What is caveman-code?

A coding method that starts by studying official examples and existing high-quality code before writing something new.

Use it when learning an unfamiliar tool, reading a codebase, choosing an implementation pattern, or adapting code from open-source projects.

It reduces guesswork and helps the agent reuse established patterns instead of creating unfamiliar or fragile solutions.

caveman-code — Skill for Claude Code and Codex by aidvizhhub

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 aidvizhhub/caveman-dvizh-skills --skill caveman-code

Clone the repo

git clone --depth 1 https://github.com/aidvizhhub/caveman-dvizh-skills

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/aidvizhhub/caveman-dvizh-skills/caveman-code/github.svg)](https://agentmods.dev/skills/aidvizhhub/caveman-dvizh-skills/caveman-code)

Your own site

<a href="https://agentmods.dev/skills/aidvizhhub/caveman-dvizh-skills/caveman-code"><img src="https://agentmods.dev/badge/skills/aidvizhhub/caveman-dvizh-skills/caveman-code/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/aidvizhhub/caveman-dvizh-skills/caveman-code"><img src="https://agentmods.dev/badge/skills/aidvizhhub/caveman-dvizh-skills/caveman-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 267 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,144 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 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.

Model	Per session	Once invoked
Fable 5.1	$0.00267	$0.04144
Opus 5.5	$0.00107	$0.01658
Sonnet 5.5	$0.00053	$0.00829
Haiku 4.5	$0.00027	$0.00414

Measured 2mo ago against content hash 995dd2945df2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

caveman-code 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 2mo 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-code/SKILL.md · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

caveman-code — изучай, как пишут код: примеры, чужой код, советы (авг 2026)

🇬🇧 English instructions: references/EN.md — полный перевод тела.

Это часть устава пещерника. Полный канон целиком — скилл caveman-canon. Всё ниже — выдержки из BRO.md один в один (без сокращений).

⚡ ЗАКОН СКИЛЛОВ (авг 2026): на КАЖДЫЙ промт грузи как можно больше скиллов племени — МИНИМУМ 6, лучше ВСЕ 17 (canon + conclusion + teach + cheat + advise + prevent + verify + loop + kill + code + style + think + research + run + diagnose + save + desktop). Один скилл = одна грань канона; без полного груза решение кривое, охота слепая. БОЛЬШАЯ задача = ЦИКЛ ПЛЕМЕНИ (скилл caveman-loop): 8 шагов, пока «готово» не доказано фактами, кап 3 итерации → стоп и отчёт.

⚡ ДОКИ ЖЕЛЕЗНО (закон 25, авг 2026): инструмент/флаг незнакомый → СНАЧАЛА официальная дока + man + --help (RTFM-канон: первая линия, не запасная; −40% времени, −70% ошибок; официальная дока раньше чужого веба). Прогрессивно: --help → man → полная дока/вики → потом чужое; сверять с установленной ВЕРСИЕЙ. Пример: ffmpeg — man ffmpeg + ffmpeg-all.html.

СУТЬ: пиши код, как это делает индустрия (закон 26, авг 2026) — РЕШЕНО ✅

Канон (47 источников, кауфми 24 авг 2026: algocademy art of code reading, chriswenchen reading-code — 80% времени = чтение чужого кода, 20% = писание; tutorialspoint code reading — лучшие пишут после чтения лучших; towardsdatascience 4-шаговое чтение; baransel уроки из чужого кода — паттерны впитываются сами; shiftmag — 51% разработчиков СБИРАЮТ из примеров, а не пишут с нуля; AdaptivePaste arxiv 2205.11023 — copy-paste с адаптацией = 85.9% точности; Example-Driven Development arxiv 2409.00514 + Oscar Nierstrasz — пример = спецификация; monodot/awesome-codebases — реальные codebase для учёбы; GitHub blog — как инженеры изучают codebases; Kent C. Dodds how I learn an open source codebase; charlax professional- programming; DataCamp/dev.to/educative — код-советы):

ГЛАВНОЕ: НЕ писать с нуля и НЕ гуглить сниппет вслепую. СНАЧАЛА смотреть, как это делает индустрия — готовый рабочий код, примеры из официальной доки, паттерны из открытых проектов. Потом ПОНЯТЬ и адаптировать под свою задачу. И только если индустрия не сделала — писать самому, по советам ниже.

Read the full file on GitHub · 212 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

references/EN.md 11 KB

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.

2mo ago First seen · 212 lines · 267 tokens per session scan A 995dd2945df2

Subscribe to this mod's changes

caveman-code is a skill published in the GitHub repository aidvizhhub/caveman-dvizh-skills (7 stars, last pushed 2mo ago), licensed MIT. It adds 267 tokens to every session and 4,144 once invoked, about $0.0011 per session on Opus 5.5. 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 2026-08-31.

Building agents Claude Code agent-skills ai-agents opencode skills

caveman-code next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
caveman-codeaidvizhhub/caveman-dvizh-skills	Skill	7	2mo ago	MIT	A	267	Claude Code, Codex
seats-aeroborski/travel-hacking-toolkit	Skill	906	2d ago	MIT	A	78	Claude Code
biltborski/travel-hacking-toolkit	Skill	906	2d ago	MIT	A	44	Claude Code
round-the-worldborski/travel-hacking-toolkit	Skill	906	2d ago	MIT	A	51	Claude Code
scandinavia-transitborski/travel-hacking-toolkit	Skill	906	2d ago	MIT	A	49	Claude Code
southwestborski/travel-hacking-toolkit	Skill	906	2d ago	MIT	A	40	Claude Code
status-matchborski/travel-hacking-toolkit	Skill	906	2d ago	MIT	A	48	Claude Code