跳到正文
TakoAPI
返回技能列表

agent-mode-upgrades

由 maverick-software 提供

Coding Agents & IDEs
630下载量由 clawskills.sh 提供
0浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

A comprehensive upgrade to OpenClaw's agentic capabilities with persistent state, automatic planning, approval.

描述

该技能的功能

Upgrades OpenClaw's agentic loop with persistent plan state, approval gates for risky operations, automatic retry with error diagnosis, context summarization, session checkpointing, and knowledge graph memory injection. A Mode dashboard provides visual configuration without editing JSON.

Plans survive across conversation turns and checkpoints, so multi-hour tasks can be interrupted and resumed without losing state or replaying completed steps.

何时使用

  • Resuming a multi-step coding task after closing the agent mid-session
  • Pausing before destructive shell commands to review and approve them
  • Running parallel subtasks within a single agent goal
  • Automatically retrying a failed file write with elevated permissions
  • Keeping context window manageable during long refactor sessions

示例工作流

输入

User asks: Build a REST API with authentication from scratch

智能体
  1. 1

    Detects planning intent and generates a step-by-step plan stored to ~/.openclaw/agent-state/

  2. 2

    Injects plan status into the system prompt before each turn

  3. 3

    Pauses at the git push step and requests human approval with a 15-second timeout

  4. 4

    Retries a failed dependency install by diagnosing the error and applying a modified command

  5. 5

    Creates an automatic checkpoint after each completed step

输出

Completed plan with all steps marked done; checkpoint file available for restore if the session is interrupted

安装

clawhub install maverick-software/agent-mode-upgrades

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接