Wanwu is an enterprise platform for building AI agents, workflows, retrieval-augmented applications, and managing models in multi-tenant environments. It is designed for developers and enterprise teams delivering AI applications and integrations. The catalogue entries provide skills and agents for using the platform.
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/unicomai/wanwu/knowledge-spidernpx skills add UnicomAI/wanwu --skill knowledge-spidergit clone --depth 1 https://github.com/UnicomAI/wanwuWrote 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/unicomai/wanwu/knowledge-spider)<a href="https://agentmods.dev/skills/unicomai/wanwu/knowledge-spider"><img src="https://agentmods.dev/badge/skills/unicomai/wanwu/knowledge-spider.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 | $0.00000 | $0.00694 |
| Opus 5 | $0.00000 | $0.00347 |
| Sonnet 5 | $0.00000 | $0.00139 |
| Haiku 4.5 | $0.00000 | $0.00069 |
Grade A, and why
knowledge-spider 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 2d 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
name: knowledge-spider description: "本地知识库，支持存储、查询、删除和统计用户偏好、事实等信息。当用户提及「本地知识库」「我的知识库」或要求保存/查询/统计信息时使用。"
本地知识库技能
When to use (必须使用本技能的场景)
- 存储信息：当用户说“保存到本地知识库”、“记到我的知识库里”、“把这条信息加入知识库”等包含「本地知识库」「我的知识库」关键词的指令时，必须使用本技能。
- 查询信息：当用户问“我的知识库里有什么？”、“从本地知识库查找...”、“我的知识库中有关于...的记录吗？”时，必须使用本技能。
- 删除信息：当用户说“从知识库中删除...”、“忘掉这条记录”时，必须使用本技能。
- 统计信息：当用户问“我的知识库里有多少条记录？”、“统计一下我的知识库”、“知识库的状态如何”时，必须使用本技能进行统计并返回记录总数。
使用原则
- 优先使用知识库内容：当回答用户问题时，如果知识库中已有相关信息（如用户偏好、历史事实），应优先采用知识库中的内容进行回答，使回复更个性化和准确。
- 自然语言存储：当用户要求保存信息时，自动提取核心内容存入知识库。
触发词示例
- 保存到本地知识库
- 记到我的知识库里
- 从知识库查找...
- 我的知识库中有...吗？
- 统计我的知识库
- 知识库有多少记录
执行流程
- 识别意图：判断是存储、查询、删除还是统计
- 提取内容：清理"记录一下"等指令词，保留纯内容
- 执行操作：
- 存储：写入 SQLite，自动分类（preference/fact/task/important）
- 查询：语义搜索，按优先级排序返回
- 删除：确认后移除记录
- 统计：显示知识库状态
- 返回结果：用自然语言回复用户
分类标记
自动检测内容类型：
| 分类 | 检测关键词 | 说明 |
|---|---|---|
| preference | 喜欢、偏好、习惯、讨厌 | 用户偏好设置 |
| important | 重要、关键、密码、密钥 | 关键信息 |
| task | 任务、待办、截止、期限 | 待办事项 |
| fact | 事实是、数据、研究表明 | 客观事实 |
| general | 其他 | 一般信息 |
约束
- 存储前自动去重检测
- 查询结果按时效性、频率、类型优先级排序
- 删除前必须确认
- 所有数据本地存储，不上传云端
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 53 lines · 0 tokens per session scan A be5a575c1b66
knowledge-spider is a skill published in the GitHub repository UnicomAI/wanwu (2,456 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 694 tokens. 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 2026-09-03.
Other skills, from other repositories
dify
Use when building LLM applications with visual workflow — RAG knowledge bases, AI agents, chatbots with drag-and-drop orchestration. Dify: open-source LLM app platform supporting 30+ models (OpenAI, Claude, DeepSeek, Ollama, Qwen, GLM) with Docker deployment.
ai-skills
Use when building LLM applications, RAG knowledge bases, AI agents, terminal coding agents, multi-model orchestration, plugin-based agent harnesses, or file translation. Index of 9 skills: Dify, Hermes Agent, OpenClaw, OpenCode, Pi, DocuTranslate, Oh-My-OpenAgent, Superpowers-zh, DeepSeek Harness.
pinecone-research
Agent RAG and long-term memory with Pinecone.
memory-triage
Persistent long-term memory protocol powered by mem0. Evaluate conversations for durable facts worth storing via memoryadd. Handles identity, preferences, decisions, configurations, rules, projects, and relationships. Loaded by the openclaw-mem0 plugin when skills mode is active.
mem0-dream
Consolidates stored memories by merging duplicates, resolving contradictions, and pruning stale entries. Use when memory count is high, search results feel noisy or repetitive, or periodic cleanup is needed to maintain memory quality.
mem0-status
Diagnoses mem0 connectivity, API key validity, and memory read/write functionality. Use when memory operations fail, searches return empty, addmemory errors occur, or to verify the plugin is working correctly.