
Matt Pocock's `/caveman` skill (83.2K GitHub stars) puts Claude Code and 50+ other agents into persistent ultra-compressed output mode — cutting response tokens by 30–87% with a single trigger, while keeping all technical content intact.
.claude directory in late April 2026 as a GitHub repository called mattpocock/skills 1. The repo hit 83,200 stars within three weeks 2. Eighteen skills, all written as plain markdown, all installable with one npx command./caveman./caveman targets./caveman puts the agent into a persistent compressed-output mode. The SKILL.md definition is explicit about what gets dropped and what survives 4:a, an, the)just, really, basically, actually, simply)Sure!, Certainly, Of course, Happy to help)DB, auth, config, req, res[thing] [action] [reason]. [next step].Not: "Sure! I'd be happy to help you with that. The issue you're experiencing is likely caused by..."Yes: "Bug in auth middleware. Token expiry check use<not<=. Fix:"
"Inline obj prop -> new ref -> re-render. useMemo." 4
lite (drop filler, keep grammar), full (default fragment-style), and ultra (telegraphic abbreviations). Most users settle on full — ultra occasionally drops edge cases in complex explanations.npx). That's it.npx skills@latest add mattpocock/skills/setup-matt-pocock-skills in your selection — Pocock's README is direct about this: "Make sure you select /setup-matt-pocock-skills." 1/setup-matt-pocock-skills. It scaffolds per-repo config: issue tracker choice, triage label vocabulary, and domain doc layout 5.skills CLI (v1.5.7 as of May 15, 2026 6) supports 51+ agents with explicit flags, including Claude Code, Codex, Cursor, Cline, GitHub Copilot, Windsurf, Gemini CLI, OpenHands, Roo Code, and Aider.-g flag): installs under your home directory, available across all projects⚠️ Known issue (May 2026): User @skoshx reported the symlink step failing with the current Claude Code release —.claude/skillsdoesn't get created 7. If you hit this, switch to copy mode during installation. The/cavemanskill itself works normally once installed.

| Source | Measured savings | Methodology |
|---|---|---|
| mattpocock/skills README 1 | ~75% | Output tokens vs verbose baseline |
| JuliusBrussee/caveman benchmark suite 8 | 65% average (range: 22–87%) | 10 real dev tasks, Claude Code |
| Community independent testing 3 | 30–50% | Various tasks, mixed agents |
| Towards AI (10-prompt sample, Opus 4.7) 2 | 71% prose tokens | Opus 4.7, Q&A tasks |
/caveman doesn't compress. Thinking/reasoning tokens and code generation are completely untouched 8. The JuliusBrussee README puts it plainly: "Caveman only affects output tokens — thinking/reasoning tokens untouched. Caveman no make brain smaller. Caveman make mouth smaller." 8
/caveman is less about cost and more about speed and readability: shorter responses are faster to generate and faster to scan. DevTalk reviewer xiji2646-netizen, after one week of daily use: "/caveman — if you already know what you want, this cuts agent verbosity to near zero. Underrated." 9caveman-compress tool — which rewrites your CLAUDE.md into caveman-speak, cutting an average of 46% of input tokens across tested memory files 8 — targets the input side of the budget where the real money is./caveman creates more friction than it saves:/tdd. GitHub Issue #111 documents that activating both skills simultaneously causes the agent to skip the RED phase of the red-green-refactor cycle and go directly to implementation. The context window shows terse like caveman as the causal indicator. Don't combine them 10.--with-init) to hold the mode reliably 3.ultra mode occasionally drops edge cases and important caveats. For debugging sessions where the why behind an answer matters as much as the what, stick with full or turn caveman off entirely 8.npmjs.com
This story was produced automatically by a channel. One sentence is all it takes for Neodrop to keep producing for you.