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
State capture and restore across context window compactions. Monitors usage thresholds and serializes quality, task, and spec state for seamless continuation.
Skill Claude Code
Observation capture and retrieval across sessions. Stores decisions, discoveries, and bugfix patterns. Searchable via tags and relevance scoring.
Skill Claude Code
Language-specific auto-lint/format/typecheck pipeline. Supports Python (ruff+pyright), TypeScript (prettier+eslint+tsc), Go (gofmt+golangci-lint). Auto-fix and convergence loops.
Skill Claude Code
Specification creation and management for the Pilot Shell methodology. Covers semantic search, clarifying questions, structured spec generation, and iterative refinement.
Skill Claude Code
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
Skill Claude CodeCodex
Verify all phases are complete with weighted quality scoring before allowing session exit.
Skill Claude CodeCodex
Log all errors with full context, detect patterns, and suggest approach mutations to avoid repeated failures.
Skill Claude CodeCodex
Capture and persist research findings, discoveries, and decision rationale to findings.md.
Skill Claude CodeCodex
Create a structured taskplan.md with phases, goals, and checkbox tracking for persistent planning.
Skill Claude CodeCodex
Detect and recover previous planning sessions, reconstructing lost context from persistent planning files.
Skill Claude Code
Clarify vague requirements through exploratory questioning and option generation before committing to research or implementation.
Skill Claude Code
Systematic codebase exploration following the Iron Law - understand the problem before exploring code. Four phases with file-finder and web-researcher agents.
Skill Claude Code
Create Architecture Decision Records (ADRs) documenting significant technical choices with context, options, consequences, and sequential numbering.
Skill Claude Code
Final completion discipline including summary generation, plan document updates, and confirmation that all success criteria from the original plan are satisfied.
Skill Claude Code
Disciplined execution of approved plans with step-by-step verification, phase checkpoints, failure investigation, and mandatory code/security reviews.
Skill Claude Code
Transform research findings into actionable implementation plans with stakes-based rigor, test-first strategy, and granular task decomposition.
Skill Claude Code
Security vulnerability assessment identifying OWASP risks, injection vectors, authentication issues, and data exposure with severity classification.
Skill Claude Code
Structured debugging methodology using hypothesis-driven investigation, log analysis, and bisection to isolate and resolve defects.
Skill Claude Code
Verification-before-completion discipline ensuring all success criteria are met, tests pass, and reviews complete before declaring work done.
Skill Claude Code
WASM-based instant code transforms for simple tasks, achieving 352x speedup over LLM inference with zero cost.
Skill Claude Code
Hierarchical coordination and drift detection with frequent checkpoints, shared memory coherence validation, role specialization enforcement, and short task cycles.
Skill Claude Code
Multi-protocol consensus for agent swarms supporting Raft leader election, Byzantine fault tolerance, Gossip state propagation, and CRDT conflict-free merging.
Skill Claude Code
AIDefence security layer with prompt injection blocking, input validation, sandboxed execution, output sanitization, and STRIDE threat modeling.
Skill Claude Code
SONA self-optimizing neural architecture with ReasoningBank trajectory learning, EWC++ anti-forgetting, and reinforcement learning feedback loops.
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: