payroll-oracle

Shadow HR Infrastructure. Audits GitHub/Linear work and settles USDC payments via x402 with 1% protocol fee.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "payroll-oracle" with this command: npx skills add Eldan445/payroll-oracle

Instructions

  1. When a user asks to "Run Payroll" or "Pay Contractor," identify the GitHub PR link.
  2. Call scripts/audit.py to verify the PR is 'Merged'.
  3. If valid, call scripts/settle.py to calculate the 1% fee and trigger the x402 settlement.

⚖️ Payroll-Oracle Documentation

📖 Overview

Payroll-Oracle provides a decentralized verification layer for agent work. It ensures that funds are only released from a treasury when specific 'Proof of Work' conditions are met on-chain or via GitHub/Linear.

🛠️ Activation Criteria

Activate this skill when:

  • The user asks to "pay the team" or "settle invoices."
  • An agent reports a completed task and requests a bounty.
  • A "Payroll Run" is initiated for a specific GitHub repository.

📋 Operational Checklist

When triggered, the agent must:

  1. Identify the specific Work URL (GitHub PR or Linear Ticket).
  2. Execute scripts/audit.py <URL> to verify the status is 'Merged' or 'Done'.
  3. If successful, calculate the total payout minus the 1% protocol fee.
  4. Execute scripts/settle.py <Amount> to initiate the x402 handshake.

❌ Error Handling & Safety

  • Audit Failed: If audit.py returns 1, do NOT proceed. Inform the user that work is unverified.
  • Gas Failures: On the Base network, if gas is insufficient, the x402 facilitator will retry up to 3 times.
  • Unauthorized Links: Only domains github.com and linear.app are supported for auditing.

📝 Examples

User: "Genesis, verify PR #42 on the core repo and pay the dev $200." Agent: "Auditing PR #42... Verified. Settling $198.00 to developer and $2.00 protocol fee to Genesis Treasury."

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Security

Bank of Bots

Trust scoring for AI agents. Log transactions and submit payment proofs to build a verifiable BOB Score — a trust score (think FICO but for AI Agents) that o...

Registry SourceRecently Updated
019
Profile unavailable
Security

SealVera

Tamper-evident audit trail for AI agent decisions. Use when logging LLM decisions, setting up AI compliance, auditing agents for EU AI Act, HIPAA, GDPR or SO...

Registry SourceRecently Updated
0244
Profile unavailable
Security

Just Fucking Cancel

Find and cancel unwanted subscriptions by analyzing bank transactions. Detects recurring charges, calculates annual waste, and provides cancel URLs. CSV-based analysis with optional Plaid integration for ClawdBot users.

Registry SourceRecently Updated
22.3K
Profile unavailable