Agentic AI development workflow for Claude Code — AI-specific skills, agents, and project context for teams building AI automations
npx claudepluginhub selcukyucel/north-starr-genaiAgentic AI development workflow for Claude Code — AI-specific skills, agents, hooks, and project context for teams building AI automations
Your North Starr for AI Development | v0.11.0
An agentic AI development agency framework — North Starr plans, designs, validates, and orchestrates while Claude Code writes code in YOUR codebase. Works with any project: RAG pipelines, agent harnesses, multi-agent systems, prompt chains, or AI platform components.
North Starr GenAI is the brain of an AI development agency. It doesn't generate code — it generates the specs, designs, evaluations, and guardrails that make AI code production-grade.
CLIENT (you) → gives requirement
NORTH STARR (brain) → plans, designs, validates, orchestrates, quality-gates
CLAUDE CODE (hands) → reads North Starr's specs + writes code in YOUR codebase
/bootstrap → makes Claude Code aware of your specific codebase patterns
Requirement → /assess (classify project type)
→ /discover (elicit requirements if needed)
→ /decompose (PRD → stories with AI safety criteria)
→ /orchestrate (start the pipeline)
→ TRIAGE: chief-ai-po refines story
→ DESIGN: ai-architect → ADR + cost envelope
→ PLAN: layoutplan → tasks with specialist tags
→ BUILD: specialists produce specs → Claude Code implements
→ HARDEN: eval + guardrails + ops validate (ALL must pass)
→ DELIVER: demo-builder packages for client
Before ANY code change, the gate catches AI-specific risks:
| # | Question | Why |
|---|---|---|
| Q0 | Is current behavior covered by evals? | Eval-first discipline |
| Q1 | Does this touch a production prompt or model config? | Prompt changes are high-risk |
| Q2 | Does this change what data the model sees? | Data changes alter model behavior |
| Q3 | Does this affect a client-facing output? | Client-visible changes need baselines |
| Q4 | Could this change cost at scale? | Cost is a first-class concern |
Based on answers, it routes through: ASSESS → BUILD (specialists auto-spawn) → HARDEN (validators auto-run) → COMPLETE → LEARN.
Which option? Use Option A if you work in Claude Code — all 23 skills and 15 agents load directly into your session, no file generation needed. Use Option B + C if you work in VS Code with GitHub Copilot — the CLI generates project files that Copilot reads.
/plugin marketplace add selcukyucel/north-starr-genai
/plugin install north-starr-genai
This immediately makes all 23 skills (e.g. /assess, /decompose, /orchestrate) and 15 agents available in your Claude Code session. No files are added to your project — the plugin lives in ~/.claude/plugins/.
Then run /bootstrap in your project to generate a CLAUDE.md with your codebase's tech stack, architecture, and module map. This lets North Starr tailor its output to your specific project.
Update:
/plugin marketplace update selcukyucel/north-starr-genai
/plugin install north-starr-genai
After updating, run north-starr-genai cache-update if skills don't reflect the latest version.
Uninstall:
/plugin uninstall north-starr-genai
/plugin marketplace remove selcukyucel/north-starr-genai
This removes the plugin from Claude Code. Any CLAUDE.md generated by /bootstrap stays in your project — delete it manually if you no longer want it.
brew tap selcukyucel/north-starr-genai
brew install north-starr-genai
This installs the north-starr-genai CLI to your PATH. The CLI is used to initialize and update project files for VS Code Copilot (see Option C). It does not add skills to Claude Code — use Option A for that.
Update:
brew upgrade north-starr-genai
Uninstall:
brew uninstall north-starr-genai
brew untap selcukyucel/north-starr-genai
After installing the CLI via Homebrew (Option B), run in your project directory:
north-starr-genai init
This copies skills, agents, and instruction templates into your project:
.github/agents/ — agent definitions for Copilot.github/skills/ — skill definitions.github/instructions/ — pattern and landmine rulesAGENTS.md — workflow gates and specialist dispatch instructionsThese files give VS Code Copilot the same AI complexity gate and specialist dispatch workflow that Claude Code gets from the plugin.
Update:
north-starr-genai update
Preserves your project-specific configuration while updating skill and agent definitions.
Uninstall: Remove the generated files from your project:
rm -rf .github/agents/ .github/skills/ .github/instructions/
rm AGENTS.md
Bootstrap your codebase (once per project):
/bootstrap
Start building — pick your entry point:
Claude Code marketplace entries for the plugin-safe Antigravity Awesome Skills library and its compatible editorial bundles.
Production-ready workflow orchestration with 84 marketplace plugins, 192 local specialized agents, and 156 local skills - optimized for granular installation and minimal token usage
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations