪条事实或反例改变了判断;未改变也照实说,不编造“被说服”的戏。

四象限与 unknown-first:让问题继续生长

按 家里的探索原则 寻找最可能改变认识的未知。 先分清谁不知道什么:人已有但尚未说出的经验、猫还没读到的材料、研究本身尚无答案,不能混成一种“不知道”。

Read the full file on GitHub · 130 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 8d ago First seen · 130 lines · 136 tokens per session scan A b168f0798d30

Subscribe to this mod's changes

learning-companion is a skill published in the GitHub repository zts212653/clowder-ai (3,471 stars, last pushed today), licensed MIT. It adds 136 tokens to every session and 2,523 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 2026-10-13.

Related

Other skills, from other repositories

hr-onboarding

A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".

nexu-io/open-design · 62 tokens

book-mirror

Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…

garrytan/gbrain · 138 tokens

lean-formalize

Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…

wanshuiyin/Auto-claude-code-research-in-sleep · 81 tokens

exam-forecast

Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.

anthropics/claude-for-legal · 73 tokens

eli5

Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.

companion-inc/feynman · 63 tokens

deck-course-module

A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.

nexu-io/html-anything · 25 tokens