github.com/JuliusBrussee/caveman @v2.3.1@v2.2.0@v2.0.0@v1.10.0@v1.9.1@v1.9.0@bin-v1.1.1@bin-v1.1.0

why use many token when few do trick

Original skill made agents say less. Caveman 2 makes them read less too.

33.2% fewer provider-reported input tokens in a pinned Claude Code benchmark. benchmark_counterfactual

Keep your agent. Brain big. Context small.

See it · Install · Learn · Proxy · Pixel · Wrap · Docs · License

See it

🗣️ Normal agent — 69 tokens	Caveman agent — 19 tokens
> The reason your React component is re-rendering is likely because you're creating a new object reference on each render cycle. When you pass an inline object as a prop, React's shallow comparison sees it as a different object every time, which triggers a re-render. I'd recommend using useMemo to memoize the object.	> New object ref each render. Inline object prop = new ref = re-render. Wrap in `useMemo`.

Install

Two products. Pick one or both.

1 · Save input — Caveman Proxy shrinks what your agent reads before every provider call, with byte-exact recovery. BSL-1.1 runtime, MIT CLI.

npm install -g @caveman-ai/cli && caveman setup --install
caveman claude        # or codex · gemini · aider · opencode · hermes · openclaw

2 · Save output — the skill, the original. Your agent answers in tight caveman-speak while code, commands, and errors stay exact. MIT, 30+ agents.

npx skills add JuliusBrussee/caveman

Other ways in — full installer with hooks, Windows, one agent only

The full installer also wires the Claude Code hooks and statusline, finds every supported agent on your machine, and is safe to rerun (Node.js 18+):

curl -fsSL https://raw.githubusercontent.com/JuliusBrussee/caveman/v2.3.1/install.sh | bash

Windows (PowerShell 5.1+):

irm https://raw.githubusercontent.com/JuliusBrussee/caveman/v2.3.1/install.ps1 | iex

One agent only:

# Claude Code
claude plugin marketplace add JuliusBrussee/caveman && claude plugin install caveman@caveman

# Gemini CLI
gemini extensions install https://github.com/JuliusBrussee/caveman

# Codex, Cursor, Windsurf, Cline, and other skills-compatible agents
npx skills add JuliusBrussee/caveman --skill '*' -a codex --yes  # replace codex with your agent profile

Full 30+ agent matrix, dry run, flags, verification, and uninstall: INSTALL.md.

Where your tokens go

You have months of agent history on disk. caveman learn reads it and scores your setup. Local, read-only, no account.

caveman learn             # Claude Code + Codex + Gemini CLI + opencode; aider via CAVEMAN_AIDER_ROOT

The report shows your Cave Score, every token sink ranked by flow with a one-line fix behind each row, how deep each session ran into its context window, a replay of what the fixes would have cut from your past sessions, and a list-price illustration of what the ranked sinks cost over 30 days.

caveman learn implement   # hand the plan to Claude Code or Codex

learn implement opens your own agent with the plan and the caveman-learn skill, which instructs it to propose each fix as a diff, apply only on your yes, re-measure, and revert anything that did not lower tokens per turn. Caveman never makes your agent dumber to make it cheaper.

Caveman Proxy

One command wraps your agent and routes provider traffic through a local proxy powered by Caveman Engine. In a pinned 54-run Claude Code benchmark it used 33.2% fewer provider-reported input tokens than direct Claude Code while passing all 18 exact-answer checks. Method, per-case results, and limits. benchmark_counterfactual

No code change, no Caveman backend: the proxy forwards each request to your chosen provider, and recovery copies stay on your disk. Claude Pro/Max OAuth credentials pass through to Anthropic as-is.

caveman claude             # Claude Code + Codex + Gemini CLI + opencode; aider via CAVEMAN_AIDER_ROOT

What the engine does to a payload — detect() types each payload, then routes it to a compressor that keeps what answers depend on:

contextwindow.Pack() additionally fits candidate context into a token budget by BM25 relevance, recency, and error signal, returned in original order so chronology survives.

The same engine powers a set of verbs:

caveman learn                   # scan your real agent history → score + ranked token sinks
caveman learn implement         # fix the findings with your own agent, consent-gated per edit
caveman explore install         # read-only FastContext subagent: finds code as path:line
caveman shrink -- pnpm test     # compress noisy command output, byte-exact recoverable
caveman browse <url>            # local Chrome over a compressed a11y tree
caveman mem remember|recall     # durable memory; `mem recover <handle>` = original bytes
caveman trial -- claude         # A/B a real session, then `trial report`
caveman toon encode|decode      # the TOON re-encoder, standalone
caveman stats                   # what caveman actually did, by content type

The MCP server exposes five tools to any MCP host: caveman_compress, caveman_retrieve, caveman_stats, caveman_toon_encode, caveman_toon_decode.

On browse (needs Chrome): a focused query against a 200-row operations table costs 121 tokens, 129.8× smaller than the Playwright ARIA baseline of 15,704. Full method: browse/BENCHMARK.md.

Pixel mode

Skills as images

Full circle: the engine now compresses the thing caveman started as. Every fat skill you install re-loads its whole prompt body on every invocation, and you pay that tax forever. caveman convert renders each installed SKILL.md body to PNG pages in place. Frontmatter stays text, so discovery and triggering work exactly as before; the model reads the body as an image.

caveman convert --dry-run        # every installed skill, with the token math, no writes
caveman convert --agent claude   # convert the profitable ones
caveman convert --revert         # byte-identical restore from SKILL.orig.md

Measured on the caveman skill itself: 1,069 → 415 est. tokens, −61%. Convert only fires when pages beat the text; any failure leaves the skill byte-identical and names the gate that said no. New skills installed through caveman skills install auto-pixel by default (--no-pixel to opt out).

The skill

The original, and still the fastest way to feel caveman. MIT forever. Works in Claude Code, Codex, Gemini, Cursor, Windsurf, Cline, Copilot, and 30+ other agents.

Type /caveman if your agent does not activate it automatically. Switch with /caveman lite|full|ultra|wenyan-lite|wenyan-full|wenyan-ultra; turn it off with /caveman off or normal mode.

One install also brings the small tools:

[!IMPORTANT] Honest number warning. The skill only shrinks output tokens. Input and reasoning tokens are untouched, and the skill itself adds ~1–1.5k input tokens per turn. Whole-session savings run smaller than the output number, and on already-terse workloads they can go net-negative. The real win is readability and speed; cost savings are the bonus. When caveman wins, when it loses, and how to measure it yourself: docs/HONEST-NUMBERS.md.

Wrap any agent

caveman <agent> wraps eight agents natively. Adding one is a data change, a single JSON profile in agents/profiles/, no code.

Wrap never edits your own config files. Real sessions round-trip in record mode, tested against Hermes v0.18.0, OpenClaw 2026.6.11, and Pi 0.84.2.

Not on the list? Point any provider SDK or framework (Vercel AI SDK, LangChain, LiteLLM, OpenAI Agents, CrewAI, PydanticAI) at the local proxy with a baseURL swap: integrations/recipes/.

The default wrap hands the agent the whole loadout: the five caveman MCP tools, the browse MCP server when Chrome resolves, command-output shrink through a real hook on Claude, opencode, Gemini, Hermes, and OpenClaw (Codex gets an hone