All Formats
StarPillar Specification & Hub Directory

AGENTS.md Multi-Agent System Protocol Directory

Unified steering specifications for autonomous AI coding agents. Establish agent boundaries, verification gates, and delegation contracts.

Open Blank Studio Editor
Target: ./ (Repository Root)AGENTS.md
01 / SPECIFICATION & RUNTIME BEHAVIOR

How AGENTS.md Multi-Agent Rules Operates in Production

AGENTS.md is an emerging universal open standard for steering autonomous coding agents across different AI tooling ecosystems. Placed at repository root, AGENTS.md instructs autonomous agents on environment setup, allowed operations, branching strategies, automated testing gates, and documentation integrity rules.

Agent Verification GatesSpec Syntax

Non-negotiable verification steps the agent must execute before declaring a task complete.

## Verification Requirements
Every agent task must be verified with:
1. `npm run build` (must exit 0)
2. `npm test` (all tests green)
3. No newly introduced TypeScript errors
02 / REPOSITORY PLACEMENT
./AGENTS.mdRepository Root

Universal specification read by multi-agent frameworks, IDE coding assistants, and CI agents.

03 / PRESET SPOKE MATRIX

Available Tech Stack Presets (18)

Click any tech stack below to open the client-side editor preloaded with this verified configuration.

FrontendLaunch

Next.js 15 Autonomous Agents

Generate a Next.js 15 AGENTS.md specification file for autonomous AI coding agents.

Enforced Invariant:

"Require build verification (`npm run build`) before submitting code."

FrontendLaunch

React 19 & Vite

Generate an AGENTS.md multi-agent specification for React 19 & Vite.

Enforced Invariant:

"Use React 19 action hooks (useActionState, useOptimistic, useFormStatus) for async mutations."

BackendLaunch

Python FastAPI Autonomous Agents

Generate a Python FastAPI AGENTS.md specification file for autonomous AI coding agents.

Enforced Invariant:

"Require `pytest` to pass with zero failures before task completion."

Fullstack & DBLaunch

Supabase & PostgreSQL

Generate an AGENTS.md multi-agent specification for Supabase & PostgreSQL.

Enforced Invariant:

"Always include `ENABLE ROW LEVEL SECURITY;` on every created table."

Fullstack & DBLaunch

Prisma ORM

Generate an AGENTS.md multi-agent specification for Prisma ORM.

Enforced Invariant:

"Always use `select` to specify required fields; avoid raw `findMany()` fetching unused relations."

Fullstack & DBLaunch

Drizzle ORM

Generate an AGENTS.md multi-agent specification for Drizzle ORM.

Enforced Invariant:

"Define schemas using pgTable/sqliteTable with explicit foreign keys and constraints."

BackendLaunch

Go (Golang) & Fiber

Generate an AGENTS.md multi-agent specification for Go (Golang) & Fiber.

Enforced Invariant:

"Check every `if err != nil` explicitly; never swallow errors or ignore returned values."

BackendLaunch

Rust & Axum

Generate an AGENTS.md multi-agent specification for Rust & Axum.

Enforced Invariant:

"Never call `.unwrap()` or `.expect()` in production route handlers; propagate errors via `Result<T, AppError>`."

FrontendLaunch

Tailwind CSS v4

Generate an AGENTS.md multi-agent specification for Tailwind CSS v4.

Enforced Invariant:

"Configure themes directly in globals.css using `@theme` and `@import 'tailwindcss';`."

FrontendLaunch

Vue 3 & Nuxt 3

Generate an AGENTS.md multi-agent specification for Vue 3 & Nuxt 3.

Enforced Invariant:

"Always use `<script setup lang='ts'>` and the Composition API; ban legacy Options API."

FrontendLaunch

SvelteKit 5 & Svelte 5

Generate an AGENTS.md multi-agent specification for SvelteKit 5 & Svelte 5.

Enforced Invariant:

"Use Svelte 5 runes: `$state()`, `$derived()`, and `$props()`."

Specialist PersonaLaunch

Universal Cursor Pro

Generate an AGENTS.md multi-agent specification for Universal Cursor Pro.

Enforced Invariant:

"Deliver surgical, targeted diffs; never replace entire files unnecessarily."

Specialist PersonaLaunch

Pragmatic Rapid Prototyping

Generate an AGENTS.md multi-agent specification for Pragmatic Rapid Prototyping.

Enforced Invariant:

"Prioritize working software over complex design patterns or deep inheritance hierarchies."

Specialist PersonaLaunch

Zero-Trust Security

Generate an AGENTS.md multi-agent specification for Zero-Trust Security.

Enforced Invariant:

"Flag and prevent any dynamic SQL query string interpolation."

DevOps & ToolingLaunch

Docker & CI/CD

Generate an AGENTS.md multi-agent specification for Docker & CI/CD.

Enforced Invariant:

"Always use multi-stage Docker builds to separate builder tools from the lean production image."

Specialist PersonaLaunch

Vitest & Playwright TDD

Generate an AGENTS.md multi-agent specification for Vitest & Playwright TDD.

Enforced Invariant:

"Write unit tests covering happy paths and at least two edge/error cases for every new function."

Specialist PersonaLaunch

Automated Code Reviewer

Generate an AGENTS.md multi-agent specification for Automated Code Reviewer.

Enforced Invariant:

"Scan repository manifests to map stack idioms before evaluating logic."

Specialist PersonaLaunch

Multi-Agent System Orchestration

Create a universal multi-agent team AGENTS.md coordinating frontend, backend, and security subagents.

Enforced Invariant:

"Define subagent roles: Lead Architect, Frontend Engineer, Backend Specialist, Security Reviewer."

04 / BEST PRACTICES
Define clean permission boundaries (e.g. 'Read-only access to .env files; never write credentials').
Specify required git branching rules (e.g. 'Create feature branches with prefix feat/').
Enforce documentation integrity: do not delete existing comments or docstrings.
Other Format DirectoriesHub Network
05 / FREQUENTLY ASKED QUESTIONS

What is AGENTS.md used for?

AGENTS.md provides standardized instructions for autonomous AI agents that operate in codebases without human intervention at every step. It defines constraints, testing requirements, and architecture rules.