~ / rigs / Azzaraell / agent-payments-x402

Azzaraell/agent-payments-x402

The money layer for AI agents on Solana — pay and get paid via x402 (USDC) behind enforced, non-custodial spending limits. A Claude Code / Codex skill for the Solana AI Kit.

↗ GitHub ★ 0 MIT updated 1d ago project Claude Code
stack: Python
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~176 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details
Quality 0/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ npx degit Azzaraell/agent-payments-x402/agents ./rig-agent-payments-x402/agents
$ npx degit Azzaraell/agent-payments-x402/commands ./rig-agent-payments-x402/commands

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ curl -fsSL --create-dirs -o .claude/agents/agent-payments-engineer.md https://raw.githubusercontent.com/Azzaraell/agent-payments-x402/main/agents/agent-payments-engineer.md
$ curl -fsSL --create-dirs -o .claude/agents/payment-safety-auditor.md https://raw.githubusercontent.com/Azzaraell/agent-payments-x402/main/agents/payment-safety-auditor.md

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(./.env.*)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(git push --force:*)",
      "Read(**/*.pem)",
      "Read(.env)",
      "Read(~/.aws/**)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Bash(rm -rf *)",
      "Bash(sudo *)",
      "Bash(sudo:*)",
      "Bash(rm -rf /)",
      "Bash(git push -f:*)",
      "Read(.env.*)",
      "Bash(git reset --hard*)",
      "Bash(rm -rf /*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(gh pr merge *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(gh pr merge:*)",
      "Bash(gh pr create *)",
      "Bash(git reset --hard:*)",
      "Bash(npm publish:*)",
      "Bash(git rebase *)"
    ]
  }
}

Subagents (2)

agent-payments-engineer
model: sonnet
Implements agent payments on Solana — x402 client (pay) and server (get paid), non-custodial wallet wiring, and enforced spending controls. Use when adding payments to an agent, paywalling an API/MCP,
payment-safety-auditor
model: opus
Audits an agent's money path for the ways it can be drained — god-mode keys, missing caps, unbounded loops, hallucinated destinations, decimals bugs, leaked secrets, no kill switch, no audit trail. Us

Slash commands (3)

/add-x402-paywall/audit-agent-spending/setup-agent-wallet

Similar rigs

copied ✓