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.
curl -O https://raw.githubusercontent.com/kkry486/ai-learn-plugin/master/.claude/agents/learn-agent.mdgit clone --depth 1 https://github.com/kkry486/ai-learn-pluginWrote 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/agents/kkry486/ai-learn-plugin/learn-agent)<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.
<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>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 | $0.00076 | $0.01528 |
| Opus 5.5 | $0.00030 | $0.00611 |
| Sonnet 5.5 | $0.00015 | $0.00306 |
| Haiku 4.5 | $0.00008 | $0.00153 |
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.
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)
- 严格按五步顺序执行,不允许跳过任何步骤
- 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
- 使用中文进行所有交互
- 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
- 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:
- 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)
- 根据搜索结果,读取
.claude/skills/learn/templates/concept-map.md获取提示模板 - 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
- 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:
- 读取
.claude/skills/learn/templates/feynman.md获取提示模板 - 按概念地图的顺序,从第一个概念开始
- 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
- 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)
- 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:
- 读取
.claude/skills/learn/templates/self-test.md获取提示模板 - 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
- 逐个呈现问题,等待用户回答
- 每个回答给出点评 + 参考答案
- 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
- 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:
- 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 - 读取
.claude/skills/learn/templates/association.md获取提示模板 - 将新概念与检索到的已学主题进行对比分析
- 对比维度:解决同一问题吗?经验可迁移吗?差异在哪?
- 用 AskUserQuestion 确认:
- 保存并继续
- 补充更多关联
- 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:
- 读取
.claude/skills/learn/templates/summary.md获取提示模板 - 综合前四步产出,生成不超过 500 字的精华笔记
- 格式:核心公式 → 三个关键点 → 薄弱点标注 → 一句话类比 → 关键词
- 用 AskUserQuestion 确认:
- 保存(写入知识库)
- 修改(调整后再保存)
- 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]" - 告知用户知识已保存的位置
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.
- 2mo ago First seen · 122 lines · 76 tokens per session scan A 1aa7d5cdff1f
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.
ai-learn compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ai-learnkkry486/ai-learn-plugin | Agent | 7 | 5mo ago | MIT | A | 76 | Claude Code |
| extractorathola/claude-night-market | Agent | 350 | today | MIT | A | 35 | Claude Code |
| shamanpjt222/agent-almanac | Agent | 44 | today | MIT | A | 29 | Claude Code |
| chapter-synthesis-editorequinor/neqsim | Agent | 168 | today | Apache-2.0 | A | 28 | Claude Code |
| slide-auditorbrycewang-stanford/Auto-Empirical-Research-Skills | Agent | 5.0k | 2d ago | none | A | 38 | Claude Code |
| human-3-coachbl1nk-bot/bl1nk-agents-manager | Agent | 8 | 9d ago | MIT | A | 32 | Claude Code |
| consistency_auditor_agentYujxZJCN/teaching-skills | Agent | 50 | 1mo ago | MIT | A | 35 | Claude Code |