Orchestrate the full SDLC from idea to shipped code: plan from requirements, implement in phases, validate with assertions and browser tests, audit codebase quality, review diffs, refactor across quality axes, and debug with root cause analysis.
Milestone executor. Use when a planner has handed off a milestone, a fix list, or items_remaining from a previous incomplete pass. Codes, tests, repairs. Returns what's done, what's remaining, and a completion score. Never replans, never judges.
Planning agent. Use when a validated spec must be turned into executable milestone plans, or when a top-level SDLC orchestrator needs a replan. Writes plans and decisions only. Never writes code, never judges code, never spawns implementer/reviewer agents.
Independent critic in fresh context. Use when an artifact (code, spec, plan, doc) needs verification against a validator (acceptance criteria, checklist file, or any explicit ruleset). Returns reviewed items, findings, completion score and quality score. Never edits the artifact, never decides what to do next.
Pure orchestrator for the full AIDD development flow. Use when a human (or Gardener) needs to take a free-form request from idea to shipped code, end-to-end. Coordinates spec generation, planning, implementation, review, and shipping by composing other skills and agents. Supports two modes - `auto` (default, no human interaction) and `interactive` (pauses for human confirmation at key gates). Holds no business logic of its own; every step is delegated.
Generate technical implementation plans, define component behaviors, and extract design details from images.
Execute an implementation plan phase by phase via the implementer agent, iterating until 100% completeness.
Assert features work as intended - general assertions, architecture conformance, and frontend UI validation.
Read-only codebase audit across quality pillars (code-quality, architecture, security, dependencies, performance, tests, ui). Diagnoses and reports findings; never edits code. Use when the user wants to assess, audit, or health-check a codebase or one dimension of it, then hands off to the act-skills (refactor, test, impeccable) to fix. Do NOT use for fixing the findings (hand off to refactor/test/impeccable), per-PR code review (use 05-review), or validating that a feature works (use 03-assert).
Uses power tools
Uses Bash, Write, or Edit tools
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.
6 plugins · 37 skills · 3 agents · MIT
Quick start → · Browse plugins → · How it works → · Join Discord →
The AIDD Framework is a marketplace of skills, agents, rules, and conventions that make the AI-Driven Development flow concrete inside your AI coding assistant - the full SDLC (plan → implement → review → ship) under rigorous human supervision. It is the open toolset of the AI-Driven Dev community.
The framework is authored for Claude Code, and this repository is its native marketplace. Every release also attaches archives adapted to each tool we support - Cursor, GitHub Copilot, Codex, OpenCode (marketplace or flat format per tool) - so you grab the build that matches your assistant. See Another AI tool? for the per-tool download + install table.
Founded by Alex Soyes - Blog · GitHub · LinkedIn · X.
Join the conversation: Discord · YouTube · LinkedIn · Website
Just an AI coding assistant. Everything else is per-plugin and optional.
| To… | You need |
|---|---|
| Register & run the marketplace | An AI assistant - Claude Code runs this marketplace natively; for another tool, grab the release archive the aidd-cli builds for it |
| Use a plugin's extras | Only what that plugin's README lists - e.g. gh / glab for VCS, a ticketing tool for PM |
Nothing beyond the AI tool is required just to register the marketplace.
Register the marketplace and install the core plugins (Claude Code slash commands, not shell):
/plugin marketplace add ai-driven-dev/framework
/plugin install aidd-context@aidd-framework
/plugin install aidd-refine@aidd-framework
/plugin install aidd-dev@aidd-framework
/plugin install aidd-vcs@aidd-framework
Then set up project context (guided onboard, or direct project-init) and run the dev flow:
---
title: AIDD quick start
---
flowchart TD
Install["Marketplace + plugins installed"]
Setup{"Set up context"}
Onboard["aidd-context:00-onboard - guided hub"]
Init["aidd-context:02-project-init - context engineering"]
Brainstorm["aidd-refine:01-brainstorm"]
Plan["aidd-dev:01-plan"]
Implement["aidd-dev:02-implement"]
Assert["aidd-dev:03-assert"]
Review["aidd-dev:05-review"]
Commit["aidd-vcs:01-commit"]
PR["aidd-vcs:02-pull-request"]
Learn["aidd-context:10-learn"]
Install --> Setup
Setup -->|guided| Onboard
Setup -->|direct| Init
Onboard --> Init
Init --> Brainstorm
Brainstorm --> Plan
Plan --> Implement
Implement --> Assert
Assert --> Review
Review --> Commit
Commit --> PR
PR --> Learn
/aidd-context:00-onboard - it inspects the project and guides you./aidd-dev:00-sdlc runs plan → implement → review → ship./plugin Discover tab.npx claudepluginhub ai-driven-dev/frameworkOrchestration plugin. v1 use case: async development - turn ready issues into pull requests, then iterate on review feedback until a human takes over. Designed to host more orchestration use cases (refactoring, docs, audits) in future versions.
Product management: ticket-info, user-stories-create, prd, spec
External artifacts: commit, pull-request, release-tag, issue-create
Meta-cognition: refine input through brainstorming, refine output through challenge and condensed communication mode.
Knowledge production: project bootstrap, project init, generation of context artifacts (skills, agents, rules, commands, hooks), mermaid diagrams, learn, discovery
AI-powered development workflow automation - Phase-based planning, implementation orchestration, preflight code quality checks with security scanning, ship-it workflow, and development principles generator for CLAUDE.md
Persona-driven AI development team: orchestrator, team agents, review agents, skills, slash commands, and advisory hooks for Claude Code
Helder's personal SDLC toolbelt for AI coding agents — from PRD to ship. Bundles the tracer-bullet workflow alongside TDD, code review, audits, and shipping skills.
PROJECT.md-first autonomous development with hybrid auto-fix documentation. 8-agent pipeline, auto-orchestration, docs auto-update on commit (true vibe coding). Knowledge base system with 90% faster repeat research. Strict mode enforces SDLC best practices automatically. Works for ANY Python/JavaScript/TypeScript/Go project.
Verification-first engineering toolkit for Claude Code. 15 skills across a 5-phase spine (Investigate → Design → Implement → Verify → Ship), 8 specialist agents, an interactive setup wizard. Every skill has rationalizations + evidence requirements. Built for senior ICs and tech leads.
AI-First SDLC — zero-debt development with validators, enforcement, and workflows