Saltar al contenido
TakoAPI
Volver a skills

policy-engine

por joetomasone

Coding Agents & IDEs
—Aún sin valoraciones
Tu valoración

Resumen

Deterministic governance layer for OpenClaw tool execution.

Descripción

Qué hace esta 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.

Cuándo usarla

  • 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

Flujo de trabajo de ejemplo

ENTRADA

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

AGENTE
  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

SALIDA

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

Instalación

clawhub install joetomasone/policy-engine

Ejecuta el comando de la CLI o pega el prompt en Claude Code, Cursor, Codex o el agente de programación que uses.

Enlaces