Skip to content
mcp/skillhub

Agent Skill

Caveman Learn skill

caveman-learnJuliusBrussee/cavemanskills/caveman-learn/SKILL.md

Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned. Use when asked to lower an agent's token cost, what caveman has saved, to trim a heavy CLAUDE.md, or to offload re-pasted context into cavemem.

114kApache-2.0

always on

76 tokname + description

once used

2,658 tokSKILL.md body

bundled files

52 scripts

installs

102kskills.sh

Install the Caveman Learn skill

Skills CLI (Claude Code, Codex, Cursor and others)

npx skills add https://github.com/JuliusBrussee/caveman --skill caveman-learn

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/JuliusBrussee/caveman.git /tmp/caveman
mkdir -p ~/.claude/skills
cp -R /tmp/caveman/skills/caveman-learn ~/.claude/skills/caveman-learn

For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.

What it costs your context

Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.

WhenWhat loadsCost
Every sessionName and description76 tok
When the agent uses itThe SKILL.md instructions2,658 tok
Only if opened5 bundled files (7 KB)varies

Until it is used, caveman-learn costs about 18× less than the median MCP server we measured (1,362 tokens on every turn). Installing all 28 skills from JuliusBrussee/caveman would load 1,303 tokens of descriptions. Skills vs MCP study

Checks

  • Ships scripts the agent can run. Read them before installing.

Checked 2026-10-22 · method

More skills from JuliusBrussee/caveman

All skills in this repo
  1. cavemanJuliusBrussee/caveman

    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".

    586k62 tok idle · 1,086 in use
  2. caveman-commitJuliusBrussee/caveman

    Write a Conventional Commits message compressed to intent only. Use for "write a commit", "commit message", /commit or /caveman-commit.

    411k38 tok idle · 564 in use
  3. caveman-reviewJuliusBrussee/caveman

    Compressed code review - one line per finding with location, problem and fix. Use for /caveman-review, "review this PR", or "review the diff".

    407k40 tok idle · 585 in use
  4. caveman-compressJuliusBrussee/caveman

    Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup. Sends the file's text to the configured model provider. Trigger: /caveman-compress.

    407k754 tok idle · 1,247 in use
  5. caveman-helpJuliusBrussee/caveman

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

    398k32 tok idle · 667 in use
  6. cavecrewJuliusBrussee/caveman

    When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inline or using `Explore`. Their output is compressed, so main context lasts longer.

    354k65 tok idle · 869 in use
  7. caveman-statsJuliusBrussee/caveman

    Show recorded output and cache-read token usage and mode attribution for the current Claude Code session, or locate the host's native usage report. Trigger: /caveman-stats.

    353k42 tok idle · 331 in use
  8. caveman-statsJuliusBrussee/caveman

    Show recorded output and cache-read token usage and mode attribution for the current Claude Code session, or locate the host's native usage report. Trigger: /caveman-stats.

    353k42 tok idle · 352 in use