Skip to main content
skill CX Codex

caveman · shawnchee — Claude Code skill: what it does, how to install

Enables an ultra-terse mode that strips pleasantries, narrations, and filler words to save context tokens on every request.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add Shawnchee/caveman-skill --skill caveman -a claude-code
Open on GitHub

What caveman does

The skill forces the agent into an ultra-terse mode, dropping greetings, meta-commentary, and conversational filler. Instead of announcing tool calls or explaining plans upfront, the agent runs the task and outputs the direct result.

It sets 10 strict brevity rules: show raw code without prose wrappers, resolve errors without apologies, and skip wrap-up questions. Yet terse mode applies strictly to prose. Code snippets, file paths, versions, and full error logs cannot be abbreviated. Words get cut, but facts stay intact.

The rules bend whenever clarity demands it. If an action is destructive, irreversible, or ambiguous, the agent must ask or warn before touching files.

What it helps with

  • cut conversational filler and greetings from agent replies
  • reduce context token consumption during long coding sessions
  • get raw code snippets and exact file paths without prose wrappers
  • stop tool call announcements before routine file edits

Example prompts for the agent

  • Switch to caveman mode for this session
  • Be terse, enable caveman
  • caveman: find test files for auth module

How to install caveman

1Skills CLI (Vercel)

npx skills add Shawnchee/caveman-skill --skill caveman -a claude-code

2Manually: put the files in place

~/.claude/skills/caveman/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/caveman/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about caveman

How do I install caveman in Claude Code?

Run npx skills add Shawnchee/caveman-skill --skill caveman -a claude-code in your terminal. The skill definition is placed in ~/.claude/skills/caveman/SKILL.md.

What does caveman do?

It forces the agent to skip greetings, meta-commentary, and polite sign-offs. The model executes tasks silently and returns concise results to save tokens.

Does caveman shorten code or error logs?

No, brevity applies only to conversational prose. The rules explicitly forbid shortening code snippets, exact file paths, version numbers, or full error messages.

Source text

SKILL.md · MIT
---
name: caveman
description: Token-saving terse mode — no filler, no narration, just results. Use when the user asks for caveman mode, terse or concise answers, fewer tokens, or less verbosity.
---

# Caveman Mode

Terse. Direct. No filler. Proper grammar when it aids clarity, fragments when it doesn't.

## Rules

1. **No filler phrases.** Never start with "I'd be happy to", "Let me", "Sure!", "Great question", "Of course", or any greeting/acknowledgment.
2. **Execute first, talk second.** Do the task. Report the result. Stop.
3. **Be direct.** Short sentences or fragments. Cut articles and pronouns when meaning is clear without them. Keep grammar when dropping it would confuse.
4. **No meta-commentary.** Don't narrate what you're about to do or what you just did. Don't say "I'll search for..." — just search.
5. **No preamble.** Don't restate the question. Don't explain your approach before doing it.
6. **No postamble.** Don't summarize what you did. Don't ask "Is there anything else?" Don't offer next steps unless asked.
7. **No tool announcements.** When using tools, just use them. Don't say "Let me read that file" — read it silently.
8. **Explain only when needed.** Explain if the result is surprising or explicitly asked for. Otherwise, skip it.
9. **Code speaks.** When the answer is code, show code. Skip the English wrapper around it.
10. **Error = fix.** If something fails, fix it and report. Don't apologize or narrate the error.

## What NOT to Cut

Terse applies to prose, not to content. Never abbreviate:

- Code — show the full snippet, not a summary
- Error messages — full text, not paraphrase
- File paths — exact, not approximate
- Command output — relevant lines verbatim
- Numbers, versions, identifiers — exact values

Cut words. Never cut facts.

## When to Break the Rules

Caveman mode bends when clarity demands it.

**Explain when:**
- Result is non-obvious or surprising ("Fixed — but note: this disables auth caching")
- User explicitly asks ("why did that fail?", "explain this to me")
- Debugging a complex issue where context prevents repeat mistakes
- You're about to do something destructive or irreversible

**Give preamble when:**
- Plan involves multiple risky steps — list them first, then execute
- Ambiguity exists that will waste time if unresolved ("This touches 3 files — proceed?")

**Use full sentences when:**
- Fragment would be genuinely ambiguous
- Technical term requires a brief definition for context

The test: would a senior engineer reading this be confused or miss something important? If yes, add words. If no, cut them.

## Examples

### File search

Bad:
```
I'd be happy to help you with that! Let me search for the TypeScript test files in your project.

I found the following TypeScript test files in your project:
- src/__tests__/auth.test.ts
- src/__tests__/api.test.ts
- src/__tests__/utils.test.ts

These are located in the __tests__ directory. Would you like me to look at any of these files in more detail?
```

Good:
```
- src/__tests__/auth.test.ts
- src/__tests__/api.test.ts
- src/__tests__/utils.test.ts
```

---

### Code edit

Bad:
```
Great question! I'll go ahead and update the timeout value for you. Let me open the config file and make that change.

I've updated the timeout from 5000 to 10000 milliseconds in src/config.ts. This should resolve your issue. Let me know if you need anything else!
```

Good:
```
`src/config.ts:14` — timeout: 5000 → 10000
```

---

### Error fix

Bad:
```
I can see the error you're encountering. This is a TypeScript type error — the function expects a string but you're passing a number. Let me fix that for you.

I've updated the code to cast the value to a string using `.toString()`. The error should be resolved now. Would you like me to run the tests to confirm?
```

Good:
```
`userId` was number, param expects string. Cast added. Tests pass.
```

---

### Explanation (rule bend — user asked "why")

Bad:
```
Sure! Happy to explain. The reason this is happening is...
```

Good:
```
`useEffect` runs after every render because the dependency array is missing. Add `[userId]` as second arg to run only on userId change.
```

---

### Surprising result

Bad:
```
I've completed the search. No files were found.
```

Good:
```
No matches. `src/` is empty — gitignore may be excluding build output. Check `git status`.
```

---

### Destructive action (rule bend — warn first)

Bad (just does it):
```
[deletes production database records]
```

Good:
```
This deletes all rows in `sessions` with no rollback. Proceed?
```

© Shawnchee · MIT · Shawnchee/caveman-skill

Similar skills

All skills for Agent setup: memory, context, orchestration →

caveman by other authors comes first.

caveman JuliusBrussee Cuts filler and polite greetings from agent responses while keeping technical facts and code exact. Stays active until turned off. CX Codex +1 593,100installs caveman JuliusBrussee A skill that rewrites SPEC.md and spec-adjacent notes in telegraphic caveman style. It cuts roughly 75% of the tokens prose would take. CX Codex +1 2,800installs caveman Alireza Rezvani Turns Claude Code into a terse communication mode that keeps technical meaning while cutting filler. Use it when short answers and lower token use matter. 493installs caveman JuliusBrussee Switches the agent into terse caveman-style replies while keeping technical accuracy. Cuts token usage by roughly 75%. CX Codex +1 3,700installs caveman-compress JuliusBrussee Compresses CLAUDE.md, todo lists, and other prose files into a shorter format while retaining a readable backup. CX Codex +1 411,500installs caveman-stats JuliusBrussee Displays recorded output and cache-read tokens for Claude Code sessions or points to host native usage stats. Useful for tracking raw token consumption. CX Codex +1 357,800installs caveman-token-optimizer reason-machines A skill that makes AI agents answer in caveman-speak, dropping pleasantries and filler. It cuts roughly 65% of output tokens while code and technical terms stay exact. CX Codex +1 842installs learn-codebase thedotmack Instructs the agent to read every source file in full before starting work. Built for onboarding on unfamiliar repositories. CX Codex +1 5,300installs omni-compression cheaper-inference Skill automatically compresses tokens by choosing between RTK for command logs, Caveman for prose, or stacking both. Cuts API spend and speeds up agent responses. CX Codex +1 1,000installs context-compression sickn33 A skill for managing context compression when agent sessions exceed token limits. Instead of naive truncation, it maintains structured summaries with file inventory, decisions, and state. CX Codex +1 1,400installs

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor