caveman-token-reduction

caveman-token-reduction is a skill for Claude Code from UitbreidenOS/UitKit. It costs 35 tokens per session (1,666 once invoked), scanned A, original, no licence file.

A communication style that uses short responses and minimal output to save context space during coding-agent sessions.

In plain words
What is it for?
Use it for context-heavy sessions where compact communication matters.
Why use it?
It reduces unnecessary text when the session has limited context or needs terse acknowledgments.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the uitkit-ai-engineering plugin — 143 skills shipped together

Good fit Use it for context-heavy sessions where compact communication matters.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/uitbreidenos/uitkit/caveman-token-reduction
Install

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.

Any agent
npx skills add UitbreidenOS/UitKit --skill caveman-token-reduction
Clone the repo
git clone --depth 1 https://github.com/UitbreidenOS/UitKit

Made for: Claude Code.

Or install uitkit-ai-engineering, the plugin that ships this one along with the rest of its 143 skills.

Wrote 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.

agentmods badge for caveman-token-reduction

README.md
[![agentmods](https://agentmods.dev/badge/skills/uitbreidenos/uitkit/caveman-token-reduction/github.svg)](https://agentmods.dev/skills/uitbreidenos/uitkit/caveman-token-reduction)
Your own site
<a href="https://agentmods.dev/skills/uitbreidenos/uitkit/caveman-token-reduction"><img src="https://agentmods.dev/badge/skills/uitbreidenos/uitkit/caveman-token-reduction/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.

agentmods 80×15 button for caveman-token-reduction

Your own site · 80×15
<a href="https://agentmods.dev/skills/uitbreidenos/uitkit/caveman-token-reduction"><img src="https://agentmods.dev/badge/skills/uitbreidenos/uitkit/caveman-token-reduction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,666 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.01666
Opus 5 $0.00017 $0.00833
Sonnet 5 $0.00007 $0.00333
Haiku 4.5 $0.00003 $0.00167

Measured 8d ago against content hash 3ccb5e365d39, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

caveman-token-reduction 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 8d 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.

plugins/uitkit-ai-engineering/skills/caveman-token-reduction/SKILL.md · 198 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

Changes

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.

  1. 8d ago First seen · 198 lines · 35 tokens per session scan A 3ccb5e365d39

Subscribe to this mod's changes

caveman-token-reduction is a skill published in the GitHub repository UitbreidenOS/UitKit (14 stars, last pushed 2mo ago), with no licence file. It adds 35 tokens to every session and 1,666 once invoked, about $0.0002 per session on Opus 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.