Stop buying dead boilerplate. ClaudeThings drops 89 specialized agents, 103 pre-built skills, and 181 slash commands into any project, a living team that plans, builds, tests, ships, and markets alongside you.
You've bought the $300 templates and the "ship-fast" kits. Every time, you hit the same wall:
Good luck migrating when Next.js 16 breaks everything. Their architecture, their rules.
Now you're maintaining THEIR code. CVEs pile up. Security becomes your problem.
Spend days ripping out features you don't need and fighting opinions you didn't ask for.
"Download and good luck" isn't a business model. You're on your own.
ClaudeThings agents read a CLAUDE.md
you fill in once, then adapt to your stack and conventions and get smarter every time Claude does.
Next.js → Django → Rails → Go → Rust. No forced framework. Agents learn your patterns via context engineering, not template conventions.
Traditional kits are frozen at purchase. When Anthropic ships a smarter Claude, your team levels up automatically. No upgrade fees.
Two kits in one. An engineering team that ships features, and a marketing team that ships the launch. Most kits only do one.
backend-architect
, react-specialist
, typescript-pro
, python-pro
, golang-pro
, rust-pro
.postgres-pro
, kubernetes-specialist
, terraform-specialist
, sre-engineer
.code-reviewer
, test-automator
, debugger
, security-auditor
./api-scaffold
, /test-coverage
, /deploy-checklist
.seo-specialist
, content-marketer
, competitive-analyst
, market-researcher
./campaign-brief
, /blog-post
, /email-sequence
, /landing-page
, /launch-plan
.Run the npx github:claudethings/…
one-liner from your private repo's README. Pick engineer, marketing, or both. No global install.
Fill in the generated CLAUDE.md
once — stack, conventions, brand voice. Every agent reads it first.
Open Claude Code: "use tech-lead to build auth"
or /blog-post our launch
. That's it.
Want just the debugger? claudethings add agent debugger
. No all-or-nothing.
Never overwrites your files. Your CLAUDE.md
and custom configs are always protected.
Run claudethings update
for the latest agents. Buy once, use forever. Agents learn YOUR codebase via CLAUDE.md — output matches your style, not a template's.
Sequential chains, parallel fan-out, or smart delegation — orchestrators pick the right one.
Curated from MIT/Apache projects with full attribution & license files. Built to be sold cleanly.
| Feature | Boilerplate | Other AI kits | ClaudeThings |
|---|---|---|---|
| What you get | Dead code | Agents + skills | 89 agents · 103 skills · 181 commands |
| Engineering and marketing | ✕ | Sold separately | ✓ both kits, one repo |
| Installer | Copy/paste | bun-only CLI | ✓ npx · no install · Node 18+ |
| Cherry-pick one component | ✕ | ✕ | ✓ add agent/skill/command |
| Tech stack | Locked | Any | ✓ any — adapts via CLAUDE.md |
| Updates over time | Never | Sometimes | ✓ lifetime, included |
| Open-source attribution | — | — | ✓ full CREDITS + licenses |
Lifetime access & all future updates. Private repo delivery. Instant access after checkout.
This is the launch price, prices will increase soon.
.claude/
directory of agents, skills, and slash commands, CLAUDE.md templates, the claudethings
installer CLI, and full docs. You drop it into any project with a one-line npx github:claudethings/…
command that pulls straight from your private repo — the exact command is in your repo's README.claudethings update
(or git pull
) to refresh. Your custom files and CLAUDE.md are never touched.Code and growth, from one toolkit. One command away.