By udaykabe
AI Development Agents (AIDA) - Agentic framework for autonomous project execution with human-in-the-loop checkpoints. Coordinates specialized sub-agents through a research-plan-execute-review pipeline.
npx claudepluginhub udaykabe/odo --plugin aidaLog a deferred issue or enhancement to ISSUES.md
Create project roadmap with phases
Execute the current approved plan
Analyze codebase with parallel agents to produce .planning/codebase/ documents
View auto-derived AIDA project metrics from git history and planning artifacts
Initialize a new AIDA project with PROJECT.md and planning structure
Create context handoff when pausing work mid-phase
Create detailed execution plan for a phase
Check AIDA project status and route to next action
Research a topic or phase before planning
Resume work from previous session with context restoration
Review deferred issues and decide which to address
Run verification suite from PROJECT.md commands. Args: quick | smoke
Executes plan segments autonomously. Handles coding, testing, and documentation tasks. Returns to orchestrator at checkpoints.
Creates detailed phase execution plans (PLAN.md) from research findings. Produces structured, executable task lists with checkpoints.
Explores codebase to gather context for phase planning. Use for understanding existing patterns, finding relevant files, and researching implementation approaches.
Verifies phase completion quality. Runs tests, checks requirements, validates outputs against plan.
Map an existing codebase via parallel Explore agents, producing 7 reference documents (STACK, INTEGRATIONS, ARCHITECTURE, STRUCTURE, CONVENTIONS, TESTING, CONCERNS) in .planning/codebase/.
Project planning and execution workflow. Use when user mentions phases, roadmaps, milestones, planning, project management, or wants to execute work systematically. Coordinates research, planning, execution, and review sub-agents.
A collection of Claude Code plugins.
| Plugin | Description |
|---|---|
| aida | AI Development Agents -- Agentic framework for autonomous project execution with human-in-the-loop checkpoints |
# Install a single plugin
claude --plugin-dir ./plugins/aida
# Install for current user (all projects)
claude plugin install aida@<marketplace>
# Install for current project (shared with team)
claude plugin install aida@<marketplace> --scope project
plugins/
aida/ # AI Development Agents plugin
.claude-plugin/plugin.json
agents/
commands/
skills/
settings.json
CLAUDE.md.template
LICENSE
README.md # This file
plugins/<plugin-name>/.claude-plugin/plugin.json manifestMIT
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Uses power tools
Uses Bash, Write, or Edit tools
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research