caveman-code

caveman-code is a skill for Claude Code, Codex from aidvizhhub/caveman-dvizh-skills. It costs 267 tokens per session (4,144 once invoked), scanned A, original, MIT.

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

In plain words
What is it for?
Use it when learning an unfamiliar tool, reading a codebase, choosing an implementation pattern, or adapting code from open-source projects.
Why use it?
It reduces guesswork and helps the agent reuse established patterns instead of creating unfamiliar or fragile solutions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions OpenCode.

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

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aidvizhhub/caveman-dvizh-skills/caveman-code
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.

agentmods badge for caveman-code

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.

agentmods 80×15 button for caveman-code

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00267 $0.04144
Opus 5 $0.00133 $0.02072
Sonnet 5 $0.00053 $0.00829
Haiku 4.5 $0.00027 $0.00414

Measured 11d ago against content hash 995dd2945df2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 11d 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.

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. 11d 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 (6 stars, last pushed 17d ago), licensed MIT. It adds 267 tokens to every session and 4,144 once invoked, about $0.0013 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 2026-08-31.

Related

Other skills, from other repositories