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.
Security grade of this SKILL.md: CAUTION · how we grade
How to install caveman-learn
npx skills add JuliusBrussee/caveman --skill caveman-learn -a claude-code
The skills CLI copies this one skill into Claude Code (use -a for another agent). Or read its SKILL.md on GitHub.
What the SKILL.md says
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: cache_efficiency — 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. tool_output_portfolio — the call shapes that dominate context, ranked. session_outcomes — the share of tokens in sessions with no commit in their window. Correlational. Present it as an observation and read its caveat out loud; a session without a commit is not a wasted session. subagent_spend — the share of context that ran in subagents. Visibility only.
Other skills in JuliusBrussee/caveman
cavecrewWhen to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead…
cavemanTerse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief"…
caveman-commitWrite a Conventional Commits message compressed to intent only. Use for "write a commit", "commit message", /commit or /caveman-commit.
caveman-compressCompress 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…
caveman-discoverFind and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one bucket. Use for "discover work…
caveman-evidence-reviewRead-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings. Use when asked what Cav…
caveman-exploreRead-only repository explorer for cold-start orientation, broad cross-file localization, or when a direct search failed. Skip it when the e…
caveman-helpQuick-reference card for the three caveman skills and their commands. Trigger: /caveman-help or "caveman help".
caveman-manageInspect Caveman Cloud's experiment lifecycle and block unsafe execution. Use when asked to start, approve, cancel, promote or roll back a C…
caveman-optimizeTurn a Caveman optimization observation into an operator-chosen candidate with a paired baseline evaluation. Use when asked to inspect or e…
caveman-reviewCompressed code review - one line per finding with location, problem and fix. Use for /caveman-review, "review this PR", or "review the dif…
caveman-setupWire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change. Use for "set up caveman" or…
caveman-statsShow recorded output and cache-read token usage and mode attribution for the current Claude Code session, or locate the host's native usage…
investigate-firstDiagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needi…
lean-buildBuild feature work with high overbuilding risk. Use for new behavior, product slices, or integrations where repository reuse, strict scope,…
megacaveCaveman in Classical Chinese: 文言文 register, far fewer characters, technical terms verbatim. Invoke only with /megacave or /caveman wenyan.…
migrationImplement reversible compatibility-safe transitions. Use for schema, data, API, protocol, configuration, or dependency migrations requiring…
safe-refactorRestructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket…
surgical-patchFix bugs and small behavior changes at the narrowest responsible layer. Use when regression proof, preserved surrounding behavior, and task…
ultracaveCaveman at maximum compression: fragments, one word when one word is enough, each fact once. Invoke only with /ultracave or /caveman ultra.…