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 multi-service-orchestrationgit 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/multi-service-orchestration)<a href="https://agentmods.dev/skills/a5c-ai/babysitter/multi-service-orchestration"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/multi-service-orchestration/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/multi-service-orchestration"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/multi-service-orchestration.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 | $0.00027 | $0.00490 |
| Opus 5 | $0.00014 | $0.00245 |
| Sonnet 5 | $0.00005 | $0.00098 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
multi-service-orchestration 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
- Scan for service directories (packages/, services/, apps/)
- Parse package.json for dependencies and scripts
- Build dependency graph
- Detect package managers per service
- Determine topological execution order
- Flag circular dependencies
Execution Modes
Cascade Mode
- Sequential execution following dependency order
- Wait for health check before starting dependents
- Stop on failure with detailed error report
- Support partial cascade (skip healthy services)
Parallel Mode
- Concurrent execution for independent services
- Optional worktree isolation per service
- Configurable concurrency limit
- Collect all results (continue on individual failures)
Auto Mode (Default)
- Analyze dependency graph
- Use cascade for services with sequential dependencies
- Use parallel for independent service groups
- Hybrid: cascade between groups, parallel within groups
PM2 Management
- Generate ecosystem.config.js from service manifest
- Configure per service: name, script, cwd, env, instances
- Start in topological order with health check gates
- Log rotation and restart policies
- Status monitoring: online, stopped, errored
Cross-Service Testing
- API contract verification (request/response schemas)
- Event bus message flow testing
- Shared state consistency checks
- Authentication across service boundaries
- Circuit breaker behavior validation
Health Monitoring
- Health check endpoint polling
- PM2 process status monitoring
- Resource usage tracking (CPU, memory)
- Log file error pattern detection
- Inter-service connectivity verification
When to Use
- Multi-package monorepo development
- Microservice orchestration
- Full-stack application management
- CI/CD pipeline for multi-service deployments
Agents Used
architect(service discovery and dependency mapping)build-resolver(individual service builds)e2e-runner(cross-service integration testing)
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 · 73 lines · 27 tokens per session scan A 4305c0d0ab06
multi-service-orchestration is a skill published in the GitHub repository a5c-ai/babysitter (1,783 stars, last pushed 5d ago), licensed MIT. It adds 27 tokens to every session and 490 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
moai-platform-deployment
Deployment and hosting platform specialist covering Vercel, Railway, and Convex. Use when deploying applications, configuring edge functions, setting up continuous deployment, or managing serverless infrastructure.
sinch-functions
Sinch Functions, the beta serverless platform for voice, SMS and conversation apps. Use for platform questions: what it is, how deployment works, choosing Node.js or C#, install and auth, FunctionContext, handlers, the Voice v2 call lifecycle and call. events, voice services and VOICESERVICEID, and SVAML. Runtime code…
sinch-cli
Terminal commands for the Sinch CLI (sinch, npm @sinch/cli). Use whenever the user runs or asks about a sinch command: login, Functions init/dev/deploy/logs/status, phone numbers and porting, sending SMS/WhatsApp/RCS, placing calls and configuring voice services, fax, SIP trunks, secrets and templates. Runtime code is…
software-design-system-design
Design scalable distributed systems using structured approaches for load balancing, caching, database scaling, and message queues. Use when the user mentions "system design", "scale this", "high availability", "rate limiter", "design a URL shortener", "system design interview", "capacity planning", or "distributed…
cloudflare-workers-expert
Expert in Cloudflare Workers and the Edge Computing ecosystem. Covers Wrangler, KV, D1, Durable Objects, and R2 storage.
fleetq-connect
Connect an agent to FleetQ over MCP or the REST API, including obtaining credentials via dynamic client registration.