How to Migrate from Cursor Rules to Agent Skills

Agent Skills are the open standard (agentskills.io) for packaging team-specific instructions that any AI coding tool can discover.

Migrating from hand-maintained Cursor rules means moving from static markdown you write once to structured, evidence-ranked intelligence your team already enforced in PR review — and (optionally) letting tooling generate the skill automatically.

Why…

Read more →
Setting Up the Codehabits MCP Server in Cursor (5 Minutes)

The Codehabits MCP server gives Cursor six tools that read from .codehabits/ in your repo — convention lookup, code validation, domain knowledge, reviewer suggestions, and a feedback loop for updating conventions.

Setup takes about five minutes if you already ran codehabits enable.

Prerequisites

  • Node.js 20+
  • .codehabits/meta.json in your repo (from `npx @codehabits/cli…
Read more →
IR #011: When the Help Desk Helps Itself

IR #011: When the Help Desk Helps Itself

Agent Incident Report #011 — June 13, 2026

Three of these happened. One is fabricated. Which one?

A. The Deputy Did What It Was Told

System: Meta AI Support Chatbot (Instagram)
Date: April–May 2026
Severity: Critical — up to 20,225 account takeovers

Meta launched an AI-powered support chatbot for Instagram account recovery in early 2026. The "High…

Read more →
B
A free site uses live weather data to flag pavement that will burn your dog's paws

Press the back of your hand against the sidewalk for seven seconds. If you can't stand it, your dog can't either. That's the old vet's rule for hot pavement, and it works. Asphalt at an 87°F air temperature can reach 140°F in direct sun; vets see paw burns every summer. — Read the rest

The post A free site uses live weather data to flag pavement that will burn your dog's paws appeared first on…

B
The $30 billion AI code editor that might already be obsolete

Cursor's four cofounders became billionaires in 2025 selling an AI code editor that hit $1 billion in annualized revenue by November. Three months later, they held an all-hands meeting with slides titled "War Time."

Over the holiday break, the company's own engineers had tested Anthropic's Opus 4.5 and found that the model could write code well enough to skip human review. — Read the rest…

Cursor’s new Automations launch reimagines agentic coding

Cursor launched a new automation tool designed to manage coding agents on Thursday. The system, called Automations, automatically launches agents triggered by events like new code additions, Slack messages, or timers. This aims to shift engineers from a “prompt-and-monitor” dynamic to a model where humans are looped in only when needed. The tool addresses the […]

Cursor hits $2 billion in annual revenue as run rate doubles

Cursor surpassed $2 billion in annualized revenue, according to a Bloomberg source. The startup’s revenue run rate doubled over the past three months. The disclosure counters recent skepticism regarding user defections to competing tools like Anthropic’s Claude Code. This revenue milestone underscores the rapid scaling of AI-assisted software development tools. It highlights a shift in […]

Developing a Mental Model for using Models

I had an interesting realization today while doing a demo building a web app with Cursor.
I was debugging an issue with an MCP server, trying to connect it to Cursor's MCP integration.
The code I was using was buggy, and I'd never tried this before (attempting it live was probably a fool's errand to begin with).

When I ran into issues, someone watching asked, "Why don't you just ask the Cursor…

Read more →
Page 1