Babysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestration
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.
This repository also configures its own agents. See what babysitter tells them →
Skill Claude Code
Git commit patterns, formats, and conventions for GSD methodology. Provides atomic commits per task, structured commit messages, planning file commits, branch management, and milestone tag operations.
Skill Claude Code
Central utility skill for GSD operations. Provides config parsing, slug generation, timestamps, path operations, and orchestrates calls to other specialized skills. Acts as the unified entry point that the original gsd-tools.cjs provided via its lib/ modules (commands, config, core, init).
Skill Claude Code
Resolve model profile (quality/balanced/budget) at orchestration start and map agents to specific models. Enables cost/quality tradeoffs by selecting appropriate AI models for each agent role.
Skill Claude Code
Roadmap parsing, analysis, and mutation operations for ROADMAP.md. Handles phase and milestone lifecycle including add, insert (decimal), remove, complete, and requirements coverage analysis.
Skill Claude Code
STATE.md reading, writing, and field-level updates. Provides cross-session state persistence via .planning/STATE.md with structured fields for current task, completed phases, blockers, decisions, and quick tasks.
Skill Claude Code
Template loading, variable filling, and scaffolding for all GSD artifacts. Manages 22+ templates covering every document type in the GSD system, from PROJECT.md to milestone archives.
Skill Claude Code
Plan structure validation, phase completeness checks, reference integrity verification, and artifact existence confirmation. Provides the structured verification layer ensuring GSD artifacts are well-formed and complete.
Skill Claude Code
Urgent issue classification, root cause analysis, and fast-path routing for production hotfixes.
Skill Claude Code
Capture, validate, query, and sync architectural patterns and design decisions in the knowledge graph.
Skill Claude Code
Technical debt management including branch cleanup, doc verification, TODO scanning, and dependency auditing.
Skill Claude Code
Interactive PM interview with expertise-adaptive questioning for requirements elicitation.
Skill Claude Code
Convert requirements into structured technical specifications with architecture decisions.
Skill Claude Code
Break technical specifications into small, implementable stories with dependency ordering.
Skill Claude Code
Automated test validation, coverage checking, and quality metrics with aggressive defaults.
Skill Claude Code
Fresh adversarial code review with binary PASS/FAIL verdicts, evidence citations, and anchoring bias prevention via fresh reviewer spawning.
Skill Claude Code
Parallel design review by 6 specialist agents (PM, Architect, Designer, Security Design, UX, CTO) with mandatory unanimous approval.
Skill Claude Code
Coordinate external AI tool integration (OpenAI Codex, Google Gemini) for cross-model adversarial review and delegated implementation.
Skill Claude Code
Context priming before work (bd prime) and self-reflection after completion to extract patterns, gotchas, and decisions into the knowledge base.
Skill Claude Code
Execute work units through the rigorous 4-phase Metaswarm cycle (Implement -> Validate -> Adversarial Review -> Commit) with independent quality gate enforcement.
Skill Claude Code
Adversarial plan review by 3 independent reviewers (Feasibility, Completeness, Scope & Alignment) before presenting to user.
Skill Claude Code
Monitor PR lifecycle from creation through merge including CI monitoring, review comment handling, thread resolution, and merge readiness verification.
Skill Claude Code
Decompose implementation plans into discrete work units with enumerated DoD items, file scope declarations, dependency mapping, and human checkpoint flags.
Skill Claude Code
Bug condition/postcondition formalization as testable Behavior Contracts. Defines invariants that must be preserved across fixes.
Skill Claude Code
Convention discovery and rule generation from codebase analysis. Scans project structure, builds search indexes, identifies patterns, and generates enforceable rules.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: