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/auuduu/dsh-timem-memory/timem-knowledgenpx skills add auuduu/dsh-timem-memory --skill timem-knowledgegit clone --depth 1 https://github.com/auuduu/dsh-timem-memoryWrote 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/auuduu/dsh-timem-memory/timem-knowledge)<a href="https://agentmods.dev/skills/auuduu/dsh-timem-memory/timem-knowledge"><img src="https://agentmods.dev/badge/skills/auuduu/dsh-timem-memory/timem-knowledge.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 | $0.00128 | $0.00988 |
| Opus 5 | $0.00064 | $0.00494 |
| Sonnet 5 | $0.00026 | $0.00198 |
| Haiku 4.5 | $0.00013 | $0.00099 |
Grade A, and why
timem-knowledge 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.
What it actually says
TiMEM Knowledge Base（DSH 适配版）
编排知识库操作 —— 搜索、上传、列出 —— 只用 MCP 原子工具。
可用性检查
TiMEM 工具在 DSH 中以 mcp__timem__* 命名。若工具列表中不存在这些工具，说明 TiMEM MCP 未连接——跳过本 skill，不要猜别的工具名。
每回合清单
- [ ] 1. 这是知识库任务吗？
- [ ] 2. 搜索 → mcp__timem__search_knowledge(query=...)
- [ ] 3. 上传 → mcp__timem__upload_document(file_content=..., filename=...)
- [ ] 4. 列出/查看 → mcp__timem__list_knowledge_bases() 或 mcp__timem__list_documents()
- [ ] 5. 对照用户问题核实结果
- [ ] 6. 回答用户
何时搜索知识库
仅当以下情况用 mcp__timem__search_knowledge：
- 用户的问题可能由已上传文档（PDF、文档、笔记）回答
- 用户明确要求查自己的知识库
- 答案依赖之前上传文件的内容
以下情况不要用 mcp__timem__search_knowledge：
- 个人偏好或对话历史 → 用
mcp__timem__search_memories - 模型本身就知道的常识
- 代码仓库问题 → 用
mcp__timem__search_memories(domain="coding")
何时上传
以下情况用 mcp__timem__upload_document：
- 用户发来文件并说「加入知识库」「归档」「上传到知识库」
- 用户想存一份文档供以后检索
- 用户粘贴内容并明确要进知识库
不要上传：
- 对话片段 → 用
mcp__timem__create_memory - 无复用价值的临时内容
何时列出
mcp__timem__list_knowledge_bases()—— 用户问「我有哪些知识库？」或首次搜索前拿不准mcp__timem__list_documents()—— 检查上传是否处理完成，或浏览知识库内容
kb_id 指引
| 情形 | kb_id |
|---|---|
| 默认 / 用户未指定 | 省略 —— 自动解析到默认知识库 |
| 用户指定具体知识库 | 传 mcp__timem__list_knowledge_bases 结果里的 kb_id |
知识库 vs 记忆
| 维度 | 知识库 | 记忆 |
|---|---|---|
| 来源 | 上传文件（PDF、MD、TXT…） | 对话轮次 |
| 内容 | 文档、参考资料、笔记 | 偏好、决策、经验 |
| 工具 | mcp__timem__search_knowledge / mcp__timem__upload_document |
mcp__timem__search_memories / mcp__timem__create_memory |
| 范围 | 按知识库 | 按 domain + session |
两类都能回答时，事实/文档内容优先知识库，个人/历史背景优先记忆。
反模式
- 不要把
mcp__timem__search_knowledge当mcp__timem__search_memories的替代品 - 不要上传对话记录 —— 用
mcp__timem__create_memory - 不要调用
should_*、begin_coding_turn、end_coding_turn - 上传时
file_content必须 Base64 编码
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 · 85 lines · 128 tokens per session scan A a36f9e791b7c
timem-knowledge is a skill published in the GitHub repository auuduu/dsh-timem-memory (0 stars, last pushed 17d ago), licensed MIT. It adds 128 tokens to every session and 988 once invoked, about $0.0006 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
write-docs-cn
Skill "write-docs-cn" from pingfanfan/hello-dsh, covering 写项目文档, 放在哪, readme 的结构, 名字 and 安装 / 快速开始.
write-tech-cn
当需要写中文技术文档、README、博客、教程或技术说明时使用——去掉翻译腔和 AI 味，先给结论和可执行动作，术语中英混排按中文习惯处理。.
okfy
Use when a user wants an agent to use docs through OKFy, set up or verify an OKFy MCP docs source, convert docs websites or local Markdown into OKF bundles, generate activation proof, or answer from an existing OKFy bundle/workspace.
doc-parse
将 PDF/PPT/Excel/Word 等多格式文档解析为结构化 Markdown，并输出元数据与解析置信度，作为 RAG 与四色卡片的数据底座。.
google-workspace-ops
Operate across Google Drive, Docs, Sheets, and Slides as one workflow surface for plans, trackers, decks, and shared documents. Use when the user needs to find, summarize, edit, migrate, or clean up Google Workspace assets without dropping to raw tool calls.
nutrient-document-processing
Process, convert, OCR, extract, redact, sign, and fill documents using the Nutrient DWS API. Works with PDFs, DOCX, XLSX, PPTX, HTML, and images. Use when converting, OCRing, extracting from, redacting, signing, or filling documents via the Nutrient DWS API.