Skill Claude Code
System and API design guidance covering component boundaries, data flow, integration patterns, and scalability considerations.
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
System and API design guidance covering component boundaries, data flow, integration patterns, and scalability considerations.
Skill Claude Code
Minimal, pattern-matching code output. Write the least code that satisfies requirements. Match existing project patterns. Use Write/Edit tools only.
Skill Claude Code
Multi-dimensional code assessment across security, quality, performance, and maintainability with confidence-gated reporting (>=80%) and Router Contract generation.
Skill Claude Code
Root cause analysis frameworks including log-first investigation, git bisect correlation, and pattern-based diagnosis with confidence scoring.
Skill Claude Code
Structured planning methodology with research, brainstorming, phased plan creation, risk assessment, and plan-to-build continuity.
Skill Claude Code
Mandatory memory persistence system across session resets using three markdown surfaces in .claude/cc10x/. Iron law - every workflow must load at start and update at end.
Skill Claude Code
Strict RED-GREEN-REFACTOR cycle enforcement. Tests are never skipped or deferred. Run mode only, never watch mode. Exit code evidence mandatory.
Skill Claude Code
Evidence requirement enforcement ensuring all claims are backed by logs, test results, or exit codes. Zero = success, non-zero = failure. No guessing allowed.
Skill Claude CodeCodex
Full traceability from PRD to code commit through the CCPM spec-driven pipeline.
Skill Claude CodeCodex
Project context loading, isolation, and persistent state management across CCPM sessions.
Skill Claude CodeCodex
Transform PRD into a technical implementation plan with architecture decisions and dependency mapping.
Skill Claude CodeCodex
Bidirectional synchronization of epics and tasks with GitHub issues, labels, and relationships.
Skill Claude CodeCodex
Coordinate multiple specialized agents across parallel work streams with quality gates and conflict resolution.
Skill Claude CodeCodex
Status dashboards, standup reports, and blocked task management with GitHub synchronization.
Skill Claude CodeCodex
Break epics into parallelizable tasks with acceptance criteria, effort estimates, and dependency graphs.
Skill Claude Code
Git-backed state management for safe rollback. Create and restore checkpoints with tagged commits and metadata tracking.
Skill Claude Code
6-agent parallel code review orchestration covering architecture, security, performance, testing, quality, and documentation dimensions with weighted scoring.
Skill Claude Code
Automatic codebase indexing for invisible context injection. Catalogs project structure, file types, entry points, dependencies, and test layout.
Skill Claude Code
PreToolUse protection blocking sensitive file access across 195+ patterns in 12 categories with bash pipeline analysis and multi-tool ignore support.
Skill Claude Code
Session-scoped hook lifecycle management with enable/disable/status controls, execution profiling, and color-coded performance alerts.
Skill Claude Code
Parallel research agent orchestration dispatching 5-10 concurrent agents for comprehensive multi-source research with synthesis and validation.
Skill Claude Code
Feature specification creation from codebase research. Produces requirements, acceptance criteria, architecture decisions, implementation plans, and risk analysis.
Skill Claude Code
6-phase iterative specification execution workflow covering implementation, testing, review, improvement, commit, and progress tracking with quality-gated convergence.
Skill Claude Code
Capture raw thoughts with automatic domain classification and vault routing.
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: