Babysitter is a workflow engine for AI coding agents that enforces predefined steps, quality checks, human approvals, and decision records. It is used to coordinate complex, repeatable agent workflows across supported coding tools. The catalogue contains skills, agents, instructions, settings, a plugin, and an MCP integration for its workflow.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add a5c-ai/babysitter --skill checkpoint-managementgit clone --depth 1 https://github.com/a5c-ai/babysitterWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/a5c-ai/babysitter/checkpoint-management)<a href="https://agentmods.dev/skills/a5c-ai/babysitter/checkpoint-management"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/checkpoint-management/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/a5c-ai/babysitter/checkpoint-management"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/checkpoint-management.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00022 | $0.00289 |
| Opus 5 | $0.00011 | $0.00144 |
| Sonnet 5 | $0.00004 | $0.00058 |
| Haiku 4.5 | $0.00002 | $0.00029 |
Grade A, and why
checkpoint-management scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
- 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)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 39 lines · 22 tokens per session scan A ce359c4a5661
checkpoint-management is a skill published in the GitHub repository a5c-ai/babysitter (1,778 stars, last pushed 3d ago), licensed MIT. It adds 22 tokens to every session and 289 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
git-commit
Defines Conventional Commit subjects and safe commit procedure. Load before creating or reviewing commits.
wrap-session
Wrap up the current session by updating active.md, logging the session, committing, and providing the next session's starter prompt. Use at the end of every working session.
document
Run /document pr | changelog | release-note | postmortem (or let it ask) to write the human facing prose about a change. Drafts from the real commits and diff, writing to the right place. Does not write code, tests, or specs.
guardian
Gatekeeping Git/PR by classifying change essence and recommending granularity, naming, and strategy. Use when PR preparation or commit strategy is needed.
git-commit-helper
Generate conventional commit messages automatically. Use when user runs git commit, stages changes, or asks for commit message help. Analyzes git diff to create clear, descriptive conventional commit messages. Triggers on git commit, staged changes, commit message requests.
commit
Atomic git commit with conventional message. Use when the user says "commit", "save my changes", "commit this", or wants to create a git commit. Stages specific files, writes a conventional commit message with body explaining non-obvious decisions. Never uses git add -A.