AIAny
AI Agent2025
Icon for item

AGENTS.md

Defines a predictable repository-level instruction file for coding agents, giving teams one place to document workflow rules instead of each tool inventing its own context format.

Introduction

Coding agents are only as useful as the project context they can reliably find. AGENTS.md makes instructions visible, versioned, and shared in the same way README files made human onboarding predictable.

What Sets It Apart

The format is deliberately small: build commands, testing expectations, architecture notes, and contribution rules can live in a file that many agents discover without custom integration. Its restraint is the point; it is a convention layer, not a policy engine.

Who Should Use It

Great fit if a repository is touched by several AI coding tools or has conventions agents often miss. Look elsewhere for enforceable access control, sandboxing, or task orchestration.

Information

  • Websitegithub.com
  • OrganizationsAgentic AI Foundation
  • Authorsagentsmd (repository owner), romainhuet
  • Published date2025/08/19

Categories

More Items

Hugging Face
AI Model2026

Open-weights LLM fine-tuned for phone-based voice agents that prioritizes low latency and reliable tool/function calling. Based on NVIDIA Nemotron 3 Nano (30B total, 3.5B active), supports very long contexts (262,144 tokens) and recommends temperature=0 with thinking disabled for deployment.

GitHub
AI Agent2026

A curated collection of production-ready Agent Skills that turn tasks—presentation production, image generation, local KB retrieval, article assembly, and web-design—into agent-loadable skill folders. Uses a SKILL.md contract, supports multiple agent runtimes (Claude Code, Cursor, Codex), and offers modular install paths with pinned release zips.

GitHub
AI Agent2026

Provides a ruleset and skills that make AI coding agents prefer the simplest correct implementation: reuse existing code, prefer stdlib/native features, and only write minimal new code. Cuts generated LOC, tokens, cost and time while preserving validation and safety.