Stop Stuffing CLAUDE.md: The 7 Controls Claude Code Gives You
Anthropic's own engineering post admits a prompted "never do this" can fail under pressure. Here's my map of the seven ways to steer Claude Code — when each one enters the context, how hard it's enforced, and the rule I use to decide where an instruction belongs.
- #claude-code
- #hooks
- #skills
- #subagents
- #context-engineering
Sign in to keep reading
Stop Stuffing CLAUDE.md: The 7 Controls Claude Code Gives You — Anthropic's own engineering post admits a prompted "never do this" can fail under pressure. Here's my map of the seven ways to steer Claude Code — when each one enters the context, how hard it's enforced, and the rule I use to decide where an instruction belongs.
Your first guide is free. Sign in with Google or LinkedIn to read the whole library and get new guides as they ship — no cost.
Keep reading
More guides like this one.
To Stop Babysitting Claude, Give It a Failing Test
Autonomy is not a permissions problem, it is a verification problem. Claude can already run unattended — what is missing is a check it cannot talk its way past. Here are the three you can wire up today.
A Good Handoff Is Mostly a List of Dead Ends
Compaction and `/resume` both preserve what happened. Neither preserves what you decided against — and the abandoned attempts are the most expensive thing in a long session. Here's the handoff file that fixes it, the prompt that writes it, and the one-liner that generates it from a session you already closed.
Stop Watching AI Demos. Read Their Transcripts.
A finished repo teaches you nothing about how it got finished. Since December 2025 you can read a power user's entire Claude Code session — every prompt, every wrong turn, every correction. Here are the five sessions and write-ups worth studying, and exactly what to look for in each.