🎁 Get the FREE AI Skills Starter Guide β€” Subscribe β†’
BytesAgainBytesAgain
πŸ¦€ ClawHub

Alfred Agent Governance

by @lllljokerllll

Enforces YAML-based runtime policies to intercept, audit, rate-limit, and stop AI agent tool calls for secure governance in OpenClaw.

Versionv1.0.0
βš™οΈ Configuration

Create config/governance-rules.yaml:

version: "1.0"
agents:
  coder:
    deny_patterns:
      - "DROP\\s+TABLE"
      - "rm\\s+-rf\\s+/"
      - "DELETE\\s+FROM\\s+users"
    rate_limit:
      exec: 50/hour
      write: 100/hour
    require_approval:
      - "exec.*sudo"
      - "exec.*systemctl"
  security:
    deny_tools:
      - "write"
      - "edit"
    rate_limit:
      web_search: 30/hour
  research:
    deny_tools:
      - "write"
      - "edit"
    rate_limit:
      web_fetch: 20/hour
  debug:
    deny_tools:
      - "write"
      - "edit"

View on ClawHub
TERMINAL
clawhub install alfred-agent-governance

πŸ§ͺ Use this skill with your agent

Most visitors already have an agent. Pick your environment, install or copy the workflow, then run the smoke-test prompt above.

πŸ” Can't find the right skill?

Search 60,000+ AI agent skills β€” free, no login needed.

Search Skills β†’