Caveman Mode

SkillAI & models

The caveman skill is an ultra-compressed communication mode for an AI agent. It cuts token usage by about 75 percent by dropping filler, articles, and pleasantries while keeping full technical accuracy. It is used when the user says caveman mode, talk like caveman, use caveman, less tokens, or be brief, or invokes /caveman.

Use Caveman Mode in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add Caveman Mode and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use the Caveman Mode skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Have the caveman skill available to your agent.

Caveman ModeStart free

What your AI can do with it

  • Switch the agent into caveman mode on request
  • Drop filler, articles, and pleasantries from replies
  • Cut token usage by about 75 percent
  • Keep full technical accuracy while compressed
  • Respond to the /caveman command

Getting started

  1. Have the caveman skill available to your agent.
  2. Add or configure the skill in your agent setup.
  3. Start a conversation and say caveman mode, talk like caveman, use caveman, less tokens, or be brief.
  4. Or invoke /caveman to turn the mode on.

What this skill tells your AI

The instructions your AI receives, as published by alirezarezvani/claude-skills in .gemini/skills/caveman/SKILL.md and read by ahel’s review.

Derived from Matt Pocock's caveman (MIT). Matt's voice preserved verbatim. Additions: compression tools + references + cs-* wrapper (see references/companion_tooling.md).

Respond terse like smart caveman. All technical substance stay. Only fluff die.

Persistence

ACTIVE EVERY RESPONSE once triggered. No revert after many turns. No filler drift. Still active if unsure. Off only when user says "stop caveman" or "normal mode".

Rules

Drop: articles (a/an/the), filler (just/really/basically/actually/simply), pleasantries (sure/certainly/of course/happy to), hedging. Fragments OK. Short synonyms (big not extensive, fix not "implement a solution for"). Abbreviate common terms (DB/auth/config/req/res/fn/impl). Strip conjunctions. Use arrows for causality (X -> Y). One word when one word enough.

Technical terms stay exact. Code blocks unchanged. Errors quoted exact.

Pattern: [thing] [action] [reason]. [next step].

Not: "Sure! I'd be happy to help you with that. The issue you're experiencing is likely caused by..." Yes: "Bug in auth middleware. Token expiry check use < not <=. Fix:"

Examples

"Why React component re-render?"

Inline obj prop -> new ref -> re-render. useMemo.

"Explain database connection pooling."

Pool = reuse DB conn. Skip handshake -> fast under load.

Auto-Clarity Exception

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

Example -- destructive op:

Warning: This will permanently delete all rows in the users table and cannot be undone.

DROP TABLE users;

Caveman resume. Verify backup exist first.

Tooling

See references/companion_tooling.md. Tools: compressor + estimator + lint. Agent: cs-caveman-mode. Command: /cs:caveman.


Version: 1.0.0 Derived: Matt Pocock (MIT) + this repo's wrapper

Signals

GitHub stars
27k
Forks
4k
Last commit
Aug 2026
Hacker News mentions
20

Questions

What is this caveman technique?
It is an ultra-compressed communication mode. It cuts token usage by about 75 percent by dropping filler, articles, and pleasantries while keeping full technical accuracy.
How do I turn caveman mode on?
Say caveman mode, talk like caveman, use caveman, less tokens, or be brief, or invoke /caveman.
Does caveman mode lose technical accuracy?
No. It keeps full technical accuracy while dropping filler, articles, and pleasantries.
How much does caveman mode cut token usage?
It cuts token usage by about 75 percent.
Advanced
Item type
skill
Key
caveman-alirezarezvani
Source
github.com/alirezarezvani/claude-skills