- name
SKILL.md
O arquivo da skill permanece no repositório do publicador.
Cole o comando copiado em um terminal. Ele instala este SKILL.md nesse agente.
npx skills add juliusbrussee/caveman --skill caveman-learn -a cursor -yCole o comando copiado em um terminal. Ele instala este SKILL.md nesse agente.
npx skills add juliusbrussee/caveman --skill caveman-learn -a claude-code -yCole o comando copiado em um terminal. Ele instala este SKILL.md nesse agente.
npx skills add juliusbrussee/caveman --skill caveman-learn -a codex -yCole o comando copiado em um terminal. Ele instala este SKILL.md nesse agente.
npx skills add juliusbrussee/caveman --skill caveman-learn -a grok -yEnvie a mensagem copiada em um chat do Grok Bot. O Bot busca este SKILL.md no GitHub e o adiciona às skills que todos os seus Bots compartilham.
Install this skill: https://github.com/juliusbrussee/caveman/tree/HEAD/skills/caveman-learnDo publicador
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:
Read the plan first:
Run: caveman learn report --json Parse the caveman.learn.v1 JSON. Show the Cave Score, its four components, and the ranked token sinks. For each sink state its class and basis. Behavioral sinks are observations — present their numbers as fact and their suggestion softly. Do not turn a behavioral finding into an imperative.
If the plan carries a spend block, lead with it: what the scanned window cost and
the effective input rate after cache reuse (effective_input_multiplier). Rules you
must not break when you show money:
unpriced is non-empty, say the total is a floor and name the excluded models.Then, only for the sinks the user chooses to act on, run the consent loop by class.
Before proposing a fix, you may run: caveman learn simulate <sink_id>. Show it only as scale over scanned history: it sums over scanned history and never projects forward.
REDUCIBLE (a heavy CLAUDE.md, a never-invoked skill):
RECURRING_CONTEXT (a heavy block re-established across sessions; fix kind cavemem_offload): move it into cavemem so it is recalled compactly instead of re-pasted every turn. The candidate carries only a LOCATOR — never the block body.
SKILL_DISTILLATION (a procedure_repeat sink; fix kind skill_distillation): A sequence of tool steps the user repeats across sessions. Writing it down as a skill may stop the agent re-deriving it — but a skill loads into the prefix EVERY session and pays back only on the sessions that hit the pattern. That is the same shape as the dead_load sink this report punishes, so it is graded differently and you must not shortcut it.
caveman learn experiment arm <label> off and work without it for a comparable
stretch. Each arm needs at least 5 sessions before any verdict exists.caveman learn experiment report <label>. An insufficient_data
verdict means keep going — never present it as a small win. A regressed verdict means
delete the skill; say so directly.MEMORY_HEALTH (memory_health::* sinks — the memory and rules doctor): audits of CLAUDE.md, CLAUDE.local.md, .claude/rules, AGENTS.md, GEMINI.md and Claude Code auto memory (MEMORY.md plus its topic files). Every item is one edit, one yes. Never delete memory content without the user's yes.
LOAD_BEARING: never touch. It appears in the report only so the score stays honest.
Reporting savings (caveman learn savings):
The ledger shows what applied fixes returned, grouped by HOW it was measured. When you present it, the grouping is not decoration — it is the claim's strength:
A holdout (controlled_holdout — the change on vs off on this machine) never appears in the ledger. It comes only from caveman learn experiment report ; present it as its own result, next to the ledger, never added to it. No command produces a counterfactual_replay row yet, so never claim one.
Three rules, all binding:
confounders on a row you are presenting as a win. They are
standing caveats, not fine print, and they exist precisely for the good-news case.attribution.provenance. intact means the file still carries the edit we
proposed. changed_since means someone edited past it and part of the delta is not
ours — say so. target_missing means the delta cannot be tied to the fix at all.
not_fingerprinted means the fix predates fingerprinting, so the edit's presence is
unverified. Experiments carry not_applicable: there is no single edit to check.
Never present a changed_since or target_missing row as a caveman result.A regression carries no dollar figure by design. Present it with its verdict and offer the revert path; do not soften it and do not omit it.
Binding rules:
spend, and priced savings rows) and only with
that block's own framing intact — window-bounded, never projected, never verified.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, wha
---name: caveman-learndescription: Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit…---# skills/caveman-learn/SKILL.mdVisão geral
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.
Perguntas frequentes
Baixe skills/caveman-learn/SKILL.md do publicador ou copie o caminho e abra o repositório. O PlugMCP lista a skill e não hospeda o arquivo.
O publicador o mantém em https://github.com/juliusbrussee/caveman.
Claude, Cursor, Codex e Grok Build conseguem ler um SKILL.md que você adiciona a partir do repositório do publicador. O Grok Bot o instala quando você envia em um chat o link da pasta da skill no GitHub.