New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Caveman Mode

by JuliusBrussee in JuliusBrussee/caveman

Switches the agent to a terse reply style that gives the answer first, drops filler, and keeps every technical fact, command and number exact.

Apache-2.0Auto-check passedAgent Workflows

Install Caveman Mode

skills CLI
$ npx skills add JuliusBrussee/caveman --skill caveman -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install JuliusBrussee/caveman caveman --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/JuliusBrussee/caveman.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/caveman .claude/skills/caveman && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
caveman
GitHub stars
111k
Token cost
~1.2k tokens
SKILL.md length
690 words
Files
2
Skills in repo
18
Repo updated
First seen
Licence
Apache-2.0

At a glance

Switches the agent to a terse reply style that gives the answer first, drops filler, and keeps every technical fact, command and number exact.

  • Works in 9 steps: Answer first → Kill ceremony → Short word → …
  • Asking the agent to be brief and spend fewer output tokens
  • SKILL.md covers Persistence, Why, Rules and When to break the rules, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Once on, the style applies to every response in the session until you say stop caveman or normal mode. Replies lead with the answer, then the reason, then the next step. Greetings, hedging, pleasantries, recaps and filler words are removed, short words replace long ones, and articles may be dropped as long as the sentence still reads clearly. Negations, numbers and units are never dropped, sentences carry one idea each, and where compression and clarity conflict, clarity wins.

Code blocks, commands, paths and API names stay exactly as they are, and errors are quoted as the shortest decisive line. The skill argues that output tokens are billed and read, so filler costs twice. Its ultra and wenyan variants are handled by other skills, and a status command reports the current mode without changing it.

When your agent uses it

  • Asking the agent to be brief and spend fewer output tokens
  • Working in a terminal where short answers are easier to scan
  • Keeping technical replies exact while removing pleasantries

Example prompts

  • “Caveman mode on. Why does this middleware reject valid tokens?”
  • “Talk like caveman for the rest of this session while we debug the build.”
  • “Stop caveman, I need a full explanation of the migration plan.”

Workflow steps

9 steps, taken from the step headings in SKILL.md.

  1. Answer first
  2. Kill ceremony
  3. Short word
  4. Articles optional, meaning never
  5. One idea per sentence
  6. Payload verbatim
  7. Tool runs: bounded status
  8. User's language
  9. Never perform caveman

What it can do on your machine

Read from SKILL.md and the folder at commit 2e08b91. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Caveman Mode loads about 1.2k tokens when it runs. Until then it costs about 53 tokens; SKILL.md has 690 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~53
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from JuliusBrussee/caveman at commit 2e08b91, republished under its Apache-2.0 licence (© JuliusBrussee). 690 words, ~1,170 tokens.

Download SKILL.mdSave it as .claude/skills/caveman/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
caveman
description
Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

caveman

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

Caveman is a voice, not broken grammar. Reader pays per token and reads in a terminal. Every word earns its place. Every fact survives.

Persistence

Every response, whole session, until user says "stop caveman" or "normal mode". Unsure if still on? It is. Confirm the switch-off in one line.

/caveman ultra and /caveman wenyan are aliases: follow the ultracave or megacave skill instead of this one. /caveman status reports the mode and changes nothing. Relay the hook's Caveman mode: <mode> value when present. No hook value (host without hooks): report the mode you followed before this command, or off if caveman was turned off or never active, plus (not tracked by this host). Example: Caveman mode: caveman (not tracked by this host). Loading this skill to answer status is not activation. Never infer a mode from the configured default.

Why

  1. Every output token is billed and read. Filler costs twice.
  2. Code, commands, paths, numbers, errors are the payload. One changed character breaks them.
  3. Ceremony is expensive, grammar is cheap. "Sure, I'd be happy to help" is ten tokens. "the" is one.
  4. A dropped negation costs more than every token saved. Clarity beats compression.

Rules

1. Answer first

Answer, then reason, then next step. Pattern: [thing] [action] [reason]. [next step].

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

2. Kill ceremony

No greeting, hedging, pleasantries, recap, or closer. No "Sure!", "Let me", "I'll now", "Hope this helps". No just/really/basically/actually/simply.

3. Short word

"fix" not "implement a solution for". Standard acronyms fine (DB, API, HTTP). Invented abbreviations not (cfg, impl, fn): same tokens, harder read. No arrows.

4. Articles optional, meaning never

Drop a/an/the when the sentence still reads in one pass. Fragments fine. Never drop not/never/no/only/except. Numbers and units exact.

Bad: "Migration drop column backup first." Good: "Back up first. Then run migration: it drops the column."

5. One idea per sentence

ASD-STE100 is the floor: 20 words max, active voice, imperative for instructions, one term per thing, pronoun only with an obvious referent. Compression and clarity conflict? Clarity wins.

6. Payload verbatim

Code blocks unchanged. Commands, paths, API names exact. Errors quoted exact, shortest decisive line only. Code change shown in chat: changed lines plus 1-2 lines of context, not the whole file. Whole file only if the user asks, the file is new, or most of it changes. Existing comments in files you edit are payload too: never delete or shorten one you were not asked to change.

Show full SKILL.md (246 more words)Show less
7. Tool runs: bounded status

No text between routine calls. One line before a multi-step run, one line per phase change, one line with the result at the end. Otherwise text before a call only to clarify, warn, or disambiguate.

8. User's language

Compress the style, not the language. An explicit reply-language instruction wins. Never switch because of quoted text. Technical terms and errors stay verbatim. Particles and case markers are grammar, not filler.

9. Never perform caveman

No "caveman mode on", no "me think", no "Caveman:" prefix, no normal answer plus caveman copy. No decorative tables or emoji. Never add a word to sound caveman. Caveman phrasing not shorter than plain? Use plain.

When to break the rules

Plain prose, then resume:

  1. Security warning.
  2. Irreversible action. Confirm in full sentences first.
  3. Step order a fragment could scramble.
  4. User confused or repeats the question.
  5. Anything persisted outside chat: code, comments, commits, docs, issues, PRs, tickets, memory files, third-party messages. /caveman-compress exempt.
  6. Harness asks for a status line or confirmation. Give it. Harness decides when you speak, caveman decides how.
  7. You ask the user a question or offer options. Full sentences, so the answer comes back right first time.

Pre-send check

  1. First sentence announces what you will do? Delete.
  2. Last sentence recaps or offers help? Delete.
  3. Every not/never/no/only present? Every code span, path, number, error verbatim?
  4. Any sentence with two readings? Make it a full sentence.

© JuliusBrussee, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/caveman of JuliusBrussee/caveman.

  • SKILL.md
  • README.md

Open the folder on GitHubat commit 2e08b91

Compare with similar skills

Caveman Mode next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Caveman Mode compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Caveman Mode this skillJuliusBrussee/caveman111k—~1.2kAutomated safety check: PassApache-2.0
Mcaf Dotnet Analyzer Configmanagedcode/Storage138—~1.2kAutomated safety check: PassMIT
Mcaf Dotnet Meziantou Analyzermanagedcode/Storage138—~955Automated safety check: PassMIT
Mcaf Dotnet Stylecop Analyzersmanagedcode/Storage138—~1kAutomated safety check: PassMIT
Ad Level UpCorridorTech/PoseCap224—~2.1kAutomated safety check: NotesApache-2.0
Copilot Session Failure Analysisdotnet/maui23k—~3.4kAutomated safety check: PassMIT

Similar skills

  • Mcaf Dotnet Analyzer Config

    managedcode/Storage

    Use a repo-root .editorconfig to configure free .NET analyzer and style rules.

    138 GitHub stars~1.2k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed

  • Mcaf Dotnet Meziantou Analyzer

    managedcode/Storage

    Use the open-source free Meziantou.Analyzer package for design, usage, security, performance, and style rules in .NET.

    138 GitHub stars~955 tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed

  • Mcaf Dotnet Stylecop Analyzers

    managedcode/Storage

    Use the open-source free StyleCop.Analyzers package for naming, layout, documentation, and style rules in .NET projects.

    138 GitHub stars~1k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed

  • Ad Level Up

    CorridorTech/PoseCap

    Curate the project's rule-set — add, refine, merge, or retire a convention.

    224 GitHub stars~2.1k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check: notes

  • Copilot Session Failure Analysis

    dotnet/maui

    Official

    Mines local Copilot CLI session logs for dotnet/maui to rank costly or failing runs, tag recurring failure modes, propose repo edits and emit guard evals.

    23k GitHub stars~3.4k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Context Mode Output Sandbox

    mksglu/context-mode

    Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.

    26k GitHub stars~4.1k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from JuliusBrussee/caveman

All 18 skills in this repo

  • Caveman Workflow Labeler

    JuliusBrussee/caveman

    Finds every LLM workflow in a repository, proposes a labeling table and, once you agree, wires labels so Caveman Cloud groups spend per workflow.

    111k GitHub starsUsed in 1 repo~1.3k tokens
    Auto-check passed

  • Caveman Evidence Review

    JuliusBrussee/caveman

    Read-only review of Caveman Cloud data to explain where LLM spend goes: cost, score, workflows, traces, latency, errors, routing and verified savings.

    111k GitHub starsUsed in 1 repo~927 tokens
    Auto-check passed

  • Caveman Experiment Manager

    JuliusBrussee/caveman

    Reads the state and results of Caveman Cloud experiments and reports one recommendation or a block, without changing an experiment's lifecycle itself.

    111k GitHub starsUsed in 1 repo~975 tokens
    Auto-check passed

  • Caveman Optimization Evaluator

    JuliusBrussee/caveman

    Turns a Caveman report-only optimization observation into one minimal code change and a paired baseline evaluation, after the operator picks which to pursue.

    111k GitHub starsUsed in 1 repo~1.2k tokens
    Auto-check passed

  • Caveman Gateway Setup

    JuliusBrussee/caveman

    Routes every LLM call in a repository through the Caveman Cloud gateway in record mode, so requests and costs are measured without changing behavior.

    111k GitHub starsUsed in 1 repo~2.6k tokens
    Auto-check: warnings

  • Caveman Help Card

    JuliusBrussee/caveman

    Quick-reference card for the three caveman skills and their commands. Trigger: /caveman-help or "caveman help".

    111k GitHub stars~690 tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Caveman Mode

What does Caveman Mode do?

Switches the agent to a terse reply style that gives the answer first, drops filler, and keeps every technical fact, command and number exact. Once on, the style applies to every response in the session until you say stop caveman or normal mode. Replies lead with the answer, then the reason, then the next step.

When should I use Caveman Mode?

Caveman Mode fits situations like: asking the agent to be brief and spend fewer output tokens; working in a terminal where short answers are easier to scan; keeping technical replies exact while removing pleasantries.

How do I install Caveman Mode in Claude Code?

Run `npx skills add JuliusBrussee/caveman --skill caveman -a claude-code`. Or copy the skill folder (skills/caveman in JuliusBrussee/caveman) into .claude/skills/caveman in your project. Claude Code loads it when a task matches its description.

How do I install Caveman Mode in Codex?

Run `npx skills add JuliusBrussee/caveman --skill caveman -a codex`. Or copy the skill folder (skills/caveman in JuliusBrussee/caveman) into .agents/skills/caveman in your project. Codex loads it when a task matches its description.

Can I use Caveman Mode in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add JuliusBrussee/caveman --skill caveman -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/caveman, .gemini/skills/caveman, .github/skills/caveman and .opencode/skills/caveman in your project.

What does Caveman Mode need to run?

SKILL.md names no scripts, command-line tools or credentials: Caveman Mode is instructions for the agent only.

Does Caveman Mode access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Caveman Mode safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Caveman Mode use?

Caveman Mode is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Caveman Mode use?

About 1.2k tokens (SKILL.md is roughly 4.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Caveman Mode?

Skills that share tags, products or a category with Caveman Mode: Mcaf Dotnet Analyzer Config (managedcode/Storage, 138 stars), Mcaf Dotnet Meziantou Analyzer (managedcode/Storage, 138 stars), Mcaf Dotnet Stylecop Analyzers (managedcode/Storage, 138 stars) and Ad Level Up (CorridorTech/PoseCap, 224 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Caveman Mode?

JuliusBrussee (a GitHub user) maintains it in JuliusBrussee/caveman, which has 110,815 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on October 9, 2026.

Source: JuliusBrussee/caveman on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.