Getting Started

Install & configure effectum

effectum takes about 2 minutes to install. Once set up, type /effectum to pick your journey — then write a spec and let Claude build it with tests, quality gates, and guardrails.

Prerequisites

Claude Code installed and configured
Node.js 18+ and npx available
A project directory (new or existing)

Installation

The recommended way to install effectum is the interactive installer. It walks you through selecting a stack preset and scope.

terminal

npx @aslomon/effectum

Installation options

GlobalRecommended for individuals

Installs to ~/.claude/ — available in all projects. Ideal if you use Claude Code across many repositories.

terminal

npx @aslomon/effectum --global

LocalRecommended for teams

Installs to ./.claude/ — committed with your repo so everyone shares the same workflow and guardrails.

terminal

npx @aslomon/effectum --local

Non-interactiveFor CI / automation

Skips all prompts. Uses Claude Code runtime defaults. Good for scripted setups and CI pipelines.

terminal

npx @aslomon/effectum --global --claude

Classic git cloneFull control

Clone the repo and use effectum:setup to configure manually. Best when you want to inspect every file before applying.

terminal

git clone https://github.com/aslomon/effectum.git
cd effectum && claude
effectum:setup ~/my-project

What gets installed

42 workflow commands

Slash commands for the entire lifecycle — /effectum entry point, /run autonomous builds, /save restore points, /diagnose post-mortem, and more

PRD Workshop

12 commands for guided specification writing — effect:prd:new, effect:prd:review, effect:prd:handoff, and the full lifecycle

Quality gates

8 automated checks — build, types, lint, tests, security, debug logs, type safety, file size

Stack preset

Pre-configured CLAUDE.md, settings.json, and guardrails tuned for your technology stack

Guardrails

Safety rules that prevent common mistakes — protected files, blocked destructive commands, architecture rules

4 MCP servers

Context7 (docs), Playwright (E2E), Sequential Thinking, Filesystem — pre-configured and ready

Your entry point: /effectum

Always start with /effectum. It shows you the three user journeys and recommends where to begin. When you're lost at any point, type /next — the smart router reads your project state and tells you exactly one action to take.

terminal

# Open your project in Claude Code
cd ~/my-project && claude

# See your options — always start here
/effectum

# Lost? Not sure what to do next?
/next

The 3 user journeys

effectum is built around three journeys. Pick the one that matches where you are.

New Project

Start from scratch

terminal

/effectum → effect:prd:new →
effect:prd:review → effect:prd:handoff →
[target repo] → effect:dev:run

You have an idea. Claude helps you write a spec, review it, then build it autonomously in the target repo.

Existing Codebase

Onboard first

terminal

/effectum → /onboard →
effect:prd:new → effect:prd:handoff → effect:dev:run

You have an existing repo. Run /onboardto analyze it, then write specs against what's already there.

Feature Build

Quick iteration

terminal

effect:prd:new → effect:prd:review → effect:prd:handoff → effect:dev:save → effect:dev:run

You know what you're building. Write the spec, save a restore point, then let Claude build it.

Your first feature

The PRD Workshop is the core of effectum. effect:prd:new → effect:prd:review → effect:prd:handoff gives you a spec that Claude can actually build from.

terminal

# 1. Write a spec (guided mode — Claude asks questions)
effect:prd:new

# 2. Review for completeness before building
effect:prd:review

# 3. Generate the build prompt for your target repo
effect:prd:handoff docs/prds/001-my-feature.md ~/my-project

# 4. In your project — create a restore point, then build
effect:dev:save
effect:dev:run

Use effect:prd:express for a one-shot spec when requirements are already clear. Use effect:prd:new for guided discovery when the idea is still vague.

Autonomous overnight builds

For complex features with a thorough spec, use effect:dev:run . Claude iterates autonomously — writing code, running tests, fixing errors — until every quality gate passes. Always effect:dev:save first as your safety net.

terminal

# Create a restore point before the autonomous run
effect:dev:save

# Start the autonomous build loop
effect:dev:run "Build the auth system per PRD" --max-iterations 30 --completion-promise "All tests pass, build succeeds, 0 lint errors"

# Something went wrong? Run post-mortem diagnosis
/diagnose

# Need to take back control?
/stop

The completion promise is only output when it is 100% true. Claude cannot lie to exit the loop. At 80% of max iterations, it writes a status report of what is done and what remains. For overnight builds, use --max-iterations 50.

Choosing your autonomy level

Configure how much Claude decides independently during npx @aslomon/effectum. Change anytime in .claude/settings.json.

Level	Behavior	Active time	Best for
Conservative	Claude asks at every step	15–30 min active	Teams, learning, sensitive codebases
Standard	Autonomous within guardrails, stops on ambiguity	5–10 min setup	Daily development
Full Autonomy	Runs until done or stuck	2–5 min setup	Overnight builds, well-defined specs

Next steps

Frequently Asked Questions

What is Effectum?

Effectum is an open-source autonomous development framework for Claude Code. It installs 42 workflow commands, 8 automated quality gates, and modular stack presets that give Claude Code a structured spec-driven workflow. You write a specification using the PRD Workshop, then run effect:dev:run to let Claude build autonomously until every quality gate passes.

How does Effectum work with Claude Code?

Effectum works entirely inside Claude Code — no new IDE, no subscription. After running npx @aslomon/effectum, the framework installs slash commands into your project that Claude Code reads as workflow instructions. Type /effectum to start, effect:prd:new to write a spec, and effect:dev:run to build. The framework handles quality enforcement, stuck detection, and context budget monitoring automatically.

Is Effectum free?

Yes. Effectum is MIT-licensed and completely free and open source. No paywalls, no gated features, no enterprise tiers. Install it with npx @aslomon/effectum — no account required. The source code is on GitHub and the package is on npm.

What's the difference between Effectum and GSD, BMAD, or Kiro?

GSD (context-engineering-intro) focuses on writing better context files — it is a lightweight prompt framework without an autonomous build loop or quality gates. BMAD is a comprehensive multi-agent agile framework with many specialized personas but significant setup complexity. Kiro is a spec-driven IDE tool from Amazon that requires its own CLI and ecosystem. Effectum works entirely within Claude Code, installs in 2 minutes, and focuses on the complete development lifecycle: spec → build → verify — with enforced quality gates on every iteration. See the full comparison on the About page.

Can I use Effectum with existing projects?

Yes. Run /onboard after installation — it spawns 6 parallel analysis agents that map your existing codebase (stack, architecture, APIs, database, frontend, tests) and generate a complete CLAUDE.md tailored to your project. From there, the full Effectum framework applies: write specs with effect:prd:new, build with effect:dev:run , verify quality, and iterate.