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/spec-executionnpx skills add a5c-ai/babysitter --skill spec-executiongit 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/spec-execution)<a href="https://agentmods.dev/skills/a5c-ai/babysitter/spec-execution"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/spec-execution.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 | $0.00030 | $0.00404 |
| Opus 5 | $0.00015 | $0.00202 |
| Sonnet 5 | $0.00006 | $0.00081 |
| Haiku 4.5 | $0.00003 | $0.00040 |
Grade A, and why
spec-execution 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
- Read specification for requirements and architecture
- Implement each requirement following project conventions
- Add type definitions and JSDoc documentation
- Implement error handling for all failure modes
Phase 2: Test Writing
- Write unit tests for each module/function
- Write integration tests for API boundaries
- Cover all acceptance criteria from the specification
- Test edge cases and error paths
Phase 3: Code Review
- Verify all requirements are implemented
- Check acceptance criteria are tested
- Review architecture adherence
- Assess code quality
Phase 4: Iterative Improvement
- Address review findings
- Fix failing tests
- Resolve architecture deviations
- Re-verify quality (convergence loop, max 3 cycles)
Phase 5: Atomic Commit
- Group changes into logical atomic commits
- Descriptive messages following project conventions
- Separate production, test, and config changes
- Include specification reference
Phase 6: Progress Tracking
- Requirement completion percentage
- Test coverage summary
- Quality score report
- Remaining work identification
Quality Gate
Quality threshold defaults to 80. If not met after max improvement cycles, a human breakpoint is triggered for review.
When to Use
/spec:execute [file]slash command- After spec creation when ready to implement
Processes Used By
claudekit-spec-workflow(execute mode)
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 · 60 lines · 30 tokens per session scan A 143fe357763f
spec-execution is a skill published in the GitHub repository a5c-ai/babysitter (1,769 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 404 once invoked, about $0.0002 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…
moai-ref-testing-pyramid
Test pyramid strategy, coverage targets, test patterns, and quality metrics reference. Agent-extending skill that amplifies manager-develop test-creation and quality-validation work with production-grade testing patterns. NOT for: production code implementation, architecture design, DevOps, security audits.
nw-hexagonal-testing
5-layer agent output validation, I/O contract specification, vertical slice development, and test doubles policy with per-layer examples.
groom-backlog
Grooms a project backlog and proposes tracker changes. Trigger on "groom the backlog", "groom the board", "clean up the backlog", or "/groom-backlog"; changes require user approval.
pr-watch-as-reviewer
Watches a reviewed PR and approves settled feedback. Trigger on "approve the PR when my comments are resolved", "watch and approve", or "/pr-watch-as-reviewer"; user-invoked only.