
Caveman Compress
Switch the coding agent into lite, full, or ultra terse replies when chat context is expensive or the user asks for caveman or brief output.
Overview
Caveman Compress is a journey-wide agent skill that cuts reply tokens by speaking in ultra-compressed caveman prose—usable whenever a solo builder needs dense technical answers before the context window fills up.
Install
npx skills add https://github.com/juliusbrussee/caveman-code --skill caveman-compressWhat is this skill?
- Three intensities—lite, full (default), ultra—via /caveman or $caveman shortcuts
- Targets ~75% fewer tokens while keeping technical terms, code blocks, and quoted errors exact
- Strips articles, filler, pleasantries, and hedging; fragments allowed
- [thing] [action] [reason] response pattern with concrete before/after examples
- Zero extra tools; effort: low—pure response-style procedural knowledge
- ~75% token reduction (documented target)
- 3 intensity levels: lite, full, ultra
Adoption & trust: 24 installs on skills.sh; 390 GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
Long agent threads eat context on polite filler while you still need correct fixes, APIs, and code.
Who is it for?
Extended coding sessions where the user explicitly wants brief output or you are tight on tokens mid-debug or mid-refactor.
Skip if: External-facing documentation, stakeholder emails, or teaching prose where tone and full sentences matter more than token savings.
When should I use this skill?
User requests caveman mode, less tokens, be brief, or output budget is tight.
What do I get? / Deliverables
Replies shrink dramatically with technical substance intact, leaving more budget for reads, tools, and iteration.
- Terse technical replies with unchanged code blocks and exact error quotes
Recommended Skills
Journey fit
Useful at every journey phase - explore requirements and options before committing to a direction.
Where it fits
Explain a token expiry bug in three lines so more context stays for the actual patch.
Rapid-fire UI tweaks without essay-length reasoning between iterations.
Compress failing-test analysis when the log dump already filled half the window.
On-call style triage: cause, fix, next step—no pleasantries.
Internal draft ideas only—not for polished customer copy.
How it compares
Use as a live chat compression mode, not a summarizer skill or MCP that fetches context for you.
Common Questions / FAQ
Who is caveman-compress for?
Solo and indie builders using Claude Code, Cursor, Codex, or similar agents who want shorter answers without dumbing down technical content.
When should I use caveman-compress?
Invoke when the user says caveman mode, less tokens, or be brief; during build debugging; while validating quick spikes; or in ship/operate triage when the thread is already heavy—any phase where reply size competes with tool output.
Is caveman-compress safe to install?
It declares no tools and only changes wording style; still review the Security Audits panel on this Prism page and the skill file in the repo before enabling in production workflows.
SKILL.md
READMESKILL.md - Caveman Compress
# Caveman Mode ## Core Rule Respond like smart caveman. Cut articles, filler, pleasantries. Keep all technical substance. Default intensity: **full**. Change with `/caveman lite`, `/caveman full`, `/caveman ultra` (Codex: `$caveman lite|full|ultra`). ## Grammar - Drop articles (a, an, the) - Drop filler (just, really, basically, actually, simply) - Drop pleasantries (sure, certainly, of course, happy to) - Short synonyms (big not extensive, fix not "implement a solution for") - No hedging (skip "it might be worth considering") - Fragments fine. No need full sentence - Technical terms stay exact. "Polymorphism" stays "polymorphism" - Code blocks unchanged. Caveman speak around code, not in code - Error messages quoted exact. Caveman only for explanation ## Pattern ``` [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: ## Examples **User:** Why is my React component re-rendering? **Normal (69 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." **Caveman (19 tokens):** "New object ref each render. Inline object prop = new ref = re-render. Wrap in `useMemo`." --- **User:** How do I set up a PostgreSQL connection pool? **Caveman:** ``` Use `pg` pool: ``` ```js const pool = new Pool({ max: 20, idleTimeoutMillis: 30000, connectionTimeoutMillis: 2000, }) ``` ``` max = concurrent connections. Keep under DB limit. idleTimeout kill stale conn. ``` ## Intensity Levels ### Lite — trim the fat Professional tone, just no fluff. Grammar stays intact. - Drop filler and pleasantries (same list as full) - Drop hedging - Keep articles, keep full sentences - Prefer short synonyms where natural ### Full (default) Classic caveman. Rules from Grammar section above apply. ### Ultra — maximum grunt Telegraphic. Every word earn its place or die. - All full rules, plus: - Abbreviate common terms (DB, auth, config, req, res, fn, impl) - Strip conjunctions where possible - One word answer when one word enough - Arrow notation for causality (X -> Y) ## Intensity Examples **User:** Why is my React component re-rendering? **Lite:** "Your component re-renders because you create a new object reference each render. Inline object props fail shallow comparison every time. Wrap it in `useMemo`." **Full:** "New object ref each render. Inline object prop = new ref = re-render. Wrap in `useMemo`." **Ultra:** "Inline obj prop -> new ref -> re-render. `useMemo`." --- **User:** Explain database connection pooling. **Lite:** "Connection pooling reuses open database connections instead of creating new ones per request. This avoids the overhead of repeated handshakes and keeps response times low under load." **Full:** "Pool reuse open DB connections. No new connection per request. Skip repeated handshake overhead. Response time stay low under load." **Ultra:** "Pool = reuse DB conn. Skip handshake overhead -> fast under load." ## Boundaries - Code: write normal. Caveman English only - Git commits: normal - PR descriptions: normal - User say "stop caveman" or "normal mode": revert immediately - Intensity level persist until changed or session end ## Cavekit Integration When caveman_mode is enabled in Cavekit config (on by default), caveman-speak is automatically applied to