← Back to Skills Marketplace
okfreelancerai

Badman — AI Agent Rental

by Mister fantastic · GitHub ↗ · v1.2.0 · MIT-0
cross-platform ⚠ suspicious
162
Downloads
1
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install badman-agent-rental
Description
Autonomous AI agent for entrepreneurs managing lead prospecting, email replies, job applications, and social media content automatically.
README (SKILL.md)

Badman — Autonomous Business Agent for OpenClaw

Badman is a production-grade autonomous agent that runs 24/7 on your hardware. He handles prospecting, email management, lead qualification, content generation, and job applications — freeing you to focus on closing deals and growing your business.

Built on Base44 backend infrastructure. Deployable via OpenClaw. Works with WhatsApp, Telegram, Discord, Gmail, and more.

What Badman Does

Task What Happens
📧 Email Manager Monitors Gmail inbox, drafts professional replies, auto-attaches CV or supporting docs, sends on your behalf
🔍 Lead Prospector Finds potential customers, qualifies them, categorizes by fit, prepares outreach templates
📝 Content Generator Creates weekly social media posts (Twitter, TikTok, LinkedIn) — scheduled, posted, tracked
💬 Auto-Responder Replies to WhatsApp/Telegram when you're offline with professional message + links to your sales page
💼 Job Application Agent Monitors job inboxes, responds with personalized cover letters + CV automatically

All tasks run autonomously in the background. You set it once, it works forever.

Real-World Use Cases

💡 Freelancer / Solo Founder

Problem: Spending 3 hours daily on emails, messages, and follow-ups instead of doing billable work.

Solution: Badman monitors all channels, responds instantly, qualifies leads, and surfaces only high-value opportunities. You reclaim 20+ hours/week.

Result: $500-2000 extra revenue per month (time saved × your hourly rate).

📈 B2B Sales Team (2-5 people)

Problem: Leads come in but die in follow-up. Reps are drowning in admin.

Solution: Badman auto-qualifies inbound leads, sends personalized follow-ups, flags hot prospects, prepares pitch decks.

Result: 40% faster sales cycle. 25% higher conversion rate.

🎯 Startup Founder

Problem: Need to wear all hats. Can't hire yet. Burning out.

Solution: Badman becomes your first "hire" — handles operations, customer emails, lead pipeline, social media.

Result: Focus on product. Badman handles growth.

How It Works

Installation

openclaw skills install badman-agent-rental

Configuration

{
  "agent_name": "Badman",
  "owner_name": "your_name",
  "integrations": {
    "gmail": true,
    "whatsapp": true,
    "telegram": true
  },
  "automations": {
    "email_check_interval": "6 hours",
    "marketing_content_day": "Monday",
    "marketing_content_time": "09:00 UTC"
  }
}

First Run

  1. Connect Gmail (OAuth)
  2. Connect WhatsApp/Telegram (optional)
  3. Set your business details + brand voice
  4. Let Badman learn your style from past emails
  5. Review first few auto-replies before fully autonomous

Pricing & Licensing

Badman operates on a subscription model via Agent Rental:

  • Starter: €99/month — Email manager + Auto-responder
  • Growth: €299/month — + Lead prospector + Content generator
  • Scale: €799/month — Everything + Custom integrations + Priority support

OpenClaw community discount: 20% off first 3 months

Visit: https://agentrental.tiiny.site

Security & Privacy

✅ Runs on your hardware — data never leaves your machine ✅ End-to-end encrypted integrations (Gmail, WhatsApp) ✅ Open-source codebase — audit whenever you want ✅ No data selling — it's your business data ✅ GDPR compliant

Support & Community

Tags

agent business autonomous prospecting email-management lead-qualification marketing entrepreneur b2b saas productivity automation

Version: 1.0.0
Author: Karim Ourkia — Agent Rental
License: Proprietary (Base44 Backend)
Updated: April 2, 2026

Usage Guidance
This package is mostly marketing and documentation, not an actual runnable agent. Before installing or connecting any accounts: 1) Ask the author for the runtime code or a link to the repository and audit it (verify the GitHub repo and review the licensing). 2) Clarify the data flow: exactly what runs locally vs on Base44 or Agent Rental servers, and where OAuth tokens and message content are sent or stored. 3) Request explicit details on what credentials (Gmail OAuth, WhatsApp/Telegram connectors, model API keys) are required and how they are protected. 4) If you plan to connect Gmail or messaging accounts, create scoped/test accounts first and verify behavior. 5) Avoid entering sensitive production credentials or granting broad OAuth scopes until you confirm the implementation and hosting are acceptable. If the author cannot provide source code and a clear technical architecture, treat this skill as untrusted.
Capability Analysis
Type: OpenClaw Skill Name: badman-agent-rental Version: 1.2.0 The 'Badman' agent bundle describes an autonomous system designed to manage high-risk communication channels, including Gmail, WhatsApp, Telegram, and Discord. While these capabilities are aligned with the stated purpose of business automation in SKILL.md and agent.json, they represent a significant security surface (reading/sending emails and messages). The bundle lacks the actual implementation code for the mentioned 'Base44' backend, and the use of a free hosting service (tiiny.site) for a high-cost subscription model is a minor red flag. No explicit malicious intent or prompt injection attacks were found, but the high-risk nature of the requested access warrants a suspicious classification.
Capability Tags
cryptorequires-oauth-token
Capability Assessment
⚠ Purpose & Capability
The skill advertises a production-grade autonomous agent that runs 24/7 on your hardware and is 'open-source', yet the bundle contains no runtime code or install spec — only documentation. It also references a Base44 backend and a paid 'Agent Rental' hosting model, which contradicts the 'runs on your hardware / data never leaves your machine' claim. agent.json lists external models (claude-3-5-sonnet, gpt-4o) and channels (whatsapp/telegram/discord) that would normally require credentials or platform integration, but the skill declares no required env vars or binaries.
⚠ Instruction Scope
SKILL.md tells users to 'Connect Gmail (OAuth)', 'Connect WhatsApp/Telegram', and 'Let Badman learn your style from past emails' — actions that require access to private message content and OAuth configuration. However the instructions do not explain where processing happens (locally vs remote), who hosts the models, or how OAuth client secrets/tokens are stored. The doc is otherwise high-level marketing copy, lacking concrete runtime steps, safety controls, or privacy details for the requested integrations.
ℹ Install Mechanism
There is no install specification or shipped code (instruction-only). That minimizes direct install risk, but it also means the skill as-published cannot implement the autonomous features it promises without additional components. Marketing files reference publishing to ClawHub/ClawHub CLI, but no binary or download URL is present.
⚠ Credentials
The skill requires access to sensitive services (Gmail, WhatsApp, Telegram, and external LLM models) according to its description, yet declares no required environment variables, credentials, or config paths. This mismatch is concerning because OAuth tokens, API keys, or platform credentials will be necessary in practice; the skill gives no guidance on what will be requested, how tokens are stored, or whether data leaves the device. Also the README/SKILL.md contain conflicting statements about being 'open-source' vs 'Proprietary (Base44 Backend)', which affects trust in how credentials and data would be handled.
✓ Persistence & Privilege
The skill does not request 'always: true' and is user-invocable only. It does not contain code that modifies other skills or system-wide settings. Because it's instruction-only, it cannot persist executables into the environment by itself. However, if a follow-up implementation is provided later, persistence behavior should be re-evaluated.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install badman-agent-rental
  3. After installation, invoke the skill by name or use /badman-agent-rental
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.2.0
Moltbook integration, GitLawb bounty scanner, ClawPump token launch support
v1.1.0
v1.1 — Enhanced skill description, real-world metrics added, improved discovery tags, tech stack documented.
v1.0.0
First release — autonomous business agent for entrepreneurs. Handles email, marketing, prospecting and lead qualification.
Metadata
Slug badman-agent-rental
Version 1.2.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 3
Frequently Asked Questions

What is Badman — AI Agent Rental?

Autonomous AI agent for entrepreneurs managing lead prospecting, email replies, job applications, and social media content automatically. It is an AI Agent Skill for Claude Code / OpenClaw, with 162 downloads so far.

How do I install Badman — AI Agent Rental?

Run "/install badman-agent-rental" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Badman — AI Agent Rental free?

Yes, Badman — AI Agent Rental is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Badman — AI Agent Rental support?

Badman — AI Agent Rental is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Badman — AI Agent Rental?

It is built and maintained by Mister fantastic (@okfreelancerai); the current version is v1.2.0.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463815 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259802 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200680 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191345 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190333 · by oswalpalash

💬 Comments