Build your repo
Database
ORM
Vercel AI SDK with a streaming chat route, structured output and tool calling.
Users, bans, impersonation and an audit log at /admin. Needs sign in.
Analytics
Error tracking
Support chat
Mode
The plan loop without the gate. Best when you work alone.
AI tools
Every repo ships AGENTS.md and .agents/, so any agent that reads AGENTS.md works. A tick adds that tool's own config.
What your agent gets
152 items. 101 written for your 9 batteries.
Guard hooks
4 run before a tool call. 3 run after.
2 more hooks run in team mode.
- hooks.json
- mcp_config.json
- AGENTS.md
- instrumentation-client.ts
- instrumentation.ts
- mdx-components.tsx
- proxy.ts
- .env.example
- .gitignore
- .mcp.json
- AGENTS.md
- DESIGN.md
- README.md
- SETUP.md
- agentic.config.json
- biome.jsonc
- components.json
- drizzle.config.ts
- next.config.ts
- opencode.json
- package.json
- playwright.config.ts
- postcss.config.mjs
- sentry.edge.config.ts
- sentry.server.config.ts
- tsconfig.json
- vitest.config.ts
AGENTS.md
Structure preview. Where a line gives a rule's length, the real file has the rule in full. Plus 32 AGENTS.md files in rule folders.
# my-app Generated by [Agentic Boilerplate](https://github.com/agentic-studio/agentic-boilerplate) from [Agentic Studio](https://theagentic.studio). Same `agentic.config.json`, same repo: regenerate and diff any time. - **Stack:** Next.js on Vercel (`nextjs-vercel`)- **Services:** Drizzle ORM (`drizzle`), Neon (`neon`), Better Auth (`better-auth`), Stripe (`stripe`), Resend (`resend`), Sentry (`sentry`), PostHog (`posthog`), Admin panel (`admin-panel`), MDX blog (`blog-mdx`)- **Design:** Default (`default`). Every UI change follows [DESIGN.md](DESIGN.md).- **Package manager:** bun- **Mode:** solo ## Start here On a fresh clone, run the `setup` skill: `/setup` in most agents, `$setup` in Codex.It reads [SETUP.md](SETUP.md), which lists every environment variable, where to getit, and the order to set the services up. ```shbun installbun run setup:env -- --check # what .env.local still needsbun run verifybun run dev``` ## How this repo is set up for agents This file is the instruction file every agent reads. It holds the rules for the whole repo. - A folder with its own `AGENTS.md` adds the rules for the files under it. Before you edit a file, read every `AGENTS.md` from the repo root down to its folder. Most agents load them for you.- `.agents/rules/`: all 30 rules in full, one file each.- `.agents/skills/`: 29 skills, listed below.- `.agents/agents/`: 7 subagents, listed below. Agents with their own folder get a copy: `.claude/agents/`, `.codex/agents/`, `.cursor/agents/`, `.github/agents/`, `.gemini/agents/`, `.opencode/agents/`.- `.agents/hooks/`: 7 guard hooks. They block destructive commands and keep secrets out of the chat. Wired for Claude Code, Codex, Cursor, GitHub Copilot, Antigravity, Gemini CLI and Windsurf. `bun run verify:hooks` proves they still block.- MCP servers: `better-auth`, `neon`, `posthog`, `sentry`, `stripe`. [SETUP.md](SETUP.md) says how to connect them in each agent.- `docs/solutions/`: 74 solved problems. Read the relevant one before you re-solve anything.- `docs/plans/`: one plan per unit of work.- The `system-manager` subagent owns this agent setup: `AGENTS.md`, `.agents/` and each agent's own folder. ## Workflow The Compound Engineering plugin adds the loop: `/ce-brainstorm`, `/ce-plan`, `/ce-work`, `/ce-code-review`, `/ce-compound`.In Codex they start with `$`. [SETUP.md](SETUP.md) has the install line for each agent. ## Repo-wide rules ### Code style and file conventions Source: `nextjs-vercel` 84 lines of rule text here, the same as .agents/rules/code-style.md. ### Git and change hygiene Source: `nextjs-vercel` 53 lines of rule text here, the same as .agents/rules/git.md. ### Security rules Source: `nextjs-vercel` 81 lines of rule text here, the same as .agents/rules/security.md. ### More rules Too long to copy here. Read each one before you edit a file it applies to. - `.agents/rules/sentry-no-pii.md`: No personal data in breadcrumbs, tags or extra (`**`) ## Scoped rules - `content/AGENTS.md` (1 rule)- `drizzle/AGENTS.md` (1 rule)- `scripts/admin/AGENTS.md` (1 rule)- `scripts/billing/AGENTS.md` (2 rules)- `src/AGENTS.md` (4 rules)- `src/app/AGENTS.md` (8 rules)- `src/app/(admin)/AGENTS.md` (1 rule)- `src/app/(app)/AGENTS.md` (1 rule)- `src/app/(app)/billing/AGENTS.md` (1 rule)- `src/app/(better-auth)/AGENTS.md` (1 rule)- `src/app/api/AGENTS.md` (1 rule)- `src/app/api/admin/AGENTS.md` (1 rule)- `src/app/api/auth/AGENTS.md` (1 rule)- `src/app/api/webhooks/resend/AGENTS.md` (1 rule)- `src/app/api/webhooks/stripe/AGENTS.md` (1 rule)- `src/app/pricing/AGENTS.md` (1 rule)- `src/components/AGENTS.md` (6 rules)- `src/components/admin/AGENTS.md` (2 rules)- `src/components/app/AGENTS.md` (1 rule)- `src/components/auth/AGENTS.md` (1 rule)- `src/components/billing/AGENTS.md` (1 rule)- `src/components/marketing/AGENTS.md` (1 rule)- `src/components/site/AGENTS.md` (1 rule)- `src/components/ui/AGENTS.md` (1 rule)- `src/db/AGENTS.md` (4 rules)- `src/lib/AGENTS.md` (4 rules)- `src/lib/admin/AGENTS.md` (2 rules)- `src/lib/analytics/AGENTS.md` (3 rules)- `src/lib/auth/AGENTS.md` (3 rules)- `src/lib/billing/AGENTS.md` (4 rules)- `src/lib/email/AGENTS.md` (1 rule)- `tests/AGENTS.md` (1 rule) These also cover files at the repo root. Read one before you edit a file it names: - `.agents/rules/deployment.md`: Deployment rules (`next.config.ts`, `vercel.json`, `package.json`, `src/proxy.ts`, `src/app/**/route.ts`, `.env.example`)- `.agents/rules/drizzle-migrations.md`: Every schema change ships with its generated migration (`src/db/**`, `drizzle/**`, `drizzle.config.ts`)- `.agents/rules/sentry-capture.md`: Every captured exception carries a stable fingerprint hint (`src/**`, `sentry.server.config.ts`, `sentry.edge.config.ts`) ## Skills Run one by name (`/name` in most agents, `$name` in Codex), or let the agent pick onefrom its description:`add-admin-action`, `add-admin-page`, `add-app-page`, `add-email-template`, `add-event`, `add-mdx-component`, `add-oauth-provider`, `add-plan`, `add-table`, `ask-product`, `db-branch`, `deploy-to-vercel`, `edit-pricing`, `help`, `landing-copy`, `migrate`, `migrate-on-neon`, `new-component`, `new-post`, `preview-and-test-email`, `protect-route`, `qa-feature`, `scrub-pii`, `security-audit`, `setup`, `test-webhook`, `triage-errors`, `verify`, `write-spec` ## Subagents Hand a task to one by name. What each one is for, and its prompt, is in`.agents/agents/<name>.md`:`db-inspector`, `designer`, `documentarian`, `pr-reviewer`, `product-analyst`, `security-auditor`, `system-manager`
Default. shadcn done carefully. Neutral greys, near-black actions, one blue for links, Geist throughout.
Your agents read this design’s DESIGN.md before they touch a colour.
