Build your repo
Start from
Or pick below. Every section starts at None.
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
41 items come with every repo. Add a battery and watch it grow.
Guard hooks
3 run before a tool call. 3 run after.
2 more hooks run in team mode.
- hooks.json
- AGENTS.md
- proxy.ts
- .env.example
- .gitignore
- AGENTS.md
- DESIGN.md
- README.md
- SETUP.md
- agentic.config.json
- biome.jsonc
- components.json
- next.config.ts
- opencode.json
- package.json
- playwright.config.ts
- postcss.config.mjs
- 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 7 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:** none- **Design:** Blueprint (`blueprint`). 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, `$setup` in Codex.It reads [SETUP.md](SETUP.md), which lists every environment variable, where to getit, and the order to set the services up. ```shbun installbun run setup:env -- --check # what .env.local still needsbun run verifybun run dev``` ## How this repo is set up for agents This file is the instruction file every agent reads. It holds the rules for the whole repo. - A folder with its own `AGENTS.md` adds the rules for the files under it. Before you edit a file, read every `AGENTS.md` from the repo root down to its folder. Most agents load them for you.- `.agents/rules/`: all 8 rules in full, one file each.- `.agents/skills/`: 9 skills, listed below.- `.agents/agents/`: 5 subagents, listed below. Agents with their own folder get a copy: `.claude/agents/`, `.codex/agents/`, `.cursor/agents/`, `.github/agents/`, `.gemini/agents/`, `.opencode/agents/`.- `.agents/hooks/`: 6 guard hooks. They block destructive commands and keep secrets out of the chat. Wired for Claude Code, Codex, Cursor, GitHub Copilot, Antigravity, Gemini CLI and Windsurf. `bun run verify:hooks` proves they still block.- `docs/solutions/`: 13 solved problems. Read the relevant one before you re-solve anything.- `docs/plans/`: one plan per unit of work.- The `system-manager` subagent owns this agent setup: `AGENTS.md`, `.agents/` and each agent's own folder. ## Workflow The Compound Engineering plugin adds the loop: `/ce-brainstorm`, `/ce-plan`, `/ce-work`, `/ce-code-review`, `/ce-compound`.In Codex they start with `$`. [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. ## Scoped rules - `src/AGENTS.md` (2 rules)- `src/app/AGENTS.md` (3 rules)- `src/components/AGENTS.md` (2 rules)- `src/components/marketing/AGENTS.md` (1 rule)- `src/components/site/AGENTS.md` (1 rule)- `src/lib/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`) ## Skills Run one by name (`/name` in most agents, `$name` in Codex), or let the agent pick onefrom its description:`deploy-to-vercel`, `help`, `landing-copy`, `new-component`, `qa-feature`, `security-audit`, `setup`, `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`:`designer`, `documentarian`, `pr-reviewer`, `security-auditor`, `system-manager`
Blueprint. Black drafting table, dashed frames, mono labels and one periwinkle pen. Every section reads like a drawing.
Your agents read this design’s DESIGN.md before they touch a colour.
