[ blog ]
Field notes
Engineering insights, tutorials, and product updates from the Codehabits team, on AI coding tools, Agent Skills, and what makes good code feel like yours.
Cursor Rules Not Firing? alwaysApply, Globs & .mdc Explained
If your Cursor .mdc rules never attach, the frontmatter is usually wrong. Learn the four rule types — alwaysApply, globs, agent-requested, and manual — with copy-paste examples that actually fire.
Cursor Global User Rules: Where ~/.cursor/rules Lives (and When AlwaysApply Matters)
Confused about Cursor global vs project rules? Here's the exact home-directory path on Mac and Windows, how AlwaysApply works, and when to use user rules vs .cursor/rules in the repo.
Cursor Not Following Rules? 3 Causes (and the Fix)
Cursor not following rules usually means the wrong path, AlwaysApply/globs misconfigured, or vague rules losing to model defaults. Diagnose .cursor/rules and .cursorrules in minutes.
Setting Up the Codehabits MCP Server in Cursor (5 Minutes)
Step-by-step guide to installing @codehabits/mcp in Cursor, verifying all eight tools work (including get_repo_map), and using get_team_context and check_code in your daily workflow.
How to Migrate from Cursor Rules to Agent Skills
Stop maintaining .cursor/rules by hand. Learn how to move team conventions to the open Agent Skills standard — and auto-generate them from your PR history with Codehabits.
Why we built Codehabits
Every team has habits: the small, repeated patterns that make code feel like yours. We built Codehabits to extract those habits and ship them to every AI tool your team uses.
What's New: Team Workspaces, Split Intelligence, and MCP Feedback
Team dashboards, .codehabits split files, merge pipeline updates, MCP tools to record feedback and approve proposals, and refreshed docs. Here’s what shipped recently.
Introducing codehabits: Team Intelligence That Every AI Tool Auto-Discovers
One command extracts your team's coding conventions, anti-patterns, and domain knowledge from PR history - then delivers it to Cursor, GitHub Copilot, Claude Code, and 20+ AI tools automatically.
What Are Agent Skills? The Open Standard for AI Coding Tools
Agent Skills solve the fragmentation problem across Cursor, Copilot, Claude Code, Codex, and Windsurf by giving every AI tool a shared way to discover team-specific coding intelligence.
How to Make Cursor, GitHub Copilot, and Claude Code Follow Your Team's Conventions
A practical guide to configuring every major AI coding tool - Cursor, GitHub Copilot, Claude Code, Codex, Windsurf, Gemini CLI - to respect your team's patterns, or automating the entire process with codehabits.
The Complete Guide to AI-Assisted Code Review in 2026
Everything teams need to know about AI-assisted code review - from GitHub Copilot code review to codehabits's team intelligence, comparing tools, workflows, and best practices for modern engineering teams.
Why AI Coding Tools Ignore Your Team's Patterns (And How to Fix It)
Cursor, Copilot, and Claude Code generate great code - but not your team's code. Here's why the gap exists, what it costs, and how team intelligence closes it.