Back to browse
GitHub Repository

AI coding tool boilerplate marketplace

2 starsTypeScript

Updose – A boilerplate for AI coding tool configs

by beomjunkdev·Mar 2, 2026·1 point·1 comment

AI Analysis

Mid

Copy-paste config manager for AI coding tools, but adoption depends entirely on community.

Strengths
  • Solves real friction point—repetitive boilerplate across Claude/Gemini/Codex projects
  • Multi-tool support (Claude, Gemini, Codex) rather than single-vendor lock-in is forward-thinking
  • Monorepo support and dry-run mode show practical UX consideration
Weaknesses
  • Zero community—0 stars, 0 forks on GitHub; marketplace viability entirely unproven
  • Boilerplate sharing already solved by GitHub templates, dotfiles, and vendor-native extensions
Target Audience

AI coding tool users (Claude Code, Gemini, Codex), developers tired of manual config management

Similar To

GitHub Templates · dotfiles repos · VS Code extension marketplace

Post Description

I got tired of copy-pasting the same CLAUDE.md, rules, and skills across projects. So I built updose — a boilerplate manager for AI coding tool configurations.

It works with Claude Code, Codex, and Gemini CLI.

What it does: - Search and install community-shared boilerplates (rules, skills, agents, commands) with one command

npx updose search <query> npx updose add <owner/repo>

- Publish your own setup so others can use it

npx updose init npx updose publish

Built with TypeScript. Open source (MIT). Feedback welcome.

Similar Projects

SaaS●●Solid

MarketplaceKit – Ship a rental marketplace in days instead of months

Rental marketplace boilerplate with clean flag-driven architecture, but Supabase+Stripe templates exist.

Solve My ProblemNiche GemShip It
markoristicc
103mo ago
AI/ML●●Solid

Forage – MCP server that lets AI agents find and install their own MCPs

Forage proxies MCP capability discovery so an agent can search registries, install a package as a child process, emit list_changed so the agent picks the tool up immediately, and even write usage notes to CLAUDE.md for future sessions. That operational pattern — dynamic install + instant availability + persisted learnings — is a clever, pragmatic fix for brittle agent setups, though the project is clearly early and raises real security/trust questions around auto-installing third-party MCPs (user approval is noted but sandboxing/attestation will matter).

Big BrainShip It
DoomedWheel1027
113mo ago