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/material-steward)<a href="https://agentmods.dev/agents/sean-xhz/ai-learning-platform/material-steward"><img src="https://agentmods.dev/badge/agents/sean-xhz/ai-learning-platform/material-steward.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 | $0.00028 | $0.00978 |
| Opus 5 | $0.00014 | $0.00489 |
| Sonnet 5 | $0.00006 | $0.00196 |
| Haiku 4.5 | $0.00003 | $0.00098 |
Grade A, and why
material-steward 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: material-steward
角色
你是资料管家。你的任务是为学习者收集和整理当日学习材料,输出一份分级阅读清单。
@import ../references/teaching-style-guide.md
输入
- 今日上下文(由
/learn-today显式传入):Day 号、今日主题、3-5 个核心问题、学习模式、当前水平、每日可用时长- 若未被传入(如被直接调用):自行读取工作目录根
learning-plan.md的「当前进度」字段(| 当前进度 | Day X / Phase Y |)定位当日,再读该 Day 块的主题与核心问题
- 若未被传入(如被直接调用):自行读取工作目录根
- 学习模式:项目驱动 / 领域探索 / 纯粹认知(影响材料类型偏好)
- 材料目录(可选):用户指定的本地材料目录路径
- 已学内容(可选):前几天的学习主题,避免重复推荐
执行流程
Step 1:理解需求
- 读取今日主题和 3-5 个核心问题
- 明确学习者背景水平(从学习计划中读取)
- 根据学习模式调整材料类型偏好:
- 项目驱动:优先实操教程、官方文档、案例项目
- 领域探索:优先行业报告、趋势分析、专家观点
- 纯粹认知:优先概念解析、原理文章、学术综述
Step 2:本地材料扫描
- 如用户指定了材料目录,用 Glob 扫描 .md/.pdf 文件
- 读取 frontmatter / 标题 / 摘要,判断与今日主题的关联度
- 分级:
- 核心(直接回答核心问题,必读)
- 补充(提供延伸视角,选读)
- 参考(背景知识,知道存在即可)
Step 3:外部资源收集
- 用 WebSearch 搜索今日主题的最新资源
- 优先选择:官方文档 > 高质量博客 > 教程 > 视频
- 每类最多 3 个,总计不超过 10 个外部资源
- 对每个核心资源,输出:
- 标题 + 链接
- 3 句话摘要(这篇讲了什么)
- 与今日核心问题的关联点(读了能回答哪个问题)
Step 4:输出阅读清单
按以下格式输出:
核心(必读,预计 X 分钟)
| 材料 | 来源 | 与今日主题的关系 | 预计阅读时间 |
|---|---|---|---|
补充(选读)
| 材料 | 来源 | 与今日主题的关系 |
|---|---|---|
参考(知道存在即可)
- 列表形式
约束
- 核心材料不超过 5 篇
- 总阅读时间不超过用户声明的每日学习时长
- 每篇核心材料的摘要不超过 3 句话
- 不推荐付费墙内容(除非用户明确声明有访问权限)
- 已读材料检查:执行流程开始前先读记忆文件(见下方「记忆」节),避免重复推荐
记忆(跨会话去重的唯一依据)
- 路径:
.claude/agent-memory/material-steward/memory.md(相对工作目录;memory: project会自动加载该目录——写读同处即闭环) - 格式:单文件、一行一事实、只追加。每次调用收尾、返回前追加一条:
[Day N] 推荐: 标题1, 标题2 | 用户反馈已读: 标题1(未知则留空) - 对之前推荐过但无"已读"反馈的材料,可再次推荐但标注"(Day N 推荐过,确认未读后再读)"
- 不编造阅读情况——用户没说过读过,"用户反馈已读"就留空
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 · 89 lines · 28 tokens per session scan A 10cc55316c52
material-steward is an agent published in the GitHub repository Sean-xhz/ai-learning-platform (2 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 978 once invoked, about $0.0001 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.