# Enforce policy-gated and auditable agent execution with LACP

> Run Claude, Codex, and related coding-agent tasks through policy gates, evidence loops, and auditable execution tiers before risky work proceeds.

- Skill: `agentskillexchange/enforce-policy-gated-and-auditable-agent-execution-with-lacp` (Agent Skill)
- Install (CLI): `npx skillmds@latest add agentskillexchange/enforce-policy-gated-and-auditable-agent-execution-with-lacp`
- Raw SKILL.md: https://api.skillmd.com/api/skills/agentskillexchange/enforce-policy-gated-and-auditable-agent-execution-with-lacp/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: agentskillexchange (https://skillmd.com/u/agentskillexchange)
- Updated: 2026-09-08
- Page: https://skillmd.com/skills/agentskillexchange/enforce-policy-gated-and-auditable-agent-execution-with-lacp

---


# Enforce policy-gated and auditable agent execution with LACP

Run Claude, Codex, and related coding-agent tasks through policy gates, evidence loops, and auditable execution tiers before risky work proceeds.

## Prerequisites

Local development environment, supported agent runtime such as Claude or Codex, shell access, repository to govern, optional verification tooling

## Installation

Use the upstream install or setup path that matches your environment:
- brew tap 0xNyk/lacp && brew install lacp

Requirements and caveats from upstream:
- ├── hooks/ # Python hook pipeline for Claude Code
- Modular Python hooks enforcing quality at every session stage:

Basic usage or getting-started notes:
- bash
- # Homebrew (recommended)
- # or cURL bootstrap

- Source: https://github.com/0xNyk/lacp
- Extracted from upstream docs: https://raw.githubusercontent.com/0xNyk/lacp/HEAD/README.md

## Documentation

- https://github.com/0xNyk/lacp#readme

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/enforce-policy-gated-and-auditable-agent-execution-with-lacp/)