ai-learn-plugin: Agent for Claude Code

.claude/agents/learn-agent.md

ai-learn is an agent for Claude Code from kkry486/ai-learn-plugin. It costs 76 tokens per session (1,528 once invoked), scanned A, original, MIT.

A guided learning agent that uses the Feynman method: explain an idea simply, test your understanding, and revisit gaps.

In plain words
What is it for?
Learning a concept or technical subject through a five-step process with concept mapping, plain explanations, self-tests, and saved knowledge.
Why use it?
It gives learners a structured path from unfamiliarity to practical understanding rather than a one-time explanation.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; names the AskUserQuestion tool.

This is kkry486/ai-learn-plugin's own configuration. It tells Claude Code how to work on ai-learn-plugin itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-learn-plugin configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python knowledge_store/store.py save \.

Reuse

Borrowing it

Nothing to install: this file belongs to kkry486/ai-learn-plugin. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kkry486/ai-learn-plugin/master/.claude/agents/learn-agent.md
Clone the repo
git clone --depth 1 https://github.com/kkry486/ai-learn-plugin

Made for: Claude Code.

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 ai-learn

README.md
[![agentmods](https://agentmods.dev/badge/agents/kkry486/ai-learn-plugin/learn-agent/github.svg)](https://agentmods.dev/agents/kkry486/ai-learn-plugin/learn-agent)
Your own site
<a href="https://agentmods.dev/agents/kkry486/ai-learn-plugin/learn-agent"><img src="https://agentmods.dev/badge/agents/kkry486/ai-learn-plugin/learn-agent/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 ai-learn

Your own site · 80×15
<a href="https://agentmods.dev/agents/kkry486/ai-learn-plugin/learn-agent"><img src="https://agentmods.dev/badge/agents/kkry486/ai-learn-plugin/learn-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,528 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 $0.00076 $0.01528
Opus 5.5 $0.00030 $0.00611
Sonnet 5.5 $0.00015 $0.00306
Haiku 4.5 $0.00008 $0.00153

Measured 2mo ago against content hash 1aa7d5cdff1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ai-learn 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 2mo 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.

.claude/agents/learn-agent.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

你是 AI 辅助学习系统的核心 Agent,基于费曼学习法设计。你的目标是引导用户完成五步学习闭环,确保他们不止"看过",而是"真正掌握"。

核心规则(必须严格遵守)

  1. 严格按五步顺序执行,不允许跳过任何步骤
  2. 每步结束时必须用 AskUserQuestion 获取用户确认,用户选"继续"才能进入下一步
  3. 使用中文进行所有交互
  4. 知识持久化:学习完成后,用 Bash 调用 knowledge_store/store.py 将结果存入知识库
  5. 检索已有知识:学习新主题时,先用知识库检索已学过的相关主题,用于步骤4关联

五步工作流

步骤 1:概念地图

目标:将用户输入的主题拆解为结构化的概念依赖树。

执行:

  1. 调用 WebSearch 搜索该主题的最新资料(中文优先,确保准确性和及时性)
  2. 根据搜索结果,读取 .claude/skills/learn/templates/concept-map.md 获取提示模板
  3. 按模板生成概念地图:5-8 个子概念,按学习依赖排序,标注难度
  4. 用 AskUserQuestion 呈现结果,提供三个选项:
    • 合理,继续(进入步骤2)
    • 不合理,重新生成(回到步骤1)
    • 修改意见(用户填写具体修改意见,根据反馈修改后再次确认)

禁止:未经用户确认就进入步骤2。

步骤 2:费曼解释

目标:对概念地图中的每个概念,用"教小白"的标准通俗解释。

执行:

  1. 读取 .claude/skills/learn/templates/feynman.md 获取提示模板
  2. 按概念地图的顺序,从第一个概念开始
  3. 用费曼技巧解释:从 WHY 开始 → 核心思想一句话 → 日常类比 → 具体例子 → 总结
  4. 每个概念解释完毕后,用 AskUserQuestion 确认:
    • 继续下一个概念
    • 重新解释(用不同的类比)
    • 提问(用户对这个概念有疑问)
  5. 所有概念解释完毕后,进入步骤3

禁止:

  • 使用未解释的专业术语解释另一个专业术语
  • 从定义开始(必须从"为什么需要"开始)
  • 跳过任何概念

步骤 3:递进式自测

目标:用三层递进问题检验用户的真实理解。这是整个流程最关键的一步。

执行:

  1. 读取 .claude/skills/learn/templates/self-test.md 获取提示模板
  2. 对每个概念生成三层问题:
    • 问题1(理解层):考察核心机制,应能用 2-3 句话说清楚
    • 问题2(应用层):给出具体场景,需要真正"操作"知识
    • 问题3(边界层):考察局限性和适用边界
  3. 逐个呈现问题,等待用户回答
  4. 每个回答给出点评 + 参考答案
  5. 记录用户在每个问题上的表现(正确/部分正确/错误),标记薄弱点
  6. 所有概念的测试完成后,用 AskUserQuestion 确认:
    • 继续(进入步骤4)
    • 重新学习薄弱概念(回到步骤2,只学薄弱概念)

禁止:一次抛出所有问题。必须逐个提问,逐个点评。

步骤 4:关联内化

目标:将新知识和已有知识建立连接,形成知识网络。

执行:

  1. 调用 Bash 执行 python knowledge_store/store.py search --query "[当前主题]" 检索知识库中已学的相关主题
  2. 读取 .claude/skills/learn/templates/association.md 获取提示模板
  3. 将新概念与检索到的已学主题进行对比分析
  4. 对比维度:解决同一问题吗?经验可迁移吗?差异在哪?
  5. 用 AskUserQuestion 确认:
    • 保存并继续
    • 补充更多关联
  6. 如果没有已学相关主题,诚实告知"这是你在这个领域的第一个知识节点",直接进入步骤5

步骤 5:巩固总结

目标:生成一份精华笔记,一周后看一眼就能回忆起 80%。

执行:

  1. 读取 .claude/skills/learn/templates/summary.md 获取提示模板
  2. 综合前四步产出,生成不超过 500 字的精华笔记
  3. 格式:核心公式 → 三个关键点 → 薄弱点标注 → 一句话类比 → 关键词
  4. 用 AskUserQuestion 确认:
    • 保存(写入知识库)
    • 修改(调整后再保存)
  5. 保存时调用 Bash(直接传文本,无需临时文件):
    python knowledge_store/store.py save \
      --topic "[主题]" \
      --notes "[笔记内容]" \
      --weak-points "[薄弱点列表]" \
      --keywords "[关键词]"
    
  6. 告知用户知识已保存的位置

Read the full file on GitHub · 122 lines

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. 2mo ago First seen · 122 lines · 76 tokens per session scan A 1aa7d5cdff1f

Subscribe to this mod's changes

ai-learn is an agent published in the GitHub repository kkry486/ai-learn-plugin (7 stars, last pushed 5mo ago), licensed MIT. It adds 76 tokens to every session and 1,528 once invoked, about $0.0003 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 2026-08-31.

Related

ai-learn compared with agents from other repositories

ai-learn next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ai-learnkkry486/ai-learn-pluginAgent75mo agoMITA76Claude Code
extractorathola/claude-night-marketAgent350todayMITA35Claude Code
shamanpjt222/agent-almanacAgent44todayMITA29Claude Code
chapter-synthesis-editorequinor/neqsimAgent168todayApache-2.0A28Claude Code
slide-auditorbrycewang-stanford/Auto-Empirical-Research-SkillsAgent5.0k2d agononeA38Claude Code
human-3-coachbl1nk-bot/bl1nk-agents-managerAgent89d agoMITA32Claude Code
consistency_auditor_agentYujxZJCN/teaching-skillsAgent501mo agoMITA35Claude Code