For AI-native developers / CLAUDE CODE
A SaaS boilerplate
Claude Code can work inside
CLAUDE.md tells Claude Code the rules. Hooks, ESLint and CI make it keep them. Here is exactly which files useDeploy ships for each, and where the guarantee stops.
How Claude Code loads your rules
Per the official memory docs (https://code.claude.com/docs/en/memory), Claude Code reads CLAUDE.md at the start of every session, from ./CLAUDE.md or ./.claude/CLAUDE.md, and it can also read a repository's AGENTS.md in place of CLAUDE.md. The same page is explicit about the limit: Claude treats CLAUDE.md as context, not enforced configuration, and to block an action regardless of what Claude decides you use a PreToolUse hook. Rules in a file are a request. Enforcement lives in hooks, lint and CI.
What useDeploy ships today, file by file
| File in the repo | What it does | Who enforces it |
|---|---|---|
| CLAUDE.md | Long-form operating manual: DDD layering, contracts, API regeneration, docs rules, design system. | Context only. Claude Code reads it at session start. |
| AGENTS.md | Short architecture rules: layers, contracts, "done means green". Any agent that reads AGENTS.md gets them. | Context the agent reads. The rules it states are backed by the ESLint layer rules. |
| .claude/settings.json | Registers the two Claude Code hooks (PostToolUse and Stop). | Claude Code only. |
| .claude/hooks/lint-edited-file.mjs | PostToolUse hook: lints each file the agent just edited and sends the ESLint report back in the same turn. | Claude Code only. It reports after the edit; it does not block it. |
| .claude/hooks/verify-before-stop.mjs | Stop hook: when the agent tries to finish and bun run guardrails fails, it sends the agent back once with the failure. | Claude Code only. One forced retry, not a guarantee. |
| packages/eslint-config/ddd.js | ESLint layer rules: domain and application cannot import express, Prisma or BetterAuth; contexts talk through types. | Any tool, any editor. This is the part the agent cannot talk its way past. |
| .github/workflows/ci.yml | Lint and typecheck jobs run on every pull request (the test job too). | Any tool. This is the shared gate. |
What useDeploy does not ship for Claude Code
No PreToolUse hook: nothing stops an edit before it happens. The lint hook reports right after the edit and the Stop hook forces a single retry, so a failure the agent cannot fix gets through to CI, which is the real gate. We do not ship a project-level skills library for the SaaS itself either (the .claude folder holds the hooks, a code-smell subagent and a few WhatsApp integration skills). If you want a PreToolUse block, the kit is the place to extend.
Honest comparison: others ship agent files too
useDeploy is our product, so weigh this accordingly. MakerKit, supastarter, Nextbase, ShipAny and Indie Kit also ship an AGENTS.md, rules files or agent skills for AI tools, and AnotherWrapper sells a blocking-hook harness ("Hooks, not instructions"). What useDeploy adds on top of AGENTS.md is the combination of ESLint layer rules, Claude Code hooks and a CI gate in the same repo. It is not the only kit with agent files, and a rules file alone, ours or anyone's, is only a request.
The open-source kit and the guides
Take the guardrails without the boilerplate
The hooks and settings are published as an MIT kit: https://github.com/KonixDev/claude-code-guardrails. Drop it into any repo with an ESLint config and a guardrails script.
Write the files yourself
Guides: /blog/claude-md-file-example-saas (CLAUDE.md), /blog/claude-code-hooks-enforce-architecture (hooks), /blog/cursor-rules-nextjs-typescript (Cursor rules), /blog/claude-code-skills-subagents-architecture-review (skills and subagents).
Compare the kits
Roundup by use case, with the cases where another kit fits better.
Other AI tools
Cursor
How Cursor loads its rules, and what useDeploy covers for it.
OpenAI Codex
How OpenAI Codex loads its rules, and what useDeploy covers for it.
Windsurf
How Windsurf loads its rules, and what useDeploy covers for it.
GitHub Copilot
How GitHub Copilot loads its rules, and what useDeploy covers for it.
AGENTS.md
How AGENTS.md loads its rules, and what useDeploy covers for it.
AI coding agents: the overview
The overview of the guardrails every AI tool shares: layer rules, typed contracts and the CI gate.
FAQ
Does Claude Code need CLAUDE.md or can it use AGENTS.md?+
Do the hooks guarantee the agent cannot break the architecture?+
How much does useDeploy cost?+
| Price | Founder $99 or Lifetime $199, one-time payment (no subscription) |
|---|---|
| License | Full source, commercial use, unlimited projects. Founder is a frozen snapshot; Lifetime includes every future release. |
| Stack | Next.js frontend, Express API, Bun runtime, Prisma, BetterAuth |
| Auth | BetterAuth: sessions, 2FA, magic links, password reset |
| Multi-tenancy and RBAC | Organizations with members, invitations, roles and permissions |
| Payments | Polar: full billing (checkout, customer portal, webhooks, plan sync). MercadoPago: Checkout Pro one-time payments with signed webhooks; subscriptions are not supported yet. Stripe: adapter scaffold, not charging yet. |
| Guardrails for AI agents | ESLint-enforced architecture layers, Claude Code hooks and an AGENTS.md |
| Refund | 14 days |
| Try it: free account | Sign up free and explore the dashboard: organizations, roles, billing, audit log. You buy the license from inside. https://usedeploy.dev/register |
| Docs | Documentation in English, with Spanish and Portuguese translations of the main guides |
Rules the agent reads, walls it cannot cross.
Start from a base where the architecture is enforced by lint and CI, and the agent files are already written.