production-saas-starter / next_b2b_starter
AGENTS.md532 starsChanged 49 days agoMITView on GitHub
Read shared rules in ../AGENTS.md, ../README.md, this project's README.md and ../docs/ARCHITECTURE.md. This project owns presentation, the HttpOnly session boundary, Better Auth and its private bridge; Go remains the authority for business permissions and tenant data. Use these project-local procedures and roles: - .agents/skills/next-frontend/SKILL.md and .agents/agents/frontend-builder.md for routes, components, API consumers and accessibility. - .agents/skills/auth-integration/SKILL.md and .agents/agents/auth-reviewer.md for Better Auth, sessions, memberships and a read-only trust-boundary review. - .agents/skills/frontend-tools/SKILL.md and .agents/agents/quality-engineer.md for local diagnostics and synthetic browser journeys. Run pnpm verify…
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 31,542 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 repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- go-b2b-starter/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- go-b2b-starter/CLAUDE.mdCLAUDE.md
- next_b2b_starter/CLAUDE.mdCLAUDE.md
- dev-toolsSkill
- orchestrationSkill
- pr-reviewSkill
- service-connectionsSkill
- dev-toolsSkill
- orchestrationSkill
- pr-reviewSkill
- service-connectionsSkill
The file
We split this AGENTS.md into the rules it gives an agent
4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 3
Read shared rules in ../AGENTS.md, ../README.md, this project's README.md and ../docs/ARCHITECTURE.md.
- Distinctive: line 8
Use these project-local procedures and roles:
- Very specific: line 17
Run pnpm verify here for frontend behavior, lint, typecheck and build.
- Very specific: line 23
Run node ../scripts/harness.mjs check for tooling changes.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 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
Next.js project
Read shared rules in ../AGENTS.md, ../README.md, this project's README.md
and ../docs/ARCHITECTURE.md. This project owns presentation, the HttpOnly session
boundary, Better Auth and its private bridge; Go remains the authority for
business permissions and tenant data.
Use these project-local procedures and roles:
.agents/skills/next-frontend/SKILL.mdand.agents/agents/frontend-builder.mdfor routes, components, API consumers and accessibility..agents/skills/auth-integration/SKILL.mdand.agents/agents/auth-reviewer.mdfor Better Auth, sessions, memberships and a read-only trust-boundary review..agents/skills/frontend-tools/SKILL.mdand.agents/agents/quality-engineer.mdfor local diagnostics and synthetic browser journeys.
Run pnpm verify here for frontend behavior, lint, typecheck and build. Generated
business types come from the Go-owned contract; request schema/authorization
changes from the backend owner. For browser checks, use the disposable runner
at ../scripts/test-browser.sh; preserve existing stacks and real accounts.
Local auth checks do not establish external email delivery or live Polar billing.
Run node ../scripts/harness.mjs check for tooling changes. Canonical frontend
and Better Auth guidance lives here. Root only coordinates cross-project work;
generated .claude/ and .codex/ files are adapters, not instruction sources.
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.