agent-checkpointing

Community

Save and restore agent state.

Authorlgrammel
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill allows you to save the current state of an agent's execution, enabling you to resume, roll back, or fork from that point later.

Core Features & Use Cases

  • Save State: Capture the agent's current filesystem, conversation history, and tool outputs.
  • Resume/Rollback: Restore the agent to a previous saved state.
  • Forking: Branch execution from a saved state to test alternative strategies.
  • Use Case: Debugging a complex agent task by saving a checkpoint after each successful step, allowing you to roll back to a known good state if a subsequent step fails.

Quick Start

Use the agent checkpointing skill to save the current agent state.

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: agent-checkpointing
Download link: https://github.com/lgrammel/ai-engineering/archive/main.zip#agent-checkpointing

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.