Manage checkpoints for rollback capability. Use when creating save points, rolling back changes, managing recovery points, or restoring previous states.
Resources
1Install
npx skillscat add adaptationio/skrillz/ac-checkpoint-manager Install via the SkillsCat registry.
The AC Checkpoint Manager creates and manages checkpoint snapshots of project states to enable rollback to known-good states. It solves the problem of safely reverting changes during autonomous development by storing file snapshots and git references. Developers should use it before risky operations, feature implementation, or when establishing recovery points during sessions.
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
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 restorationIntegration
- Used by:
ac-state-trackerfor state recovery - Used by:
ac-task-executorbefore risky operations
API Reference
See scripts/checkpoint_manager.py for full implementation.