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 skills add UnicomAI/wanwu --skill customizegit 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/customize)<a href="https://agentmods.dev/skills/unicomai/wanwu/customize"><img src="https://agentmods.dev/badge/skills/unicomai/wanwu/customize/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/unicomai/wanwu/customize"><img src="https://agentmods.dev/badge/skills/unicomai/wanwu/customize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 156 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00088 | $0.05336 |
| Opus 5.5 | $0.00035 | $0.02134 |
| Sonnet 5.5 | $0.00018 | $0.01067 |
| Haiku 4.5 | $0.00009 | $0.00534 |
Grade A, and why
customize scanned grade A with 1 finding 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 1mo 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
return subprocess.run([sys.executable, tool, cfg_path], How it starts
The opening of the file, as written. The whole thing — 458 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customize
Build and maintain agent profiles and skills programmatically via the
repl tool using host.agents.* and host.skills.*.
A profile is a named bundle that shapes how an agent behaves:
system_prompt— the profile's identity. This is the opening of the agent's system prompt; it REPLACES the generic "You are Claude Science" base identity. Write it in second person, lead withYou are {display_name}, ..., state what the agent specializes in and what it does NOT do. Everything else (tool-usage rules, working-style bullets, scope guardrail) is inherited automatically — don't restate it.display_name/description/icon_key/color_key— picker metadata.skill_names(optional restriction) — by default a profile sees the full live skill catalog viasearch_skills/skill(...), same as the main agent. Pass an explicit list ONLY to deliberately restrict it;[]creates a zero-skill specialist. Restricting skills also restricts connectors — a singleunrestrictedflag governs both; passingskill_namesflips the profile to curated mode and starts it with zero connectors (see next).- Connector access — an unrestricted profile (the default) reaches
every connector (bundled + custom + authorized directory), same as the
main agent; use
detach_connectorto subtract specific ones. A curated profile (one created with an explicitskill_nameslist, or flipped via{"unrestricted": False}) starts with no connectors — reach is exactly what youattach_connector. excludedTools— per-tool blocklist applied after connectors resolve. Use to strip specific high-risk or irrelevant tools from an otherwise-useful connector. Per-connector, not a profile field — set viaattach_connector(..., include_tools_pattern=/exclude_tools_pattern=); the profile'sexcludedToolsinlist()is the read-only aggregation across all its attached connectors. Patterns match the connector's bare tool names (e.g.'^list_marts$', as returned bylist_connectors(name)['tools']); the aggregatedexcludedToolsentries are stored fully-qualified asmcp_<connector>_<tool>since the list spans every attached connector.
What ships with it
1 file 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.
- 1mo ago First seen · 458 lines · 88 tokens per session scan A af31c7054522
customize is a skill published in the GitHub repository UnicomAI/wanwu (2,371 stars, last pushed 3d ago), licensed Apache-2.0. It adds 88 tokens to every session and 5,336 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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 14 skills: Dify, LangChain, LlamaIndex, Ollama, Transformers, Hermes Agent, OpenClaw, OpenCode, Pi, DocuTranslate, DeepSeek Harness and more.
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-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.
agenttrace-session-audit
Audit local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates.