By az9713
Full agentic layer framework implementing the Codebase Singularity concept - enabling AI agents to operate your codebase autonomously through planning, building, reviewing, and fixing workflows. Implements Class 1-3 with orchestration capabilities.
Structured bug investigation and fix workflow. Investigates, plans, fixes, tests, and verifies the resolution.
Implement features following an approved plan or specification. Creates code, tests, and documentation.
Execute the complete Plan-Build-Review-Fix development cycle for a feature or change. The core workflow of the framework.
Directly invoke a specific agent for a targeted task. Useful when you know exactly which agent you need.
Complete feature development workflow from specification to tested, reviewed code ready for commit.
Master coordinator that manages multi-agent workflows, delegates tasks to specialized agents, and ensures cohesive execution of complex operations.
Strategic planning agent that creates detailed implementation plans, analyzes requirements, and designs system architecture before coding begins.
Implementation agent that writes clean, tested code following plans and project conventions. Creates new files and modifies existing ones.
Quality analysis agent that performs thorough code reviews, identifies issues, and provides actionable feedback with severity ratings.
Issue resolution agent that implements fixes for bugs and review findings with minimal, focused changes and verification.
Code review checklist and best practices for thorough quality assessment.
Git workflow patterns for branching, commits, and pull requests following project conventions.
Project development workflow patterns including Plan-Build-Review-Fix cycle and feature development processes.
Testing patterns, strategies, and best practices for comprehensive test coverage.
Admin access level
Server config contains admin-level keywords
Requires secrets
Needs API keys or credentials to function
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
A Claude Code plugin implementing the "Codebase Singularity" concept by IndyDevDan. This framework creates an agentic layer around your codebase, enabling AI agents to operate autonomously through planning, building, reviewing, and fixing workflows.
The Codebase Singularity is the point where AI agents can run your codebase better than you can. The framework provides:
This implementation is Class 3, Grade 1+ - the highest level of the agentic layer framework:
| Class | Description | Status |
|---|---|---|
| Class 1 | Foundation (memory, agents, tools, hooks) | ✓ Complete |
| Class 2 | Workflows (portable layers, E2E flows) | ✓ Complete |
| Class 3 | Orchestration (multi-agent coordination) | ✓ Complete |
/prime
Install globally (one-time):
# Copy commands and agents to ~/.claude/
cp -r .claude/commands/project ~/.claude/commands/singularity
cp -r agents/*.md ~/.claude/agents/
cp -r skills/* ~/.claude/skills/
Initialize in new project:
/setup
Start developing:
/plan Add user authentication
/build
/review
/fix
Or use the complete cycle:
/cycle Add user authentication
| Command | Purpose |
|---|---|
/prime | Activate with full context |
/plan | Create implementation plan |
/build | Implement from plan |
/review | Quality analysis |
/fix | Address issues |
| Command | Purpose |
|---|---|
/cycle | Complete Plan-Build-Review-Fix |
/feature | Full feature development |
/bugfix | Bug investigation and fix |
| Command | Purpose |
|---|---|
/orchestrate | Multi-agent coordination |
/delegate | Direct agent invocation |
| Command | Purpose |
|---|---|
/setup | Initialize in new project |
| Agent | Model | Specialty |
|---|---|---|
| orchestrator | opus | Multi-agent coordination |
| planner | opus | Planning, architecture |
| builder | sonnet | Code implementation |
| reviewer | opus | Quality analysis |
| fixer | sonnet | Issue resolution |
| test-writer | sonnet | Test creation |
| doc-fetcher | haiku | Documentation research |
| security-auditor | opus | Security analysis |
| refactorer | sonnet | Code improvement |
├── .claude-plugin/plugin.json # Plugin manifest
├── commands/ # 11 workflow commands
├── agents/ # 9 specialized agents
├── skills/ # 4 skill modules
├── hooks/hooks.json # Lifecycle hooks
├── scripts/ # Hook scripts
├── templates/settings.json # Project settings
├── specs/ # Plans and reviews
├── ai_docs/ # AI reference docs
├── CLAUDE.md # Claude-specific memory
├── AGENTS.md # Universal agent instructions
├── .mcp.json # MCP configuration
└── README.md # This file
The Plan-Build-Review-Fix cycle is the foundation:
┌─────────┐ ┌─────────┐ ┌─────────┐ ┌─────────┐
│ PLAN │───►│ BUILD │───►│ REVIEW │───►│ FIX │
└─────────┘ └─────────┘ └─────────┘ └────┬────┘
▲ │
└────────── Loop until quality passes ◄──────┘
| Document | Purpose |
|---|---|
CLAUDE.md | Claude-specific memory - read first |
AGENTS.md | Universal AI agent instructions |
docs/QUICKSTART.md | 20 hands-on use cases |
docs/USER_GUIDE.md | How to use the framework |
docs/DEVELOPER_GUIDE.md | Technical deep-dive |
docs/AGENTIC_LAYER.md | Core concept explanation |
docs/CLASSIFICATION.md | Class/Grade system reference |
docs/HOOKS_GUIDE.md | Hooks and feedback loops |
docs/CONFIGURATION_GUIDE.md | All settings and options |
Install commands globally (one-time setup):
# From this project directory:
cp -r .claude/commands/project ~/.claude/commands/singularity
cp -r agents/*.md ~/.claude/agents/
cp -r skills/* ~/.claude/skills/
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
Thread-Based Engineering examples - demonstrates Base, Parallel, Chained, Fusion, Big, Long, and Zero-Touch thread patterns for agentic coding
Design fluency for frontend development. 1 skill with 23 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection.
Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM coding pitfalls
Design fluency for frontend development. 1 skill with 23 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection.
npx claudepluginhub az9713/claude-code-agentic-framework11 agents, 35 skills, 18 commands, 9 hooks — spec-driven multi-agent orchestration for Claude Code, with optional cross-device semantic memory.
Multi-agent /workflow development pipeline (planner → plan-review → coder → code-review) with typed handoff contracts, lifecycle hooks, and MCP servers.
Automation bootstrap for Claude Code. Analyzes any project and generates a complete .claude/ structure with agents, pipelines, skills, memory, hooks, and settings.
Conductor v3 — Multi-agent orchestration with Evaluate-Loop, parallel execution, Board of Directors, and bundled SupaConductor skills for Claude Code
Harness for Claude Code — skills, /harness:* slash commands, persona subagents, lifecycle hooks, and MCP tools without per-repo `harness setup`. Sibling plugins exist for Cursor, Gemini CLI, and Codex.
Complete project development toolkit: 23 agents, 23 slash commands, 29 lifecycle hooks, and 69 reusable skills for Claude Code workflows