vibe-starter
AGENTS.md1 starsChanged 5 months agoMITView on GitHub
This file is for Codex, Cursor, and any other coding agent working in this repo. Claude Code reads the same rules from CLAUDE.md. Follow these exactly — they keep generated code secure and production-ready. A secure, legally-complete Next.js starter. A secure base (app/, lib/, components/, content/) is always present, and registry/ holds optional feature modules copied into the app on demand with the vibe CLI. Prefer composing an existing module over hand-writing a feature: The installer regenerates env validation, CSP…
- Installs packages
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 33,315 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository5 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- vibe-buildSkill
- vibe-legalSkill
- vibe-securitySkill
- vibe-starterSkill
The file
We split this AGENTS.md into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Distinctive: line 15
Prefer composing an existing module over hand-writing a feature:
- Distinctive: line 33
No code comments: Use self-documenting names and small functions.
- Very specific: line 40
Run pnpm run check (typecheck + lint + format) before committing.
≈ “Common” is an estimate: at least 1 in 5 of the 42,283 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Agent guide
This file is for Codex, Cursor, and any other coding agent working in this repo. Claude Code reads
the same rules from CLAUDE.md. Follow these exactly — they keep generated code secure and
production-ready.
What this repo is
A secure, legally-complete Next.js starter. A secure base (app/, lib/, components/,
content/) is always present, and registry/ holds optional feature modules copied into the app
on demand with the vibe CLI.
How to add capabilities
Prefer composing an existing module over hand-writing a feature:
pnpm vibe list # see the 24 available modules
pnpm vibe search <term> # find modules by name or description
pnpm vibe info <module> # inspect a module manifest
pnpm vibe add <module> [<module>...] # copy it in and rewire deps, env, schema, CSP, legal
pnpm install
pnpm vibe doctor # audit the installed set for conflicts and drift
pnpm vibe update <module> # pull registry fixes into an installed module
pnpm vibe remove <module> # remove it and restore backed-up base filesThe installer regenerates env validation, CSP sources, the Drizzle schema barrel, and the legal
pages from whatever is installed — never edit the *.generated.ts files by hand.
Conventions (do not break)
- No code comments. Use self-documenting names and small functions.
- TypeScript strict, no
any. Validate every input with Zod at the trust boundary. - Mutations go through server actions or POST route handlers, never unguarded.
- No secrets in client code. Declare env vars and read them through
@/lib/env. - Extend the CSP through a module's
cspfield, never by weakeninglib/security/csp.ts. - Commit messages: one short imperative sentence. No AI attribution, no
Co-Authored-By, no conventional-commit prefixes. - Run
pnpm run check(typecheck + lint + format) before committing.
Stack
Next.js 16 App Router · React 19 · Tailwind v4 + shadcn/ui · Better Auth · Drizzle + Neon Postgres · Zod. Vercel-first.
See docs/ for the architecture, security model, and module-authoring guide.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

