LaunchKit · 2026
Back to Skills

policy-engine

Deterministic governance layer for OpenClaw tool execution.

0
0 downloads
by @joetomasone

Setup & Installation

openclaw skills install @joetomasone/policy-engine

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install policy-engine

What This Skill Does

A governance plugin for OpenClaw that intercepts tool calls before execution to enforce allowlists, deny patterns, path restrictions, and risk tiers. Every decision is logged for audit. Ships with dry-run mode, escalation tracking, and hot-reload support.

Unlike ad-hoc prompt-based restrictions, it enforces policies deterministically at the hook level so prompt injection or model drift can't bypass them.

When to use it

  • Limiting a research sub-agent to read-only tools
  • Blocking dangerous exec commands like rm -rf or docker push
  • Enforcing write paths so agents can't touch files outside a workspace
  • Testing policy rules in dry-run before enforcing them in production
  • Auditing which tools each agent attempted to use across a session

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User wants to restrict a research agent to read-only tools and block it from writing files

AGENT
  1. 1Define an allowlist profile named 'readonly' with [read, web_fetch, web_search, message]
  2. 2Map the research agent ID to the 'readonly' profile via the routing config
  3. 3Enable dry-run mode to verify what would be blocked without enforcing
  4. 4Check logs for DRYRUN entries, confirm the policy behaves as expected
  5. 5Disable dry-run to enforce blocking in production
OUTPUT

Research agent is restricted to read-only tools; any write or exec attempt is blocked and logged with a remediation message