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 bsessiongit 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/bsession)<a href="https://agentmods.dev/skills/unicomai/wanwu/bsession"><img src="https://agentmods.dev/badge/skills/unicomai/wanwu/bsession/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/bsession"><img src="https://agentmods.dev/badge/skills/unicomai/wanwu/bsession.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
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 →
- medium Rogue Agent · line 3 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Server-Side Request Forgery · line 126 Code issues a request to a loopback, link-local, or private-range host. This can reach internal services not meant to be exposed and is a common SSRF pivot.Fix: Avoid requests to loopback/link-local/private hosts from skill code. If internal access is intended, document it and validate the target against an allowlist.
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 | $0.00040 | $0.01975 |
| Opus 5.5 | $0.00016 | $0.00790 |
| Sonnet 5.5 | $0.00008 | $0.00395 |
| Haiku 4.5 | $0.00004 | $0.00198 |
Grade A, and why
browser 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
import urllib.request How it starts
The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/browser skill
You help users automate browsers inside the bsession Docker container — whether it's initial setup, a quick interactive fetch, a scripted automation (one-shot or recurring), or debugging an existing session.
This is a global skill — it works from any repo. bsession is installed at ~/.bsession/, and the bsession CLI is on PATH.
Resolve paths
Before doing anything, determine how to reach bsession. Check in this order:
bsessionon PATH → usebsession~/.bsession/bsessionexists → use~/.bsession/bsession./bsessionin current directory → use./bsession- None found but container is running (
docker exec agent-browser echo ok) → usedocker exec agent-browser python3 /app/session.pyas the CLI
Similarly, resolve workspace:
~/.bsession/workspace/exists → use it./workspace/in current directory → use it- Ask
docker exec agent-browser ls /workspace/conf→ use docker exec to access files
Use these resolved paths for all commands throughout the session.
Constants (defaults)
- BSESSION_HOME:
~/.bsession/— where bsession source + docker-compose live - WORKSPACE:
~/.bsession/workspace/(default, overridable) — or resolved per above - bsession CLI: resolved per above
Routing
Parse the user's slash command arguments:
- No arguments or
list→ List mode (show all available scripts and sessions) setup→ Setup mode (install and configure bsession)fetch <url>→ Fetch mode (interactive one-shot extraction, with option to persist)new <name>→ Create mode (scaffold a script — one-shot or recurring)run <name>→ Run mode (execute a saved session and show results)- Otherwise → Debug mode (inspect/fix an existing session)
Pre-check (all modes except setup)
Before running any mode except setup, verify the container is running:
docker exec agent-browser echo ok 2>/dev/null
If this fails, tell the user to either:
- Run
/browser setupfor a fresh install, or - Run
docker compose up -dfrom the bsession project directory
What ships with it
3 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.
- 1mo ago First seen · 255 lines · 40 tokens per session scan A 2eb0360e8cee
browser is a skill published in the GitHub repository UnicomAI/wanwu (2,372 stars, last pushed 4d ago), licensed Apache-2.0. It adds 40 tokens to every session and 1,975 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
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…
browserwing-executor
Control browser automation through HTTP API. Supports page navigation, element interaction (click, type, select), data extraction, accessibility snapshot analysis, screenshot, JavaScript execution, and batch operations.
dev-browser
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website"…
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.
genbi
Turn a Wren project's context layer into a shareable, browser-side GenBI web app and deploy it to the user's Vercel or Cloudflare account. Orchestrates the full flow: wren genbi build returns a project-hydrated build instruction, the agent authors the app from scratch into apps/ /, then register → verify → deploy…
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.