Caveman Mode

An ultra-terse overlay that keeps the substance

The Padding Problem

Every answer opens with filler you didn't ask for.

"Sure! I'd be happy to help you with that." Real technical substance shows up buried under pleasantries, hedging, and articles on every single response. Caveman is a loadable Amplifier behavior overlay that strips it.

And that padding isn't free — it has a price on every turn.

Caveman's own design target: roughly 75% fewer output tokens.

The bundle self-describes as an "Ultra-terse LLM communication overlay. ~75% fewer output tokens." It's a claimed design target — no benchmark file in the repo measures the exact figure.

Cutting that much sounds great — until you ask what gets cut.

~75%
fewer output tokens per response — the bundle's stated design target (bundle.md)
The Hard Part

Terse is easy. Terse without losing the substance is the hard part.

Anything can cut words. The risk is cutting the technical payload you actually needed — fragments can mangle meaning, and fragment order can risk a misread.

So the rule has to be surgical: remove fluff, never substance.

Drop the fluff. Keep the substance exact.

One precise rule from caveman-common.md: strip articles, filler, pleasantries, and hedging — while technical terms stay exact, code blocks stay unchanged, and errors are quoted exact.

One rule, three intensities — here's the dial.

Three intensity levels, in just 8 files and 105 lines.

Caveman ships lite, full (the default), and ultra. The whole bundle is 8 tracked source files totaling 105 lines — small enough to read and trust in a sitting.

Small and terse — but what stops it from being terse at the worst moment?

caveman-lite
Lightest touch
caveman (full)
The default level
caveman-ultra
Most terse
8
tracked source files
105
total lines

It knows when NOT to be terse.

Caveman's Auto-Clarity carve-out drops terseness for security warnings and irreversible-action confirmations — those render in full normal prose. Terseness resumes after the clear part is done.

Judgment about when to stop is what makes it trustworthy, not just clever.

Auto-Clarity override

Drop caveman for: security warnings, irreversible action confirmations, multi-step sequences where fragment order risks misread, or when the user asks to clarify. Resume caveman after clear part done.

Persistent by default — you opt in once.

Caveman is active every response — no revert after many turns, no filler drift, still active if unsure. It's off only when you say "stop caveman" / "normal mode" or disable via /config.

Opt into terseness once; the safety stays automatic.

# Load the overlay amplifier bundle add \ git+https://github.com/bkrabach/amplifier-bundle-caveman # Turn it off any time stop caveman normal mode
The Pattern

Strip the fluff. Keep the substance. Let the tool know when clarity beats brevity.

Caveman v1.0.0 is a tiny, loadable Amplifier overlay layered on microsoft/amplifier-foundation — ~75% fewer output tokens by design, with the technical payload and the safety carve-out kept intact.

Sources

Research Methodology

Released — bundle v1.0.0

Data as of: 2026-04-15 (last commit). Subject: bkrabach/amplifier-bundle-caveman, identified by cloning and reading the primary-source repo directly.

Commands run:

Gaps: The ~75% figure is the bundle's own description string, not an independently measured result — treat as a claimed design target. "100% technical substance intact" is design intent in the context files, not a measured guarantee.

Contributors: Sole commit author "Amplifier Bundle <caveman-bundle@amplifier.local>" (2 of 2 commits); repo owner bkrabach per remote.

More Amplifier Stories