Free fiche
Nine modules on what actually drives your usage up. Every concept explained, then shown on my own setup: my files, my skills, my automations, and two months of real measurements.
230
sessions measured, July and August
19×
average re-reads of what goes in
0
lines of code needed to apply it
CLAUDE.md, so you stop repeating yourself
Why the model has no memory, what that means for the cache, and my full file stack, down to the instruction pointing at a folder that vanished months ago.
/clear or /compact
Why /compact costs more than /clear even though everyone assumes the opposite, and when to use each.
Model and effort, decided once
Why switching models mid-session gets billed at full price, and why a /clear beats switching halfway through.
Go straight to the point
The difference between asking Claude to search and telling it where things are, measured on one of my sessions with a million tokens of open files.
The hash sign, to remember a correction
How a correction becomes a permanent rule in one sentence, with one of my 27 memory files, in full.
Building your own skills
The two ways the same file fires, the header that decides whether Claude finds it, and the naming trap that hid the most useful measuring tool from me.
Hooks, the automations
When they fire, what the program can answer, and one of mine in full. Plus three traps I hit, including the one that lied to Claude without anyone noticing.
Delegating to an agent
Why its forty pages never land in your conversation, and why delegating a short task costs more than doing it. With the measuring trap that doubles a bill.
Delegating even the repetitive tasks
The setting that runs a whole skill in its own context, so its draft work never lands in yours.
Beyond the video
Three bonus modules (measuring, running unattended, storing notes) and a fourteen-day plan, one move a day.
One email, one link, and it's yours. You also get Umami, my monthly newsletter on what I build and what it costs.
Is it really free?
Yes. You leave an email, you get the link. Nothing to pay, nothing to install.
Do I need to code?
No. Everything in the fiche is asked of Claude in plain language. The file excerpts are there so you recognise your own, not so you write them.
Where do the numbers come from?
From my own usage, 1 July to 24 August 2026, 230 sessions, measured continuously. The configuration excerpts are my real files, shortened for readability but never rewritten.
Does it apply to Claude in general, or only Claude Code?
The cache and context mechanics apply everywhere. Skills, hooks and agents are specific to Claude Code.