Aller au contenu
TakoAPI
Retour aux skills

policy-engine

par joetomasone

Coding Agents & IDEs
—Pas encore noté
Ta note

Résumé

Deterministic governance layer for OpenClaw tool execution.

Description

Ce que fait ce skill

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.

Quand l'utiliser

  • 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

Exemple de workflow

ENTRÉE

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

AGENT
  1. 1

    Define an allowlist profile named 'readonly' with [read, web_fetch, web_search, message]

  2. 2

    Map the research agent ID to the 'readonly' profile via the routing config

  3. 3

    Enable dry-run mode to verify what would be blocked without enforcing

  4. 4

    Check logs for DRYRUN entries, confirm the policy behaves as expected

  5. 5

    Disable dry-run to enforce blocking in production

SORTIE

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

Installation

clawhub install joetomasone/policy-engine

Exécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.

Liens