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 tdd-enforcementgit 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/tdd-enforcement)<a href="https://agentmods.dev/skills/a5c-ai/babysitter/tdd-enforcement"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/tdd-enforcement/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/tdd-enforcement"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/tdd-enforcement.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 | $0.00033 | $0.00424 |
| Opus 5 | $0.00016 | $0.00212 |
| Sonnet 5 | $0.00007 | $0.00085 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
tdd-enforcement 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 6d 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
- Write tests that define expected behavior
- Tests MUST fail (exit code 1)
- Use CI=true or --run flag, never watch mode
- Apply timeout guards (60s) to prevent hanging
- Record exit code as evidence
2. GREEN Phase - Minimal Implementation
- Write the minimal code to make tests pass
- Do NOT add features not covered by tests
- Do NOT optimize prematurely
- Tests MUST pass (exit code 0)
- Record exit code as evidence
3. REFACTOR Phase - Quality Improvement
- Apply SOLID principles and clean code patterns
- Improve naming, reduce coupling
- Remove duplication
- Run tests after EACH refactoring step
- Tests MUST remain passing (exit code 0)
4. Coverage Gate
- Measure coverage: statements, branches, functions, lines
- Minimum 80% overall coverage required
- Iterate: write additional tests for gaps until threshold met
- Maximum 3 convergence iterations
Rules
- Never skip the RED phase
- Never accept GREEN without exit code 0
- Never use watch mode in CI
- Always record evidence (exit codes, coverage numbers)
- Enforce 80% coverage threshold
When to Use
- All code implementation tasks
- Feature development
- Bug fixes (write regression test first)
Agents Used
tdd-guide(primary consumer)code-reviewer(validates test quality)
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.
- 6d ago First seen · 57 lines · 33 tokens per session scan A dd339e07f123
tdd-enforcement is a skill published in the GitHub repository a5c-ai/babysitter (1,783 stars, last pushed 4d ago), licensed MIT. It adds 33 tokens to every session and 424 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
test-driven-bug-fix
Defines reproduce-red-green-refactor bug fixes. Load when correcting a defect with a regression test.
implementing-slices
Defines test-first slice execution, commits, and review fixes. Load when an implementer executes 8-plan.md.
test-first-development
Defines acceptance tests as the implementation scope contract. Load before production code is written for a planned change.
team-fix
Runs the compressed bug-fix pipeline. Trigger on "run the bug-fix pipeline", "team-fix this bug", or "/team-fix" only; never infer pipeline intent from a plain bug-fix request.
team-implement
Executes and verifies implementation slices. Trigger on "implement this", "execute the plan", or "/team-implement" only; never infer the phase from a ready plan.
rn-testing
This skill should be used when the user asks to "write a Maestro test", "create E2E flows", "add testIDs", "run UI tests", "run E2E tests", "verify a feature works", "test my screen", "set up maestro-runner", "mock network requests", "inspect store state", "write test assertions", or needs guidance on test timing…