惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

博客园 - 司徒正美
The GitHub Blog
The GitHub Blog
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
Apple Machine Learning Research
Apple Machine Learning Research
L
LangChain Blog
GbyAI
GbyAI
博客园_首页
V
Visual Studio Blog
Martin Fowler
Martin Fowler
WordPress大学
WordPress大学
H
Hackread – Cybersecurity News, Data Breaches, AI and More
博客园 - 叶小钗
腾讯CDC
博客园 - Franky
IT之家
IT之家
Google DeepMind News
Google DeepMind News
Microsoft Azure Blog
Microsoft Azure Blog
D
Docker
大猫的无限游戏
大猫的无限游戏
Recent Announcements
Recent Announcements
小众软件
小众软件
博客园 - 三生石上(FineUI控件)
B
Blog
酷 壳 – CoolShell
酷 壳 – CoolShell

DEV Community

Authentication Security Deep Dive: From Brute Force to Salted Hashing (With Java Examples) Why AI Systems Don’t Fail — They Drift Spilling beans for how i learn for exam😁"Reinforcement Learning Cheat Sheet" I Replaced Chrome with Safari for AI Browser Automation. Here's What Broke (and What Finally Worked) How Python Borrows Other People's Work The $40 Architecture: Processing 1 Billion API Requests with 99.99% Uptime Vibe Coding: A Workflow Guide (From Zero to SaaS) Most webhook security guides protect the wrong side. The scary part is delivery. Headless CMS for TanStack Start: Build a Blog with Cosmic EU Age Verification App "Hacked in 2 Minutes" — What Actually Happened Comfy Cloud’s delete function does not actually remove files Running AI Models on GPU Cloud Servers: A Beginner Guide Event-driven media intelligence with AWS Step Functions and Bedrock I scored 500 AI prompts across 8 quality dimensions — here's what broke How to Call Google Gemini API from Next.js (Free Tier, No Backend Needed) The Portal Protocol: Reclaiming Human Connection in the Age of AI How to Fix Your Team's Scattered Knowledge Problem With a Self-Hosted Forum Intro to tc Cloud Functors: A Graph-First Mental Model for the Modern Cloud Designing Multi-Tenant Backends With Both Ownership and Team Access I Built a Neumorphic CSS Library with 77+ Components — Here's What I Learned PostgreSQL Performance Optimization: Why Connection Pooling Is Critical at Scale Cómo construí un SaaS multi-rubro para gestionar expensas en Argentina con FastAPI + Vue 3 🚀 I Built an Ethical Hacking Scanner Tool – Open Source Project I Replaced /usage and /context in Claude Code With a Single Statusline A Pythonic Way to Handle Emails (IMAP/SMTP) with Auto-Discovery and AI-Ready Design I Collected 8.9 Million Polymarket Price Points — Here's What I Found About How Markets Really Move EcoTrack AI — Carbon Footprint Tracker & Dashboard Everyone's Using AI. No One Agrees How. 5 self-hosted ebook managers worth trying in 2026 Building Your First AI Agent with LangChain: From Chatbot to Autonomous Assistant
DESIGN.md, CLAUDE.md, AGENTS.md: The Agent-Context File F...
PromptMaster · 2026-06-27 · via DEV Community
Cover image for DESIGN.md, CLAUDE.md, AGENTS.md: The Agent-Context File Family

PromptMaster

DESIGN.md, CLAUDE.md and AGENTS.md are plain-text, repo-resident files that give AI coding agents persistent context. CLAUDE.md and AGENTS.md cover code and conventions; DESIGN.md covers the visual identity. Complementary layers an agent reads on every interaction.

What each file covers

CLAUDE.md / AGENTS.md  -> code & project context
                          (stack, conventions, commands)
SKILL.md               -> on-demand capabilities
DESIGN.md              -> the design system
                          (tokens + rationale)

Each handles a different concern, and they do not overlap.

Why separate files?

Separation keeps each focused and lets you adopt them independently. A team might start with CLAUDE.md for code context, add DESIGN.md when agent-generated UI drifts off-brand, and layer in skills later. All plain text, so they version and review like code.

They work together

The cleanest setup wires them: a CLAUDE.md that tells the agent to read DESIGN.md for UI work links code context to design context. The agent gets one coherent picture - how to write the code and how to make it look right.

Which to adopt first

Start with the file that solves your biggest pain:

  • Agent gets code conventions wrong -> CLAUDE.md / AGENTS.md
  • Agent writes correct code that looks off-brand -> DESIGN.md

Most teams end up with more than one, added as the need appears.

FAQ

One universal format? AGENTS.md is closest to a cross-tool standard for code context; DESIGN.md is the emerging standard for design context.
Can I have all three? Yes - code context, capabilities, and design context, each in its own file.

Bottom line

The pattern is the same across all of them: persistent, plain-text, repo-resident context an agent reads every time. DESIGN.md is the design member of the family.


Free starter: The format, a complete annotated example, and the core idea are on a free cheat sheet: DESIGN.md Quick-Start Cheat Sheet

Go deeper: The full guide covers the entire format — the token schema, the CLI in depth, accessibility, Tailwind and DTCG export, agent integration, and a complete walkthrough: DESIGN.md: The Complete Guide to Design Systems for AI Agents

How many of these files are in your repos already - none, one, or the full set? Curious where everyone is on this.