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 verification-suitegit 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/verification-suite)<a href="https://agentmods.dev/skills/a5c-ai/babysitter/verification-suite"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/verification-suite/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/verification-suite"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/verification-suite.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 | $0.00036 | $0.02220 |
| Opus 5 | $0.00018 | $0.01110 |
| Sonnet 5 | $0.00007 | $0.00444 |
| Haiku 4.5 | $0.00004 | $0.00222 |
Grade A, and why
verification-suite 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.
How it starts
The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
- Is this plan structurally valid? (XML task format, required sections, frontmatter)
- Is this phase complete? (all plans executed, summaries written, state updated)
- Do all references resolve? (no broken links, missing files, stale references)
- Do expected artifacts exist? (outputs from each phase are present)
- Is requirements coverage at 100%?
- Is the
.planning/directory healthy?
This corresponds to the original lib/verify.cjs module and the verification patterns in references/verification-patterns.md.
Capabilities
1. Plan Structure Validation
Validate a PLAN.md file for structural correctness:
Checks:
[PASS] Frontmatter present with required fields (status, phase, wave, task_count)
[PASS] XML task blocks present and well-formed
[PASS] Each task has <task>, <context>, <acceptance_criteria> elements
[PASS] Task count matches frontmatter task_count
[FAIL] Task 3 missing <acceptance_criteria> element
[WARN] No depends_on field in frontmatter (optional but recommended)
XML task format:
<task id="1" title="Implement login endpoint">
<context>
Build POST /api/auth/login endpoint with email/password validation.
</context>
<acceptance_criteria>
- Endpoint accepts POST with email and password
- Returns JWT token on success
- Returns 401 on invalid credentials
- Rate limits to 5 attempts per minute
</acceptance_criteria>
</task>
2. Phase Completeness Checks
Verify a phase has all expected artifacts:
Phase 72 completeness:
[PASS] PLAN-1.md exists and status=executed
[PASS] PLAN-2.md exists and status=executed
[PASS] SUMMARY.md exists with commits and files lists
[PASS] STATE.md updated with phase 72 in completed_phases
[FAIL] VERIFICATION.md missing (verification not run)
[WARN] No CONTEXT.md (discuss-phase was skipped)
Completeness: 4/6 checks passed (67%)
Required for completion: VERIFICATION.md must be created
3. Reference Integrity Verification
Check that all file references in GSD artifacts are valid:
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 · 269 lines · 36 tokens per session scan A 1c5db0bd6fe9
verification-suite is a skill published in the GitHub repository a5c-ai/babysitter (1,778 stars, last pushed 3d ago), licensed MIT. It adds 36 tokens to every session and 2,220 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-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…
goga-cookbook
Principles for applying DSL specification in cell and CODEMANIFEST design.
goga-review-plan
Verify execution plan completeness and correctness.
goga-brainstorm
Pipeline orchestrator for brainstorming the cells architecture.
goga-define-challenge
Challenge the complete product definition before the PRD is generated.
goga-define-experience
Define the user experience required to achieve the established product goals and solve the identified problem.