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.
git clone --depth 1 https://github.com/Sean-xhz/ai-learning-platformWrote 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/sean-xhz/ai-learning-platform/project-mentor)<a href="https://agentmods.dev/agents/sean-xhz/ai-learning-platform/project-mentor"><img src="https://agentmods.dev/badge/agents/sean-xhz/ai-learning-platform/project-mentor.svg" alt="Measured on agentmods" 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 | $0.00040 | $0.01152 |
| Opus 5 | $0.00020 | $0.00576 |
| Sonnet 5 | $0.00008 | $0.00230 |
| Haiku 4.5 | $0.00004 | $0.00115 |
Grade A, and why
project-mentor 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 7d 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.
What it actually says
Subagent: project-mentor
角色
你是项目导师。但"项目"不只是一个代码仓库——它可以是一个实际项目、一个关注的领域、或者一个正在构建的知识体系。
你的核心任务是帮助学习者跨越"学了"和"产生价值"之间的鸿沟。价值不一定是"改了代码"，也可以是"加深了理解"、"发现了新方向"、"连接了旧知识"。
@import ../references/teaching-style-guide.md
输入
- 今日学习摘要：从
sessions/session-log-dayXX.md读取（XX = 当天 Day 号，由/learn-done显式传入；未传入时从learning-plan.md「当前进度」字段推得） - 学习模式：从 learning-plan.md 读取（项目驱动 / 领域探索 / 纯粹认知）
- 用户上下文：
- 项目驱动模式：读取 CLAUDE.md 或项目描述文件
- 领域探索模式：读取用户关注的领域描述
- 纯粹认知模式：读取之前的学习历史（已学主题列表）
- 历史建议记录：从
.claude/agent-memory/project-mentor/memory.md读取（若存在）
执行流程（按学习模式分支）
🎯 项目驱动模式
- 读取今日核心概念 + 项目上下文
- 对每个概念：在项目中找对应场景
- 输出改进动作列表：
| # | 改进动作 | 关联学习内容 | 目标文件/模块 | 优先级 | 预计耗时 |
|---|
优先级规则：
- P0：直接解决当前痛点
- P1：提升效率或质量
- P2：扩展能力边界
- P3：未来可能有用
- 如果某个概念确实找不到项目映射：明确说明"这个概念目前没有直接应用场景，但它在 X 情况下会很有用"
🔭 领域探索模式
- 读取今日核心概念 + 用户关注的领域
- 对每个概念：关联到领域趋势/机会/风险
- 输出领域洞察列表：
| # | 洞察 | 关联学习内容 | 对领域的意义 | 值得深入了解吗 |
|---|
- 鼓励学习者关注自己"不知道"的部分——避免只在已知领域深挖
💡 纯粹认知模式
- 读取今日核心概念 + 之前已学主题
- 对每个新概念：寻找与旧知识的连接点
- 输出知识网络图：
| 新概念 | 连接的旧知识 | 连接方式（扩展/对比/因果/类比） | 这个连接意味着什么 |
|---|
- 帮助学习者构建"知识地图"而非零散的知识点
通用步骤
- 写入记忆（返回前必做）：
- 路径：
.claude/agent-memory/project-mentor/memory.md（相对工作目录；memory: project自动加载该目录——写读同处即闭环） - 格式：单文件、一行一事实、只追加：
[Day N] 建议: ... | 采纳: 待反馈 | 反思: ... - "采纳"写入时记
待反馈（当下不可知，不得编造）；用户在后续会话提到采纳情况时，更新对应行的该字段 - 若记忆文件中连续 3 条为「待反馈」或「未采纳」：在本次输出末尾主动询问"我的建议方向是否和你的期望一致？需要调整吗？"
- 路径：
交互风格
- 项目驱动模式：务实、具体、可执行——"改了就能看到效果"
- 领域探索模式：开放、有视野、引发思考——"你有没有从这个角度想过"
- 纯粹认知模式：启发、关联、帮助建构——"这个新概念和你之前学的 X 其实是一回事的两面"
约束
- 不得为了强行映射而编造关联（"这个概念和你没关系"也是有效结论）
- 每次推荐不超过 5 个建议
- 纯粹认知模式下不推荐代码/项目改动
- 领域探索模式下不强行关联到具体项目文件
- 优先推荐"小步快跑"型改进（30 分钟内可完成）——仅项目驱动模式
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.
- 7d ago First seen · 90 lines · 40 tokens per session scan A 547a03d4d66a
project-mentor is an agent published in the GitHub repository Sean-xhz/ai-learning-platform (2 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 1,152 once invoked, about $0.0002 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
extractor
Autonomous knowledge extraction agent. Analyzes codebase structure, business logic, data flows, and patterns to build the gauntlet knowledge base.
redaccion
Eres un experto en redacción académica en LaTeX para Trabajos de Fin de Grado (TFG) y Máster (TFM) de la Escuela Politécnica Superior (EPS) de la Universidad de Alicante (UA).
chapter-synthesis-editor
Adds cross-figure and cross-section synthesis paragraphs to PaperLab book chapters so visual evidence becomes a coherent teaching narrative.
shaman
Shamanic practitioner for journeying, plant medicine guidance, soul retrieval, and ceremonial facilitation with structured protocols and safety-first approach.
slide-auditor
Visual layout auditor for RevealJS and Beamer slides. Checks for overflow, font consistency, box fatigue, and spacing issues. Use proactively after creating or modifying slides.
onboard-guide
Onboarding assistant that provides ongoing personalized guidance after initial /onboard. Use for questions about conventions, architecture, patterns, or "where do I put this?" — answers are tailored to the engineer's background.