# Ac Checkpoint Manager

> Manage checkpoints for rollback capability. Use when creating save points, rolling back changes, managing recovery points, or restoring previous states.

- **Type:** Skill
- **Install:** `agentstack add skill-majiayu000-claude-skill-registry-ac-checkpoint-manager`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [majiayu000](https://agentstack.voostack.com/s/majiayu000)
- **Installs:** 0
- **Category:** [Developer Tools](https://agentstack.voostack.com/c/developer-tools)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [majiayu000](https://github.com/majiayu000)
- **Source:** https://github.com/majiayu000/claude-skill-registry/tree/main/skills/agent/ac-checkpoint-manager
- **Website:** https://majiayu000.github.io/claude-skill-registry/

## Install

```sh
agentstack add skill-majiayu000-claude-skill-registry-ac-checkpoint-manager
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# AC Checkpoint Manager

Manage checkpoints for safe rollback during autonomous development.

## Purpose

Creates and manages checkpoints that enable rollback to known-good states, providing safety during autonomous operation.

## Quick Start

```python
from scripts.checkpoint_manager import CheckpointManager

manager = CheckpointManager(project_dir)
checkpoint = await manager.create_checkpoint("before-refactor")
await manager.restore_checkpoint(checkpoint.id)
```

## Checkpoint Types

- **Auto**: Created automatically at key points
- **Manual**: Created on explicit request
- **Feature**: Created after each feature completion
- **Session**: Created at session boundaries

## Checkpoint Structure

```
.claude/checkpoints/
├── checkpoint-20240115-100000/
│   ├── metadata.json
│   ├── feature_list.json
│   ├── execution-state.json
│   └── git-ref.txt
├── checkpoint-20240115-110000/
│   └── ...
```

## Auto-Checkpoint Points

- Before starting new feature
- After completing feature
- Before risky operations
- At context compaction

## Workflow

```
1. CREATE    → Snapshot current state
2. STORE     → Save files and git ref
3. VALIDATE  → Verify checkpoint integrity
4. (on rollback)
5. RESTORE   → Restore from checkpoint
6. VERIFY    → Confirm restoration
```

## Integration

- Used by: `ac-state-tracker` for state recovery
- Used by: `ac-task-executor` before risky operations

## API Reference

See `scripts/checkpoint_manager.py` for full implementation.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [majiayu000](https://github.com/majiayu000)
- **Source:** [majiayu000/claude-skill-registry](https://github.com/majiayu000/claude-skill-registry)
- **License:** MIT
- **Homepage:** https://majiayu000.github.io/claude-skill-registry/

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-majiayu000-claude-skill-registry-ac-checkpoint-manager
- Seller: https://agentstack.voostack.com/s/majiayu000
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.