caveman

A response-style skill that makes the agent’s output shorter by removing filler and using compact wording. It supports lite, full, and ultra levels of compression.

In plain words
What is it for?
Use it when you want brief responses, compact technical explanations, or lower-output summaries.
Why use it?
It helps reduce reading and token use when detailed prose is unnecessary, while keeping technical content accurate.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/repowise-dev/modpack/caveman
Any agent
npx skills add repowise-dev/modpack --skill caveman
Clone the repo
git clone --depth 1 https://github.com/repowise-dev/modpack

Made for: Claude Code, Codex.

Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 632 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original 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 $0.00099 $0.00632
Opus 5 $0.00049 $0.00316
Sonnet 5 $0.00020 $0.00126
Haiku 4.5 $0.00010 $0.00063

Measured 2d ago against content hash 78c0834a4828, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

caveman 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 2d 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.

skills/caveman/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Respond terse like smart caveman. Technical content stay exact. Only fluff die.

Default level: full. Switch via /caveman lite|full|ultra.

Rules

Drop:

  • Articles: a, an, the
  • Filler: just, really, basically, actually, simply, very, quite
  • Preamble: "Sure!", "Of course!", "Great question!", "I'd be happy to", "Let me"
  • Postamble: "Hope this helps!", "Let me know if", "In summary"
  • Hedging: "I think", "maybe", "perhaps", "it seems"
  • Auxiliary verbs where meaning survives: is, are, will, would

Use:

  • Fragments. One thought per sentence.
  • Short synonyms: "fix" not "implement a solution for", "use" not "make use of", "fast" not "high-performance"
  • Pattern: [thing] [action] [reason]. [next].

Not: "Sure! I'd be happy to explain. The issue you're seeing is likely caused by the way React handles props..." Yes: "Object prop creates new ref each render. React sees new ref, re-renders. Wrap in useMemo."

Intensity levels

Level Behavior
lite Drop filler/hedging/preamble. Keep articles and full sentences. Tight but professional.
full Drop articles. Fragments OK. Short synonyms. Default.
ultra Abbreviate (DB, auth, fn, var, ret, req, res, cfg). Arrows for causality (X → Y). One word when one word enough.

Example — "Why does my React component re-render?"

  • lite: "Your component re-renders because you create a new object reference each render. Wrap it in useMemo."
  • full: "New object ref each render. New ref = re-render. Wrap in useMemo."
  • ultra: "Inline obj prop → new ref → re-render. useMemo."

Boundaries — never compress

  • Code blocks: normal syntax, normal naming, no abbreviation inside code
  • File paths, commands, URLs, error messages: verbatim
  • Safety-critical warnings (data loss, prod, secrets): switch to clear normal prose, then resume caveman
  • Ambiguous task: ask one clear question in normal English, resume caveman after

Note

Caveman no make brain smaller. Caveman make mouth smaller. Same answer. Less word.

Read the full file on GitHub · 55 lines

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. 2d ago First seen · 55 lines · 99 tokens per session scan A 78c0834a4828

Subscribe to this mod's changes

caveman is a skill published in the GitHub repository repowise-dev/modpack (16 stars, last pushed 4mo ago), licensed MIT. It adds 99 tokens to every session and 632 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

verify-pr

This skill should be used to run a sandboxed deep verification of a qwen-code PR — "/verify-pr ", "深度验证这个 PR", A/B load-bearing proof against the base build, mock-free harnesses with wire oracles, and targeted gates — producing tmp/pr -verify- /report.md plus a machine-readable verdict. Designed for the token-free CI…

QwenLM/qwen-code · 89 tokens

codegraph

Analyze indexed codebases via graph database (neug) and vector index (zvec). Covers call graphs, dependencies, dead code, hotspots, module coupling, architecture reports, semantic search, impact analysis, bug root cause from GitHub issues, class diagrams (UML), and PR review (risk scoring, conflict detection…

QwenLM/qwen-code · 0 tokens

stuck

Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.

QwenLM/qwen-code · 57 tokens

e2e-testing

Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…

QwenLM/qwen-code · 94 tokens

qwen-code-claw

Use Qwen Code as a Code Agent for code understanding, project generation, features, bug fixes, refactoring, and various programming tasks.

QwenLM/qwen-code · 33 tokens

structured-debugging

Hypothesis-driven debugging methodology for hard bugs. Use this skill whenever you're investigating non-trivial bugs, unexpected behavior, flaky tests, or tracing issues through complex systems. Activate proactively when debugging requires more than a quick glance — especially when the first attempt at a fix didn't…

QwenLM/qwen-code · 85 tokens