code-addiction

skill
Security Audit
Warn
Health Warn
  • License Ò€” License: MIT
  • Description Ò€” Repository has a description
  • Active repo Ò€” Last push 0 days ago
  • Low visibility Ò€” Only 5 GitHub stars
Code Pass
  • Code scan Ò€” Scanned 12 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions Ò€” No dangerous permissions requested
Purpose
This tool is a spec-driven development framework that standardizes AI coding workflows. It provides a CLI to scaffold guided development trailsβ€”moving from brainstorming through planning, coding, and reviewβ€”integrating with AI assistants like Claude and Codex.

Security Assessment
The rule-based scan checked 12 JavaScript files and found no dangerous patterns, hardcoded secrets, or requests for dangerous permissions. The CLI does execute local shell commands (`npx codeadd`) to manage files (install, update, repair, uninstall) and run validations via SHA-256 hashes. It also makes standard network requests to fetch package updates and download templates. It does not appear to access sensitive personal data. Overall risk: Low.

Quality Assessment
The project is actively maintained (last push was today) and properly licensed under the permissive MIT license. It features a comprehensive README and uses continuous integration (CI) for automated testing. However, community trust and visibility are currently very low. With only 5 GitHub stars, the tool is in its early stages, meaning potential bugs or edge cases might not yet be fully vetted by a wider user base.

Verdict
Safe to use, though developers should anticipate early-stage software limitations due to low community visibility.
SUMMARY

πŸ“‹ The Spec-Driven Development framework. Define the what, AI handles the how.

README.md

Code Addiction (ADD)

CI
npm version
License: MIT

AI-powered development workflows that make you addicted to shipping code. Production-ready commands, scripts, and skills for AI coding assistants, with a single CLI installer.

Official Framework Site: code.brabos.ai β€” your complete development workflow guide and documentation.

Why this project exists

Most AI coding setups are fragmented across custom prompts, scripts, and editor-specific conventions.

Code Addiction standardizes this with:

  • A shared core in .codeadd/ (commands, scripts, skills, templates)
  • Provider-specific integrations (Claude, Codex, Antigravity, KiloCode, OpenCode)
  • A versioned installer (codeadd) with install, update, uninstall, doctor, and validate

Quickstart

# install latest release
npx codeadd install

# install a specific version (e.g., v0.2.20)
npx codeadd install --version v0.2.20

# check environment health
npx codeadd doctor

# validate file integrity via SHA-256 hashes
npx codeadd validate

# repair missing or corrupted files
npx codeadd validate --repair

# update to latest release
npx codeadd update

# update to a specific version
npx codeadd update --version v0.2.14

# remove Code Addiction files from your project
npx codeadd uninstall

# list optional features
npx codeadd features list

# show installation configuration
npx codeadd config show

How it works

Code Addiction turns complex development into a guided, repeatable flow. Instead of figuring out how to build, you just follow the next command. The AI does the heavy lifting β€” you stay in control.

The Development Trail

Every feature follows a clear path from idea to delivery. Pick the trail that fits your task:

Step        Command             What happens                        Output
───────────────────────────────────────────────────────────────────────────────
0. Explore  /add.brainstorm     Brainstorm ideas (read-only)        Initial concept
1. Discover /add.new            AI-guided feature discovery          about.md
2. Design   /add.design         UX spec, mobile-first               UI/UX specification
3. Plan     /add.plan           Technical planning + checklist       plan.md
4. Code     /add.build          Subagent-driven implementation       Working code
5. Review   /add.review          Automated code review + validation   Quality gate
6. Done     /add.done           Changelog, docs, finalization        Ready to merge

Choose your flow

Pick the shortest path that fits. Less ceremony, same quality.

COMPLETE  (complex features with UI)
  brainstorm --> feature --> design --> plan --> dev --> review --> done

STANDARD  (features without complex UI)
  feature --> plan --> dev --> done

LEAN      (small changes, quick tasks)
  feature --> dev --> done

AUTONOMOUS  (full AI implementation, no interaction)
  feature --> autopilot --> done

EXPLORATION  (don't know where to start?)
  brainstorm --> feature --> ...pick your flow above

EMERGENCY  (critical bug in production)
  hotfix --> done

That's it. No config files to tweak, no boilerplate to write, no decision fatigue.
Type the command, follow the AI, ship the feature. Repeat.

Why teams get addicted

  • Zero ramp-up β€” new devs ship on day one by following the flow
  • 10x fewer decisions β€” the framework already made the boring ones for you
  • Consistent output β€” every feature gets discovery, planning, review, and docs automatically
  • Works with your stack β€” NestJS, React, any database, any provider

What gets installed

  • Core: .codeadd/
  • Optional providers:
    • Claude Code -> .claude/
    • Codex (OpenAI) -> .agents/
    • Google Antigravity -> .agent/
    • KiloCode -> .kilocode/
    • OpenCode -> .opencode/

Repository structure

  • cli/: installer CLI published as codeadd
  • framwork/: framework payload copied into target projects by the installer

Compatibility

  • Node.js 18+
  • GitHub-hosted releases for distribution
  • Works on Windows, macOS, Linux (via Node runtime)

Contributing

Contributions are welcome. Start here:

Roadmap

  • Better zero-config onboarding by project type
  • More provider adapters
  • Stronger validation and automated repair flows

Official Pages

Support

Reviews (0)

No results found