# JuliusBrussee/caveman

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

Repository: https://github.com/JuliusBrussee/caveman
Canonical: https://ross.abutalabs.com/products/caveman
Homepage: https://docs.caveman.so/docs/quickstart
Language: Go
License: NOASSERTION
License Family: other
Topics: ai, anthropic, caveman, claude, claude-code, llm, meme, prompt-engineering, skill, tokens
Last push: 2026-08-24T23:31:25+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 99, longevity 10
- inputs: {"age_days": 151, "days_push": 9, "days_rel": 10, "gap_med": 1.0, "n_releases_24m": 27}
- flags: young, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 101200, forks 5871 (observed 2026-08-28T04:12:23.678894+00:00)

## What it is
Caveman is an efficiency stack for AI coding agents that reduces token usage through a terse-writing skill, a payload-compression engine, and a local context memory layer. The MIT-licensed skill is a Markdown instruction file that makes agents drop filler while preserving code, commands, and error strings verbatim, with optional CLI tooling for profiling token spend.

## Use cases
- reduce llm api token costs
- make claude code use fewer tokens
- compress prompts sent to model apis
- profile where agent tokens are spent
- cut verbose ai agent output
- lower context window usage in coding agents
- save money on anthropic api bills

## When to choose
- you use Claude Code, Cursor, Codex, or similar coding agents and pay per token
- you want a zero-runtime, install-and-forget prompt skill that never alters code blocks or error strings
- you want local, recoverable payload compression with byte-exact restoration
- you want to profile which instructions and recurring context eat your token budget

## When to avoid
- you need terse output to remain fully human-readable prose
- your workflow depends on the agent's explanatory narration or hedged phrasing
- you require a fully open-source stack including the memory and cloud layers (those are BSL 1.1 or commercial)
- you use an agent host not covered by the supported profiles and cannot tolerate generic fallback wiring

## Facets
- artifact type: plugin
- maturity: active
- function: prompt-engineering, llm-inference, cli, developer-tools, caching
- domain: large-language-models, developer-tools
- platform: cli, cross-platform, python, go
- tags: token-optimization, claude-code, agent-skills, prompt-compression, context-compression, cost-reduction, open-core, ai-agents, command-line, nodejs

## Member repositories
- JuliusBrussee/caveman (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:23.678894+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:12:29.090659+00:00, confidence not recorded.
  - readme: https://github.com/JuliusBrussee/caveman (fetched 2026-08-28T04:12:23.678894+00:00, sha c9df04109c18)
  - homepage: https://docs.caveman.so/docs/quickstart (fetched 2026-08-28T17:33:43.875144+00:00, sha 46275227f763)
  - site_page: https://docs.caveman.so/ (fetched 2026-08-28T17:33:43.884227+00:00, sha 30c3cb3aee57)
  - site_page: https://docs.caveman.so/docs (fetched 2026-08-28T17:33:43.886234+00:00, sha e9f530b52ea9)
  - site_page: https://docs.caveman.so/docs/architecture (fetched 2026-08-28T17:33:43.887869+00:00, sha b11ab43942fb)
  - site_page: https://docs.caveman.so/docs/counting (fetched 2026-08-28T17:33:43.889488+00:00, sha ede0e0620617)
  - site_page: https://docs.caveman.so/docs/skill (fetched 2026-08-28T17:33:43.891027+00:00, sha 24c3002fcda5)
  - site_page: https://docs.caveman.so/docs/skill/learn (fetched 2026-08-28T17:33:43.892934+00:00, sha 52deee29fdb0)
  - site_page: https://docs.caveman.so/docs/skill/explore (fetched 2026-08-28T17:33:43.894619+00:00, sha 520994a4136e)
  - site_page: https://docs.caveman.so/docs/skill/profiles (fetched 2026-08-28T17:33:43.896128+00:00, sha 1df20c26ff50)
- Data as of 2026-08-30T08:39:29.467469+00:00.