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 agents/kkry486/ai-learn-plugin/learn-agentgit clone --depth 1 https://github.com/kkry486/ai-learn-pluginWhat 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 | $0.00076 | $0.01528 |
| Opus 5 | $0.00038 | $0.00764 |
| Sonnet 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 2d 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.
- 2d 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 (5 stars, last pushed 2mo ago), licensed MIT. It adds 76 tokens to every session and 1,528 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.