Mmcp.market

checkpoint-management skill

by a5c-ai·a5c-ai/babysitter·1.8k stars·MIT

Git-backed state management for safe rollback. Create and restore checkpoints with tagged commits and metadata tracking.

A100/100content scan

Is the checkpoint-management skill safe?

Clean: nothing in its files matched our rules. We read 2 files in the folder on 2026-09-28.

No findings.

Install the checkpoint-management skill

A skill is a folder. Copy it into your agent's skills folder and the agent loads it when the task matches its description. 

git clone --depth 1 https://github.com/a5c-ai/babysitter.git /tmp/babysitter
mkdir -p ~/.claude/skills
cp -r /tmp/babysitter/library/methodologies/claudekit/skills/checkpoint-management ~/.claude/skills/checkpoint-management
available in every project

In the Claude apps, zip the folder and upload it from the Skills settings. The folder on GitHub

The instructions your agent would load

SKILL.md as published, without the frontmatter. Read it on GitHub

  • Stage all current changes
  • Create commit with [CHECKPOINT] prefix
  • Tag with claudekit-checkpoint-{timestamp}
  • Record metadata: files changed, insertions, deletions

Restore Checkpoint

  • List available checkpoints by tag
  • Preview changes that would be reverted
  • Restore to selected checkpoint via git reset
  • Verify restored state matches checkpoint

Session Isolation

Checkpoints are session-scoped. Tags created during a session can be cleaned up without affecting other work.

When to Use

  • Before risky refactoring operations
  • After passing quality checks (safety checkpoints)
  • At the start and end of ClaudeKit sessions
  • Before spec execution phases

Processes Used By

  • claudekit-orchestrator (session start/end checkpoints)
  • claudekit-safety-pipeline (safety checkpoints after quality checks)

More skills from a5c-ai/babysitter

  • Aadversarial-reviewFresh adversarial code review with binary PASS/FAIL verdicts, evidence citations, and anchoring bias prevention via fresh reviewer spawning.
  • Aagent-boosterWASM-based instant code transforms for simple tasks, achieving 352x speedup over LLM inference with zero cost.
  • Aagent-coordinationCoordinate Crew (persistent) and Polecat (transient) agents using Gas Town's hook-based work distribution and GUPP principle.
  • Aagent-dispatch
  • Aanti-driftHierarchical coordination and drift detection with frequent checkpoints, shared memory coherence validation, role specialization enforcement, and short task cycles.
  • Aarchitecture-design
  • Aarchitecture-patternsSystem and API design guidance covering component boundaries, data flow, integration patterns, and scalability considerations.
  • Aassimilate-popular-workflowsThis skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there", or wants to investigate public repositories for extractable processes, babysitter plugins, and reusable procedural insights. Searches GitHub for SKILL.md files, classifies repos by archetype, and maintains structured research under docs/reference-repos/.
  • Aaudit-trail
  • AbabysitOrchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)
  • Ababysit-babysitter-issuesThis skill should be used when the user asks to "babysit issues", "work on assigned issues", "check a5c-agent issues", "process babysitter issues", or wants to find and work on open GitHub issues assigned to a5c-agent in the babysitter repo.
  • Abehavior-contractBug condition/postcondition formalization as testable Behavior Contracts. Defines invariants that must be preserved across fixes.

All agent skills → · MCP servers