# Lower Agent Token Cost

Applies approved fixes that cut an agent's token spend from a learn report.

- Repository: https://github.com/JuliusBrussee/caveman (116680 stars)
- Category: AI and agents
- License: Apache-2.0
- Last updated: 2026-11-01
- Runs scripts: yes, review before use

## Install

Claude Code: `npx skills add JuliusBrussee/caveman --skill caveman-learn -g -a claude-code -y`
Codex: `npx skills add JuliusBrussee/caveman --skill caveman-learn -g -a codex -y`
Cursor: `npx skills add JuliusBrussee/caveman --skill caveman-learn -g -a cursor -y`
Gemini CLI: `npx skills add JuliusBrussee/caveman --skill caveman-learn -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add JuliusBrussee/caveman`

## Description

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.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

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. Do not
  turn it into advice to spawn fewer subagents.
- procedure_repeat:*, a distillation candidate. See SKILL_DISTILLATION below.

Read the plan first:

1. 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.

The rest: https://github.com/JuliusBrussee/caveman/blob/HEAD/skills/caveman-learn/SKILL.md