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 skills add junqiu520/feishu-memory-mcp --skill feishu-memorygit clone --depth 1 https://github.com/junqiu520/feishu-memory-mcpWrote 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/junqiu520/feishu-memory-mcp/feishu-memory)<a href="https://agentmods.dev/skills/junqiu520/feishu-memory-mcp/feishu-memory"><img src="https://agentmods.dev/badge/skills/junqiu520/feishu-memory-mcp/feishu-memory/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/junqiu520/feishu-memory-mcp/feishu-memory"><img src="https://agentmods.dev/badge/skills/junqiu520/feishu-memory-mcp/feishu-memory.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00044 | $0.01012 |
| Opus 5 | $0.00022 | $0.00506 |
| Sonnet 5 | $0.00009 | $0.00202 |
| Haiku 4.5 | $0.00004 | $0.00101 |
Grade A, and why
feishu-memory 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 8d 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
feishu-memory MCP 技能
你可以通过 feishu-memory-mcp 访问一个共享的 RAG 记忆库。用于跨会话持久化——当用户要求你"记住这个"，或者你识别出可复用的知识，或者你需要查找过去的上下文时使用。
何时使用
| 用户说 | 工具 |
|---|---|
| "记住这个偏好 / 存这条经验 / 记录这个教训" | memory_add(scope="memory") |
| "帮我存这份规范 / 把这份文档存到知识库" | memory_add(scope="knowledge") |
| "我之前讲过 X 吗 / 找那条关于 Y 的记忆" | memory_query |
| "展开看那条 / 给我完整内容" | memory_get（需要先有 record_id） |
| "改一下标签 / 改标题" | memory_update |
| "忘掉这条 / 删除" | memory_delete（需要 confirm: true） |
| "列出我有哪些 X" | memory_list 或 memory_count |
| "同步一下 / 拉取最新" | memory_sync |
| "把这个 PDF 上传到飞书 / 把这个文件存档" | file_upload |
Scope 选择
memory（默认）：存储可复用的经验、用户的偏好/教训、事件里程碑等。 不要用于：临时上下文（对话中直接保留）、系统指令（不是记忆）。knowledge：存储用户的材料/文件（规范、文档、笔记等），但需要你先解析附件内容为文本。 file_ref 需要先调用 file_upload 工具获取 file token + URL。- 不确定？先用
memory。
查询模式选择
| 查询意图 | mode |
|---|---|
| 默认；混合意图；需要最佳结果 | "hybrid_rerank" |
| 精确匹配名称/日期/ID/缩写 | "bm25_only" |
| 抽象概念/相似表述 | "vector_only" |
| 想跳过重排以加速 | "hybrid" |
重排会花费额外时间和少量 CPU，但能显著提升长查询的质量。除非优化延迟，否则默认使用 "hybrid_rerank"。
文件上传
文件（PDF/PPT/图片）不能直接嵌入。添加文件内容的步骤：
- 通过 MCP 工具上传到飞书云盘：
file_upload(file_paths=["/path/to/file.pdf"])。传入一个列表可以一次上传多个文件。 每条路径返回自己的状态条目；单个失败不会中止其他文件。 - 从响应中获取每个成功上传的
file_token和url。 - 使用你的原生文件读取能力（Claude/GPT-4o vision 等）将每个文件转换为文本。
- 对每个文件调用
memory_add(text=<转换后的文本>, file_ref={type: "drive_file", token, url})。
file_ref 是元数据，让用户可以点击跳转到飞书中的原文档；可搜索的内容是你传入的 text。
同步
如果搜索结果看起来过时——比如用户说"我昨天加过那个"但你找不到——调用：
memory_sync(mode="incremental")
不要调用 memory_sync(mode="rebuild")，除非用户报告缓存损坏；rebuild 会重新嵌入所有内容，很慢。
不要使用的情况
- 会话内临时上下文——直接在对话中保留就好
- 系统提示/指令——这些不是记忆
- 用户明确说"不要记住"的数据
跨 scope 搜索
搜索一个 scope 不会自动搜索另一个。要搜索两个库：
- 调用
memory_query(scope="memory", ...) - 调用
memory_query(scope="knowledge", ...) - 合并结果
MCP 工具故意没有 scope="both" 参数——CLI 的 feishu-memory sync --scope both 用于运维，但每次查询时 agent 决定查询哪个库。
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.
- 8d ago First seen · 80 lines · 44 tokens per session scan A 9c4c4d463920
feishu-memory is a skill published in the GitHub repository junqiu520/feishu-memory-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 1,012 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 skills, from other repositories
pinecone-research
Agent RAG and long-term memory with Pinecone.
langchain
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG…
browserwing-admin
Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.
mem0-integration
Mem0 memory layer integration for AI agents. Implement persistent, semantic memory for long-term context retention and personalization.
install-openviking-memory
Install and configure the OpenViking long-term memory plugin for OpenClaw via natural conversation. Once installed, the plugin automatically captures facts from chats and recalls relevant context before each reply (auto-capture + auto-recall, cross-session). Covers prerequisites, install through OpenClaw's plugin…
wegent-knowledge
Knowledge base management and search tools for Wegent. Provides capabilities to list, create, update, and search knowledge bases and documents using RAG retrieval. Use this skill when the user wants to manage knowledge bases, documents, or search for information programmatically.