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 code-review-pipelinegit 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/code-review-pipeline)<a href="https://agentmods.dev/skills/a5c-ai/babysitter/code-review-pipeline"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/code-review-pipeline/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/code-review-pipeline"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/code-review-pipeline.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 | $0.00028 | $0.00460 |
| Opus 5 | $0.00014 | $0.00230 |
| Sonnet 5 | $0.00006 | $0.00092 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
code-review-pipeline 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
- Logic errors and off-by-one mistakes
- Edge case handling (null, undefined, empty, boundary)
- Type safety (no implicit any, proper narrowing)
- Error handling completeness
- Floating promise detection
- Race condition analysis
Dimension 2: Security
- Injection vectors (SQL, XSS, command, template)
- Authentication and authorization gaps
- Data exposure (PII, credentials, internal state)
- Dependency vulnerabilities (known CVEs)
- Input validation completeness
Dimension 3: Performance
- Algorithmic complexity (O(n^2) detection)
- Memory leaks (event listeners, closures, caches)
- Unnecessary allocations in hot paths
- Database query optimization (N+1, missing indexes)
- Bundle size impact
Dimension 4: Maintainability
- Naming clarity and consistency
- Documentation completeness (JSDoc, inline comments)
- Test coverage adequacy
- Coupling analysis (afferent/efferent)
- File organization compliance
Confidence Gating
- Score each issue 0-100 on confidence
- Only report issues >= 80% confidence
- Prevents false positive noise
- Higher confidence for clear patterns, lower for heuristic matches
Remediation Loop
- Prioritize: critical > high > medium > low
- Apply fixes via refactor-cleaner agent
- Re-review after remediation
- Maximum 2 remediation cycles
- Exit when no critical/high issues remain
When to Use
- Post-implementation review
- Pre-merge PR review
- Security audit
- Technical debt assessment
Agents Used
code-reviewer(primary)refactor-cleaner(remediation)
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 · 65 lines · 28 tokens per session scan A 6723460d8c3d
code-review-pipeline is a skill published in the GitHub repository a5c-ai/babysitter (1,778 stars, last pushed 3d ago), licensed MIT. It adds 28 tokens to every session and 460 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
goga-review-plan
Verify execution plan completeness and correctness.
goga-accept-manifest-review
Verify each Cell's CODEMANIFEST against the implementation.
eng-design-doc-review
Reviews a technical design document with fresh context. Trigger on "review the design doc", "audit 6-design.md", "is this design ready", or "/eng-design-doc-review".
goga-change-manifest-reconciler
Reconciliation of CODEMANIFEST specifications with implementation.
goga-change-validator
Final end-to-end validation of the completed change.
goga-accept-report
Generate the final acceptance report with verdict.