Run /code-review before you push: levels, --fix and two gotchas
The local review costs you a terminal command. A few details decide whether it's useful or noisy.
3 min read
Development
The craft of building software with AI: testing, debugging, specs, refactoring and code review.
Build a Claude Code subagent that reviews your diff with fresh eyes
A reviewer that never saw the code being written catches different things. Here's the file, the invocation and the over-reporting trap.
3 min read
Let the agent interview you, then write the spec, then start fresh
A three-step workflow for features too big for one prompt, and what makes a spec worth handing over.
3 min read
You can now ask Copilot for a code review from a script
GitHub's REST and GraphQL APIs can request a Copilot review, and the default review depth just changed.
3 min read
Stop telling your AI agent to 'fix the bug'. Make it reproduce it first
A bug prompt in three parts, a failing test you can read in ten seconds, and a reusable command so you never skip the step. About fifteen minutes to set up.
7 min read
Make Claude Code run your tests before it's allowed to say it's done
A Stop hook turns 'please run the tests' from a request into a rule. Here's a working setup and the trap to avoid.
3 min read