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/wechat-searchnpx skills add UnicomAI/wanwu --skill wechat-searchgit 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/wechat-search)<a href="https://agentmods.dev/skills/unicomai/wanwu/wechat-search"><img src="https://agentmods.dev/badge/skills/unicomai/wanwu/wechat-search.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 | $0.00030 | $0.00821 |
| Opus 5 | $0.00015 | $0.00411 |
| Sonnet 5 | $0.00006 | $0.00164 |
| Haiku 4.5 | $0.00003 | $0.00082 |
Grade A, and why
wechat-search 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.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WeChat Search Skill
Search for WeChat Official Account (微信公众号) articles using a compliant, three-layer approach that prioritizes legal search APIs and falls back to respectful web scraping when needed.
Features
- Compliant Design: Prioritizes legal search APIs, respects robots.txt and rate limits
- Three-Layer Strategy:
- Primary: OpenClaw web_search (Brave Search API)
- Secondary: Tavily Search API (if Brave unavailable)
- Fallback: Direct page fetching from WeChat search
- Recent Results: Returns the 5 most recent articles by default (configurable)
- Time Filtering: Support for date range and recency filters
- Multiple Output Formats: Text, JSON, and markdown formats available
Prerequisites
- OpenClaw Web Tools: Requires
web_search,web_fetchtools to be available - API Keys (optional but recommended):
- Brave Search API Key (for primary search)
- Tavily API Key (for secondary search, already configured in your environment)
Usage
Basic Search
wechat-search "人工智能"
Advanced Options
# Return 10 results instead of default 5
wechat-search "机器学习" --max-results 10
# Search within past week
wechat-search "大模型" --past-week
# Custom date range
wechat-search "AI应用" --from 2026-01-01 --to 2026-02-01
# JSON output format
wechat-search "开源AI" --output json
# Force specific strategy
wechat-search "最新技术" --strategy tavily_only
Configuration
Create ~/.openclaw/wechat-search-config.json to customize behavior:
{
"defaultMaxResults": 5,
"maxResultsLimit": 20,
"requestDelayMs": 5000,
"cacheDurationHours": 1,
"userAgent": "OpenClaw-WeChat-Search-Bot/1.0 (+https://github.com/your-username/wechat-search-skill)"
}
Search Strategy Details
Layer 1: OpenClaw Web Search (Brave Search)
- Uses Brave Search API with
site:mp.weixin.qq.comfilter - Fastest and most reliable when API key is configured
- Respects search engine's indexing and ranking
Layer 2: Tavily Search API
- Activated when Brave Search is unavailable or fails
- Uses Tavily's AI-powered search with WeChat site restriction
- Provides high-quality, relevant results with good coverage
What ships with it
9 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 · 101 lines · 30 tokens per session scan A 2d3afd2f56e5
wechat-search is a skill published in the GitHub repository UnicomAI/wanwu (2,458 stars, last pushed yesterday), licensed Apache-2.0. It adds 30 tokens to every session and 821 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 2026-09-03.
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.
Web2Skill
Convert one public website URL or an explicit batch of public URLs into a reusable skill zip backed by rendered HTML snapshots and a bounded JSONL retrieval index. Use to discover a documentation directory from one URL, crawl a supplied URL set sequentially, generate a source profile, or package indexed web content as…
Book2Skill
Convert one or more TXT, Markdown, DOCX, or PDF documents into a reusable skill zip backed by normalized Markdown, extracted images, and a grounded JSONL knowledge index. Invoke this skill before inspecting task files, then execute its workflow directly without listing directories.
agent-evaluation
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benc.
agent-orchestration-multi-agent-optimize
Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving agent performance, throughput, or reliability.
ai-engineer
Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations.