A Claude Code Agent Skill built from Dex Horthy's (HumanLayer) playbook on David Ondrej's podcast.
"Once the model has written thousands of lines of code, it is harder to change. The sessions that generate design docs are context-light — you get the most model intelligence when you do the hard thinking early."
By default, agents build horizontally: all the backend, then all the frontend, then a 2,000-line diff lands in your lap and reviewing it is your problem. This skill flips that. Every decision that matters gets made before the code exists — where changing your mind costs a sentence, not a rewrite.
Every tool, technique, and idea from David Ondrej's interview with Thorsten Ball (Amp) — agents in orbs, the Oracle, Puck the meta-agent, the prompting playbook, and the features Amp killed on purpose.
Click here to view the Episode Pack
(It's a single self-contained HTML page — the file thorsten-episode-pack.html below. You can also download it and open it in any browser.)
A Claude Code Agent Skill built from Thorsten Ball's (Amp) playbook on David Ondrej's podcast.
"An agent has two sources of information: training data and the context window. That's it. The most important number in this equation is the information that you put in."
Most skills change what your agent does. This one changes what you do — it coaches you to prompt like a senior engineer briefing another senior engineer, and it gets quieter as you get better.