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 adversarial-reviewgit 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/adversarial-review)<a href="https://agentmods.dev/skills/a5c-ai/babysitter/adversarial-review"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/adversarial-review/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/adversarial-review"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/adversarial-review.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 | $0.00031 | $0.00325 |
| Opus 5 | $0.00015 | $0.00162 |
| Sonnet 5 | $0.00006 | $0.00065 |
| Haiku 4.5 | $0.00003 | $0.00032 |
Grade A, and why
adversarial-review 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 7d 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
- For final comprehensive cross-unit review
- When verifying spec compliance of any implementation
Key Differences from Collaborative Review
| Aspect | Collaborative | Adversarial |
|---|---|---|
| Goal | Help improve code | Verify spec compliance |
| Verdict | Suggestions | Binary PASS/FAIL |
| Evidence | Optional | Required (file:line) |
| Reviewer | Can be reused | Must be fresh |
| Context | Shared | Independent |
Fresh Reviewer Rule
On re-review after FAIL, a NEW reviewer instance spawns with no memory of the previous review. This prevents anchoring bias where a reviewer fixates on previously identified issues.
Anti-Patterns
- Reusing reviewers after FAIL
- Passing previous findings to new reviewers
- Providing subjective or advisory feedback
- Accepting partial compliance as PASS
Tool Use
Invoke as part of: methodologies/metaswarm/metaswarm-execution-loop (Phase 3)
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.
- 7d ago First seen · 40 lines · 31 tokens per session scan A ccbd6cc28199
adversarial-review is a skill published in the GitHub repository a5c-ai/babysitter (1,788 stars, last pushed 5d ago), licensed MIT. It adds 31 tokens to every session and 325 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
goga-review-plan
Verify execution plan completeness and correctness.
goga-accept-manifest-review
Verify each Cell's CODEMANIFEST against the implementation.
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.
goga-change-usage-reconciler
Ensures .usages file consistency with code changes.