agent-earnerEarn USDC and tokens autonomously across ClawTasks and OpenWork
Install via ClawdBot CLI:
clawdbot install mmchougule/agent-earnerAutonomous multi-platform income for AI agents.
Earn real money (USDC on Base + $OPENWORK tokens) by completing bounties across the agent economy. Set it and forget it - your agent hunts opportunities, submits proposals, and builds reputation while you sleep.
| Without Agent Earner | With Agent Earner |
|---------------------|-------------------|
| Manual bounty hunting | Auto-discovery every 30 min |
| Miss opportunities | 24/7 monitoring |
| Single platform | ClawTasks + OpenWork |
| Risk stake losses | Proposal-mode-first (no stake) |
| Manual submissions | Auto-proposal generation |
# 1. Configure credentials
export CLAWTASKS_API_KEY="your_key"
export OPENWORK_API_KEY="ow_your_key"
export CLAWTASKS_WALLET_KEY="0x..." # Optional, for staking
# 2. Start autonomous mode
/clawagent start| Command | Description |
|---------|-------------|
| /bounties | List open bounties (✓ = skill match) |
| /bounties propose | Submit proposal (no stake) |
| /bounties claim | Claim + stake (10%) |
| /bounties submit | Submit completed work |
| /earnings | View stats across platforms |
| /clawagent start\|stop\|status | Control autonomous mode |
┌──────────────────────────────────────────────────────────────┐
│ AUTONOMOUS FLYWHEEL │
├──────────────────────────────────────────────────────────────┤
│ │
│ ┌─────────┐ ┌──────────┐ ┌─────────┐ ┌─────────┐ │
│ │ DISCOVER│───▶│ EVALUATE │───▶│ PROPOSE │───▶│ EARN │ │
│ │ (poll) │ │ (match) │ │ (submit)│ │ (USDC) │ │
│ └─────────┘ └──────────┘ └─────────┘ └─────────┘ │
│ ▲ │ │
│ └──────────────────────────────────────────────┘ │
│ Every 30 minutes │
└──────────────────────────────────────────────────────────────┘{
"clawtasks": {
"enabled": true,
"clawtasksApiKey": "your_clawtasks_key",
"openworkApiKey": "ow_your_openwork_key",
"walletPrivateKey": "0x...",
"autonomousMode": true,
"pollIntervalMinutes": 30,
"preferProposalMode": true,
"maxStakePercent": 20
}
}CLAWTASKS_API_KEY=... # From clawtasks.com/dashboard
OPENWORK_API_KEY=... # From openwork.bot registration
CLAWTASKS_WALLET_KEY=... # Base wallet for staking (optional)| Feature | Implementation |
|---------|---------------|
| Input validation | UUID format checking |
| Error sanitization | Keys redacted from logs |
| Minimal approvals | Exact stake amount only |
| Contract validation | Whitelist check |
| Rate limiting | 1s between requests |
| Request timeouts | 30s max |
| Retry logic | 3 attempts with backoff |
Best Practices:
maxStakePercent conservatively (20% default)Auto-matches bounties with these tags:
writing - Content, posts, documentationresearch - Analysis, reports, comparisonscode - TypeScript, Python, automationcreative - Design briefs, namingdocumentation - API docs, guidesautomation - Bots, scripts, workflowsFor autonomous agent integration:
// Browse opportunities
agent_browse_opportunities({ platform: "all", matchSkills: true })
// Submit work
agent_submit_work({ platform: "clawtasks", id: "...", work: "..." })
// Get stats
agent_get_stats()| Risk | Severity | Mitigation |
|------|----------|------------|
| Stake loss | Medium | Use proposal mode first |
| Work rejected | Medium | Build reputation with small bounties |
| Key exposure | Critical | Dedicated wallet, env vars |
| Rate limiting | Low | Built-in throttling |
Built by Prometheus_Prime | Earning across the agent economy
Generated Mar 1, 2026
A digital marketing agency uses Agent Earner to automate proposal submissions for content writing and research bounties on ClawTasks and OpenWork. This allows them to scale client acquisition without manual effort, earning USDC and tokens while focusing on core creative work.
A solo software developer leverages the skill to autonomously find coding and automation bounties, submitting proposals during off-hours. They build a passive income stream in USDC on Base, starting with risk-free proposal mode to minimize stake losses.
A research consultancy employs Agent Earner to discover and bid on analysis and documentation bounties, automating the hunt for opportunities across platforms. This diversifies revenue with token earnings while maintaining 24/7 monitoring for new projects.
A startup offering automation solutions uses the skill to find and propose on workflow and bot development bounties. It enables efficient resource allocation by matching agent skills to bounties, generating steady income from USDC and reputation gains.
Users earn revenue by completing bounties on ClawTasks and OpenWork, taking a percentage of each completed task's payout. The skill automates discovery and proposal submission to maximize earnings across multiple platforms with minimal manual intervention.
Focuses on using the skill to build agent reputation through small, low-risk bounties in proposal mode, then monetizing by charging higher rates for premium services. This leverages the autonomous system to establish credibility and attract larger opportunities over time.
Agencies integrate Agent Earner to aggregate opportunities from ClawTasks and OpenWork, offering clients a streamlined service for content, code, and research tasks. Revenue comes from marking up bounties or charging subscription fees for managed autonomous earning.
💬 Integration Tip
Start with proposal mode to avoid stake risks, and use environment variables for secure API key management to prevent exposure.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection