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 agentmods add skills/a5c-ai/babysitter/plan-implementationnpx skills add a5c-ai/babysitter --skill plan-implementationgit 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/plan-implementation)<a href="https://agentmods.dev/skills/a5c-ai/babysitter/plan-implementation"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/plan-implementation.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00029 | $0.00413 |
| Opus 5 | $0.00015 | $0.00206 |
| Sonnet 5 | $0.00006 | $0.00083 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
plan-implementation 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 yesterday.
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
- For medium and high stakes changes (low stakes can proceed inline)
- When structured execution with verification is needed
Process
- Load plan - Validate plan exists and is approved
- Stakes enforcement - High: halt without plan. Medium: ask. Low: proceed.
- Worktree isolation - Offer git worktree based on stakes level
- Execute steps - For each: mark in-progress, locate files, read, modify, verify, mark complete
- Phase checkpoints - Summarize and ask: continue, review, or pause
- Failure handling - Stop immediately, investigate, propose fix, get approval for deviations
- Code review - Run code-reviewer agent (APPROVE / APPROVE_WITH_NITS / REQUEST_CHANGES)
- Security review - Run security-reviewer agent (halt if failed)
- Completion summary - Steps completed, files changed, test status, plan location
Key Rules
- Follow the plan strictly; deviations require explicit approval
- Verify before declaring done; run verification after each step
- Track progress visibly via plan document updates
- Read files before modifying them
- Complete code and security reviews before finishing
Tool Use
Invoke via babysitter process: methodologies/rpikit/rpikit-implement
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.
- yesterday First seen · 39 lines · 29 tokens per session scan A f068326af61d
plan-implementation is a skill published in the GitHub repository a5c-ai/babysitter (1,765 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 413 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
tutti-app-release
Set up, review, run, or debug external repositories that publish a Tutti workspace app through the reusable Tutti App Release GitHub Actions workflow. Use for caller workflows, tutti.app.json manifests, @tutti-os/app-release-tools, S3/CloudFront release hosting, latest.json, versions.json, catalog.json, catalog-only…
tutti-agent-workspace-app
Build or evolve a complex agent-enabled Tutti workspace app repository. Use for Tutti apps with web/server/shared monorepos, @tutti-os/agent-acp-kit local agent runtimes, kit-owned TUTTICLI agent/composer discovery, dynamic agent catalogs, run-scoped MCP tool gateways, app-owned package builders, web-first debugging…
groom-backlog
Groom a project backlog in an issue tracker. Loads the whole board in bulk, computes a gap inventory instead of eyeballing one, verifies each candidate issue's factual claims against the code and the tracker, ranks the verified candidates by a stated four-tier heuristic, proposes an evidence-backed closure for an…
pr-watch-as-reviewer
Watch a pull request you are reviewing until your feedback is settled, re-review each settlement, then approve once: poll GitHub in 31-minute cycles for up to 24 hours until every review thread you opened is resolved and every plain PR comment you posted has a later push behind it, re-review each settlement against…
goga-cookbook
Principles for applying DSL specification in cell and CODEMANIFEST design.
goga-define-challenge
Challenge the complete product definition before the PRD is generated.