caveman

caveman is a Context window & token budget skill for AI agents, published by dmae97 in the omk repository on GitHub. Skillspace rates caveman D (62/100) and it passed the safety scan; the rating is based on static analysis only.

Opt-in ultra-compressed OUTPUT style for OMK — port of JuliusBrussee/caveman (MIT, pin 0d95a81). Cuts output tokens ~65% (measured, range 22-87%) by speaking terse while keeping technical terms, code, errors, API names, CLI commands byte-exact. OUTPUT ONLY: 0% input/context/thinking reduction; adds ~1-1.5k input tokens per turn; net loss on terse Q&A or per-request/credit billing (Copilot etc). Six levels: lite / full (default) / ultra / wenyan-lite / wenyan-full / wenyan-ultra; switch via `/caveman <level>`. Trigger when user says "caveman", "/caveman", "talk like caveman", "brief mode", "less tokens", "be brief", "짧게 답해", "토큰 아껴", "간결하게". Opt-in ONLY (disable-model-invocation): never auto-fires; explicit invocation required. Code/commits/PRs stay normal style. Orthogonal to headroom (headroom = input/context compression; caveman = output prose).

Grade
D
Quality
62 / 100
Safety
Passed
GitHub stars
122

Unproven: rated by static analysis only, not yet compared head-to-head.

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubdmae97/omk

Our review

Architecture
84 / 100
Maturity
Structured: ships references or scripts
Security scan
Low-risk patterns
License
MIT
Adoption
Adopted by 0 other repositories, in 0 collections

What the scanner flagged

  • mentions secrets in text

Not checked yet

  • Category is a classifier prediction; no model has read this skill yet
  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Better-rated skills in Context window & token budget

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.