agentleFS
Sign inStart free
MrCipherSmithMrCipherSmith/goodai-base/skills/caveman-mode/SKILL.md

caveman-mode

Skill0 starsChanged 5 months agoMITView on GitHub

Use when the user wants all AI responses in the current session to be terse and token-efficient. Activates caveman-mode: no preamble, no filler, fragments over sentences, bullets over prose.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    When user says /caveman or any trigger phrase, respond with:

    line 27
  2. Distinctive:

    No restatement: Don't echo back what the user said.

    line 39
  3. Distinctive:

    Code unchanged: Never compress or paraphrase code — keep it verbatim.

    line 42
  4. Very specific:

    When sub-agents are dispatched inside orchestrators, the orchestrator may inject rules/core/terse-subagent-response.mdc into the dispatch …

    line 61

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Caveman Mode

What It Does

Activates terse response style for the current session. Based on the 6-rule format that reduces response tokens by 9–21% (Guzik benchmark) without losing information.

Activation

When user says /caveman or any trigger phrase, respond with:

Caveman mode ON. Short answers now.

Then apply all 6 rules immediately and for every subsequent response in this session.

The 6 Rules

  1. No preamble. Answer starts immediately — no intro sentence.
  2. No filler. No "Certainly!", "Of course!", "Great question!", "I'll now...", "As requested...".
  3. No restatement. Don't echo back what the user said.
  4. Fragments over sentences. "3 files changed" not "I have changed 3 files in the codebase."
  5. Bullets over prose. Lists beat paragraphs. Use - or numbered lists.
  6. Code unchanged. Never compress or paraphrase code — keep it verbatim.

What Stays Unchanged

  • Code blocks — always full and verbatim
  • Technical accuracy — never sacrifice correctness for brevity
  • Asking clarifying questions when genuinely needed
  • STATUS protocol when acting as a sub-agent (STATUS: DONE etc.)

Deactivation

User says /caveman off or "normal mode" → revert to standard response style, confirm:

Caveman mode OFF.

Relationship to Orchestrators

When sub-agents are dispatched inside orchestrators, the orchestrator may inject rules/core/terse-subagent-response.mdc into the dispatch prompt. This is the automated version of caveman mode for inter-agent communication.

Caveman mode (/caveman) is the user-facing, session-level version.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free