a5c-ai/babysitter

Babysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestration

About the project

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 →

1.8kStars on the repository
186Mods indexed here, across every type
6d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

a5c-ai/babysitter

Skill Claude Code

Generate personalized verified news briefs with 7-day freshness and 95%+ source accuracy.

not rated 1.8k +16 6d ago A SkillSpector: pass 24 tokens original MIT

a5c-ai/babysitter

Skill Claude Code

Build structured knowledge frameworks from scattered vault notes with source attribution.

not rated 1.8k +16 6d ago A SkillSpector: pass 19 tokens original MIT

a5c-ai/babysitter

Skill Claude Code

Process meeting recordings and transcripts into decisions, action items, and team dynamics.

not rated 1.8k +16 6d ago A SkillSpector: pass 20 tokens original MIT

cog-onboarding

52

a5c-ai/babysitter

Skill Claude Code

Personalize COG Second Brain workflow through role pack selection and vault initialization.

not rated 1.8k +16 6d ago A SkillSpector: pass 19 tokens original MIT

a5c-ai/babysitter

Skill Claude Code

Cross-reference GitHub, Linear, Slack, and PostHog with bidirectional sync for team briefs.

not rated 1.8k +16 6d ago A SkillSpector: pass 26 tokens original MIT

cog-url-extraction

54

a5c-ai/babysitter

Skill Claude Code

Save URLs with auto-extracted insights, credibility scoring, and vault routing.

not rated 1.8k +16 6d ago A SkillSpector: pass 20 tokens original MIT

a5c-ai/babysitter

Skill Claude Code

Cross-domain pattern analysis with personal, professional, and project domain synthesis.

not rated 1.8k +16 6d ago A SkillSpector: pass 20 tokens original MIT

a5c-ai/babysitter

Skill Claude Code

Multi-dimensional code review across correctness, security, performance, and maintainability with confidence-gated reporting and remediation loops.

not rated 1.8k +16 6d ago A SkillSpector: pass 28 tokens original MIT

context-engineering

57

a5c-ai/babysitter

Skill Claude Code

Dynamic context injection, mode switching (dev/review/research), selective loading, and strategic compaction for token optimization.

not rated 1.8k +16 6d ago A SkillSpector: pass 28 tokens original MIT

continuous-learning

58

a5c-ai/babysitter

Skill Claude Code

Pattern extraction, confidence-scored evaluation, skill creation, organization, versioning, and cross-project export pipeline.

not rated 1.8k +16 6d ago A SkillSpector: pass 25 tokens original MIT

eval-harness

59

a5c-ai/babysitter

Skill Claude Code

Evaluation harness for testing agent and skill quality through structured benchmarks, regression tests, and quality scoring.

not rated 1.8k +16 6d ago A SkillSpector: pass 23 tokens original MIT

a5c-ai/babysitter

Skill Claude Code

PM2 process management, backend/frontend cascade execution, parallel worktree builds, and cross-service integration testing.

not rated 1.8k +16 6d ago A SkillSpector: pass 27 tokens original MIT

research-first-dev

61

a5c-ai/babysitter

Skill Claude Code

Research-first development methodology that investigates existing solutions, brainstorms alternatives, and evaluates trade-offs before any implementation begins.

not rated 1.8k +16 6d ago A SkillSpector: pass 26 tokens original MIT

security-scanning

62

a5c-ai/babysitter

Skill Claude Code

AgentShield security audit with 5 scanning categories, 102 static analysis rules, and optional red-team simulation.

not rated 1.8k +16 6d ago A SkillSpector: warn 26 tokens original MIT

tdd-enforcement

63

a5c-ai/babysitter

Skill Claude Code

Red-Green-Refactor TDD methodology with mandatory failing tests, minimal implementation, quality refactoring, and 80% coverage gating.

not rated 1.8k +16 6d ago A SkillSpector: pass 33 tokens original MIT

agent-coordination

64

a5c-ai/babysitter

Skill Claude Code

Coordinate Crew (persistent) and Polecat (transient) agents using Gas Town's hook-based work distribution and GUPP principle.

not rated 1.8k +16 6d ago A SkillSpector: pass 31 tokens original MIT

convoy-management

65

a5c-ai/babysitter

Skill Claude Code

Create, track, and land convoys of related beads as primary work orders in the Gas Town multi-agent orchestration framework.

not rated 1.8k +16 6d ago A SkillSpector: pass 29 tokens original MIT

formula-authoring

66

a5c-ai/babysitter

Skill Claude Code

Author TOML-based Formula workflow templates that become Protomolecules and active Molecules in Gas Town's durable workflow system.

not rated 1.8k +16 6d ago A SkillSpector: pass 28 tokens original MIT

issue-tracking

67

a5c-ai/babysitter

Skill Claude Code

Track beads as git-backed issues with persistent attribution, supporting Gas Town's bead lifecycle and convoy progress monitoring.

not rated 1.8k +16 6d ago A SkillSpector: pass 25 tokens original MIT

merge-queue

68

a5c-ai/babysitter

Skill Claude Code

Process the Refinery merge queue - collect agent work, detect and resolve conflicts, merge in dependency order, and verify integration.

not rated 1.8k +16 6d ago A SkillSpector: pass 29 tokens original MIT

patrol-monitoring

69

a5c-ai/babysitter

Skill Claude Code

Continuous monitoring using Deacon/Witness patterns for agent health checks, stuck detection, and automated recovery.

not rated 1.8k +16 6d ago A SkillSpector: pass 25 tokens original MIT

session-management

70

a5c-ai/babysitter

Skill Claude Code

Manage agent sessions including initialization, handoffs, revival (seance), and persistent identity for Polecats and Crew agents.

not rated 1.8k +16 6d ago A SkillSpector: pass 27 tokens original MIT

work-decomposition

71

a5c-ai/babysitter

Skill Claude Code

Decompose goals into MEOWs (Molecular Expressions of Work) - trackable atomic units following Gas Town's bead-based work model.

not rated 1.8k +16 6d ago A SkillSpector: pass 32 tokens original MIT

frontmatter-parsing

72

a5c-ai/babysitter

Skill Claude Code

YAML frontmatter parsing and manipulation for .planning/ documents. Provides read, write, update, query, and validation operations on frontmatter blocks in GSD markdown artifacts.

not rated 1.8k +16 6d ago A SkillSpector: pass 40 tokens original MIT

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: