OC Guard

该 Skill 要求所有 OpenClaw 配置变更经 oc-guard 流程完成，先执行 plan 再 apply，高风险变更需 --confirm，禁止直接编辑宿主配置文件；执行后返回中英双语执行回执，未执行时标注未执行。附带提案模板。

edmond-ai

热度 52.68

最近更新 2026-05-11 17:28:50

分类：自动化依赖：代码执行 / 读写文件应用场景：工作流 / 自动化脚本 / 模板

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add oc-guard

Metadata

name: oc_guard
description: Safe OpenClaw config planning/apply workflow with bilingual execution receipts.
metadata: {"openclaw":{"requires":{"bins":["python3","openclaw","opencode"]}}}

oc-guard Skill

Purpose

All config-changing requests must go through oc-guard. Do not directly edit ~/.openclaw/openclaw.json. When possible, invoke the bundled CLI at {baseDir}/scripts/oc-guard.py.

Hard Rules

Use oc-guard plan before apply.
High-risk changes require oc-guard apply --confirm.
Always return execution receipt first.
If command is not executed, return 【模型说明-未执行】.
Never claim success without a real oc-guard receipt.

Common Commands

{baseDir}/scripts/oc-guard.py --help
{baseDir}/scripts/oc-guard.py plan "<requirement>"
{baseDir}/scripts/oc-guard.py apply --confirm "<requirement>"
{baseDir}/scripts/oc-guard.py plan --proposal <file>
{baseDir}/scripts/oc-guard.py apply --confirm --proposal <file>