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 skills/ryanzhao1011/workframe/material-intakenpx skills add ryanzhao1011/workframe --skill material-intakegit clone --depth 1 https://github.com/ryanzhao1011/workframeWrote 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/skills/ryanzhao1011/workframe/material-intake)<a href="https://agentmods.dev/skills/ryanzhao1011/workframe/material-intake"><img src="https://agentmods.dev/badge/skills/ryanzhao1011/workframe/material-intake.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 | $0.00099 | $0.03712 |
| Opus 5 | $0.00049 | $0.01856 |
| Sonnet 5 | $0.00020 | $0.00742 |
| Haiku 4.5 | $0.00010 | $0.00371 |
Grade A, and why
material-intake 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 3d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
存量资料入库分流
前置依赖
调用前需读 skill: document-norms §1（归属矩阵）——分流判定的落点依据以其为准，本 skill 不另立一套归属规则。
定位
面对一堆来源混杂、形态不一的存量资料，先摸清楚、再定去向、最后才动手。本 skill 只做前两件事加一个结构提议，不搬运、不改写、不归档。
三段能力：
| 段 | 做什么 | 产出 |
|---|---|---|
| 盘点 | 扫描给定路径，按形态分类计数，标出无法解析的项 | 资料台账 |
| 分流 | 按形态逐批判定去向 | 分流计划（每批 → 哪个 skill） |
| 结构推荐 | 从资料聚类推荐 basic/sub 模块树 | 模块树初稿 + 证据 |
两个调用场景
| 场景 | 谁调 | 执行深度 |
|---|---|---|
| 接入 / 新建时（含 A 路径引参考资料） | workframe-launcher 的 setup skill（读本 SOP 照做） |
本 skill 产出计划（盘点 + 分流 + 结构提议 + 处置方案）进结构闸；确认后的执行层层递进：结构闸拍树 → launcher 建树 → 逐模块深读后确认并当场安置，整理归档按节奏闸拍板 |
| 接入之后项目内补料 | 用户直接调用 | 同样只出计划；用户确认后调对应执行 skill 当场执行 |
本 skill 始终只出计划——执行是调用方的事。装机会话的执行能力由 module_init.py
（确定性建树）+ 磁盘可读的各执行 skill SOP 保障，不再有「接入阶段撞上半成品环境」的限制。
Phase 1 盘点
1.0 两级盘点（2026-08-11 起，防「一次深读全部」拖垮体验）
| 级 | 深度 | 何时 | 供给 |
|---|---|---|---|
| 粗扫 | 形态计数 + 标题级抽样（md 读 H1/H2、docx 读标题与首段、xlsx 读表头），不逐字读全文 | 接入 / 新建流程的分析阶段 | 台账 + 模块树提议（结构闸） |
| 深读 | 逐份读懂内容 | 建树后逐模块进行 | 该模块的安置 + 处置方案（逐模块小闸） |
台账在粗扫级即须 100% 全覆盖（每份文件有一行——覆盖指「登记过」，不指「读完了」）； 深读按模块分批推进，不要求一次读完全部。
1.1 收料冻结
先划定范围并冻结：列出所有待盘点路径，之后新增的资料算下一批，不中途扩范围。范围内的每一份文件都必须在台账里有一行——不许因为「看着不重要」就跳过，判定为「不入库」也要写明理由。
每条路径必须标注在项目内还是项目外（内 / 外）——这一位决定下游是「搬」还是「拷」，见 §2.1。
1.2 按形态分类
| 形态 | 识别方式 |
|---|---|
| 规范 / 半规范 md | .md，有 H1、章节结构或 frontmatter |
| 零散 md / txt | .md / .txt，无结构 |
| 异构原料 | .docx / .xls(x) / .pdf / 截图 / 原型文件 |
| 在线文档链接 | 正文里的飞书 / Notion / 网页 URL，本地无副本 |
| 源码 | 按脚手架识别（package.json / pom.xml / requirements.txt 等） |
| 无法解析 | 二进制、加密、损坏，或缺解析库 |
1.3 台账
资料台账（范围：<冻结的路径清单>，冻结于 <时间>）
| # | 路径 | 源位置 | 形态 | 数量 | 备注 |
|---|---|---|---|---|---|
| 1 | docs/ | 内 | 规范 md | 43 | 有 frontmatter 的 12 份 |
| 2 | 需求归档/ | 内 | 异构原料 | 31 | docx 18 / xls 7 / 截图 6 |
| 3 | D:/老项目/specs/ | 外 | 规范 md | 20 | 跨项目导入，只拷不删 |
...
覆盖率：已分类 <N> / 总数 <M>；无法解析 <K>（原因逐条列出）
缺解析库不中断盘点：对应文件在台账标注「缺哪个库、怎么装」，装完重跑即可。
Phase 2 分流
2.1 搬还是拷（先定这一位，再谈去向）
去向按资料形态判（下表）；动作按源位置判：
| 源位置 | 动作 | 对源目录 |
|---|---|---|
| 项目内 | 搬（迁完源即消失） | 可删，按各执行 skill 自己的删源 SOP |
| 项目外 | 拷（源原封不动保留） | 只读——禁止任何写、移动、删除 |
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.
- 3d ago First seen · 196 lines · 99 tokens per session scan A 8a1fb82a6194
material-intake is a skill published in the GitHub repository ryanzhao1011/workframe (4 stars, last pushed 16d ago), licensed MIT. It adds 99 tokens to every session and 3,712 once invoked, about $0.0005 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 skills, from other repositories
check-understanding
Phase quiz for AI Engineering from Scratch. Trigger with "quiz me", "test phase", "check my understanding", "do I know phase 3", or /check-understanding .
find-your-level
Interactive quiz that maps your AI/ML knowledge to a starting point in the 260-lesson, 20-phase AI Engineering from Scratch curriculum. Trigger phrases: "where should I start", "find my level", "what do I know", "which phase", "assess my knowledge", "placement test", "skip ahead".
agent-memory-mcp
A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
eval-agents
Audit Claude Code agents defined in .claude/agents/ for description specificity, model tier appropriateness, tools scoping, and system prompt quality. Detects dispatch ambiguity between agents, flags over-permissive tool grants, and checks for human-in-the-loop patterns that break programmatic orchestration. Use when…
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.
autoresearch
Autonomous improvement loop: scan codebase metrics, scaffold experiment files, run agent-driven iterations until metric improves.