caveman is a skill and proxy for coding agents that shortens unnecessary explanatory prose so agents use fewer tokens while leaving code, commands, paths, and error messages unchanged. It is for people using coding agents who want terse responses and lower token use, including with Claude-based workflows. The catalogue entries contain its skills, commands, agents, instructions, and plugins.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/JuliusBrussee/cavemanWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/juliusbrussee/caveman/caveman-compress)<a href="https://agentmods.dev/commands/juliusbrussee/caveman/caveman-compress"><img src="https://agentmods.dev/badge/commands/juliusbrussee/caveman/caveman-compress/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/juliusbrussee/caveman/caveman-compress"><img src="https://agentmods.dev/badge/commands/juliusbrussee/caveman/caveman-compress.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00012 | $0.00163 |
| Opus 5.5 | $0.00005 | $0.00065 |
| Sonnet 5.5 | $0.00002 | $0.00033 |
| Haiku 4.5 | $0.00001 | $0.00016 |
Grade A, and why
caveman-compress scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Compress the file at: $ARGUMENTS
Run the caveman-compress skill against the given filepath. The skill rewrites
prose into terse caveman style — drops articles, filler, hedging — while
preserving code blocks, inline code, URLs, file paths, commands, and markdown
structure exactly. Original is backed up as <file>.original.md before
overwrite.
Only compress natural-language files (.md, .txt, .typ, .tex,
extensionless). Refuse source/config files (.py, .js, .ts, .json,
.yaml, .toml, .sh, etc.). Never compress an existing *.original.md
backup.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 16 lines · 12 tokens per session scan A c7d60edfbbba
caveman-compress is a command published in the GitHub repository JuliusBrussee/caveman (113,062 stars, last pushed 2d ago), licensed Apache-2.0. It adds 12 tokens to every session and 163 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
aside
Answer a quick side question without interrupting or losing context from the current task. Resume work automatically after answering.
plan
Create a phased implementation plan before writing any code.
prune-learnings
Manual command to invoke the pruning script for cleaning up old learnings.
pull-learnings
Pulls shared organization patterns into local org-patterns.toon.
recall-loop
Periodic memory digest — designed for use with Claude Code's /loop scheduler. Shows recent memories and pending to-dos in a compact, scannable format.
cwb-focus
A music-search helper for quiet instrumental audio used for concentration and deep work.