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

J
Java Code Geeks
aimingoo的专栏
aimingoo的专栏
Martin Fowler
Martin Fowler
C
Check Point Blog
G
Google Developers Blog
V
Visual Studio Blog
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
Google DeepMind News
Google DeepMind News
人人都是产品经理
人人都是产品经理
有赞技术团队
有赞技术团队
MongoDB | Blog
MongoDB | Blog
月光博客
月光博客
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
大猫的无限游戏
大猫的无限游戏
D
Docker
Hugging Face - Blog
Hugging Face - Blog
The GitHub Blog
The GitHub Blog
博客园 - 三生石上(FineUI控件)
A
About on SuperTechFans
Recent Announcements
Recent Announcements
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
阮一峰的网络日志
阮一峰的网络日志
Stack Overflow Blog
Stack Overflow Blog
Vercel News
Vercel News

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
I built a validated alternative to CLAUDE.md/AGENTS.MD — ...
Prism Team · 2026-04-26 · via DEV Community

Prism Team

If you've used Claude, Cursor, or Copilot on a real project, you've probably created a CLAUDE.md or agents.md file — a markdown file that tells the AI about your codebase.

The problem is there's nothing stopping that file from being wrong.

You declare language: typescript but the project is now Python. You list entry points that no longer exist. Your version numbers drift from what's actually in package.json. The AI reads your context file, trusts it, and works from bad information.

That's why I built GUIDE.md.

What is GUIDE.md?

GUIDE.md is a validated, drift-aware AI context standard. It's the same idea as CLAUDE.md — a file that gives AI agents structured context about your project — but with one key difference:

It can be wrong. Which means it can be verified.

How it works

A GUIDE.md file has two parts:

YAML frontmatter — machine-readable metadata validated against a schema:

---
guide_version: "1.0.0"
project: "my-app"
language: python
framework: fastapi
strict_typing: false
error_protocol: verbose
guardrails:
  no_hallucination: true
  scope_creep_prevention: true
context:
  entry_points:
    - "src/main.py"
  off_limits:
    - ".env"
---

Enter fullscreen mode Exit fullscreen mode

Markdown body — human and AI readable instructions:

## Project Overview
## Domain Vocabulary
## Non-Obvious Decisions
## What NOT to do

Enter fullscreen mode Exit fullscreen mode

The CLI tool

npm i -g @prismteam/linter

Enter fullscreen mode Exit fullscreen mode

Initialize in any project:

guidemd init

Enter fullscreen mode Exit fullscreen mode

Auto-detects your language, framework, paradigm, runtime, and entry points — across TypeScript, Python, Go, Rust, Java, Ruby, PHP, Swift, Dart, Elixir and more.

Validate:

guidemd lint

Enter fullscreen mode Exit fullscreen mode

Catches missing required fields, stale dates, weak descriptions, and exposed secrets.

Detect drift:

guidemd sync

Enter fullscreen mode Exit fullscreen mode

Compares your declared versions against actual package.json, requirements.txt, Cargo.toml, go.mod and warns you when they diverge.

Export to every format:

guidemd export

Enter fullscreen mode Exit fullscreen mode

Generates CLAUDE.md, .cursorrules, .windsurfrules, AGENTS.md, .github/copilot-instructions.md and .aider.conf.yml from one source of truth.

Why not just use CLAUDE.md?

CLAUDE.md GUIDE.md
Schema validation
Drift detection
Auto-detection
Multi-format export
Secret scanning
MCP server

CLAUDE.md is a convention. GUIDE.md is a standard.

Try it

npx @prismteam/linter init

Enter fullscreen mode Exit fullscreen mode

The repo is open source — feedback and contributions welcome.