caveman-learn
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.
Before you install
- Last update
- Files in folder
- 6
- Scripts
- Contains scripts. Review them before running.
- SKILL.md size
- 11 KB (about 2,879 tokens of context each time it loads)
- License
- Apache-2.0
- Source on GitHub
- JuliusBrussee/caveman
Skills are plain text instructions the agent follows, sometimes with scripts. Check the source, prefer repositories with many installs and stars, and read any script it ships.
Install
npx skills add JuliusBrussee/caveman@caveman-learnRuns in a terminal with Node.js 18 or newer. Add -y to skip the prompts and -g to install for every project instead of this one.
Install for your agent
npx skills add JuliusBrussee/caveman@caveman-learn --agent claude-code -y- Project install writes to
.claude/skills/caveman-learn- Global install writes to
~/.claude/skills/caveman-learn
Start a new session afterwards so the agent picks the skill up. In Claude Code you can also call it directly with /caveman-learn.
What it does
You are the Caveman Learn editing skill. The "caveman learn" command MEASURES where an agent's tokens go; you are the consent-gated half that turns its findings into edits — with the user approving each one. You never claim a saving you have not measured, and you never make the agent dumber. New sinks you may see, and what they are for: - cacheefficiency — what a million input tokens actually cost after cache reuse. It is a RATE the other sinks are priced at, not a volume; never add it to anything. - tooloutputportfolio — the call shapes that dominate context, ranked. - sessionoutcomes — the…
Excerpt from the skill's own SKILL.md. Read the full file on GitHub before installing: skills run with your agent's permissions.
Categories
Related skills
- caveman
JuliusBrussee/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".
- caveman
JuliusBrussee/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".
- caveman-commit
JuliusBrussee/caveman
Write a Conventional Commits message compressed to intent only. Use for "write a commit", "commit message", /commit or /caveman-commit.
- caveman-review
JuliusBrussee/caveman
Compressed code review - one line per finding with location, problem and fix. Use for /caveman-review, "review this PR", or "review the diff".
- caveman-compress
JuliusBrussee/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.
- caveman-compress
JuliusBrussee/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.