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 git-integrationgit 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/git-integration)<a href="https://agentmods.dev/skills/a5c-ai/babysitter/git-integration"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/git-integration/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/git-integration"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/git-integration.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 | $0.00039 | $0.02129 |
| Opus 5.5 | $0.00016 | $0.00852 |
| Sonnet 5.5 | $0.00008 | $0.00426 |
| Haiku 4.5 | $0.00004 | $0.00213 |
Grade A, and why
git-integration 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capabilities
1. Atomic Commit Per Task
Each task in a plan produces one atomic commit:
# After completing task 1 of PLAN-1.md
git add src/auth/oauth.ts src/auth/types.ts
git commit -m "feat(auth): implement OAuth2 login endpoint
Phase 72, Plan 1, Task 1: Implement login endpoint
- Added POST /api/auth/login with email/password validation
- Returns JWT token on success, 401 on invalid credentials
- Rate limited to 5 attempts per minute
Refs: Phase-72/PLAN-1/Task-1"
Commit message format:
<type>(<scope>): <short description>
Phase <N>, Plan <M>, Task <K>: <task title>
- <change 1>
- <change 2>
Refs: Phase-<N>/PLAN-<M>/Task-<K>
Types: feat, fix, refactor, test, docs, chore, style, perf.
2. Planning File Commits
Planning files are committed separately from code:
# After generating plans
git add .planning/phase-72/PLAN-1.md .planning/phase-72/PLAN-2.md
git commit -m "plan(phase-72): create execution plans
Phase 72: Authentication
- PLAN-1.md: OAuth2 login and token management (4 tasks, wave 1)
- PLAN-2.md: Auth middleware and role guards (3 tasks, wave 1)
Refs: Phase-72/planning"
Planning commit types: plan, state, research, context, verify, audit.
3. Commit Message Generation
Generate commit messages from task context:
Input:
phase: 72
plan: 1
task: 1
title: "Implement login endpoint"
type: "feat"
scope: "auth"
changes: ["POST /api/auth/login endpoint", "JWT token generation", "Rate limiting"]
Output:
"feat(auth): implement OAuth2 login endpoint
Phase 72, Plan 1, Task 1: Implement login endpoint
- Added POST /api/auth/login endpoint
- JWT token generation on success
- Rate limiting (5 attempts/minute)
Refs: Phase-72/PLAN-1/Task-1"
4. Git Tag Creation
Create annotated tags for milestone completions:
git tag -a v1.0 -m "Milestone v1.0: MVP Launch
Phases completed: 70, 71, 72, 73
Requirements covered: R1-R11
Audit result: PASSED
Key deliverables:
- Project scaffolding and CI pipeline
- Database layer with migrations
- OAuth2 authentication
- REST API endpoints"
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.
- 1mo ago First seen · 278 lines · 39 tokens per session scan A 317e046094ee
git-integration is a skill published in the GitHub repository a5c-ai/babysitter (1,857 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 2,129 once invoked, about $0.0002 per session on Opus 5.5. 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
github-automation
GitHub workflow automation, PR management, issue tracking, and code review coordination. Integrates with GitHub Actions and repository management. Use when: PR creation, code review, issue management, release automation, workflow setup. Skip when: local-only changes, non-GitHub repositories.
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.
version-bump
Use for version bumps on explicit request or as the pre-merge step of a PR land. Never infer from finished, reviewed, green, or draft-ready work. Assigns SemVer.
ship-change
Ship an OpenSpec change after openspec-apply completes. When only QA/manual tasks remain, marks them done (tested later), archives + syncs specs, commits, pushes, opens a PR against develop, watches CI, waits for CodeRabbit, auto-applies safe fixes and re-pushes, loops until CI green + no actionable review threads…
team-pr
Use for opening PRs only on explicit request. Never infer from passed verification. Includes project terms, evidence, and risk.
agentic-jujutsu
Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination.