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.
npx skills add aidvizhhub/caveman-dvizh-skills --skill caveman-teachgit clone --depth 1 https://github.com/aidvizhhub/caveman-dvizh-skillsWrote 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.
[](https://agentmods.dev/skills/aidvizhhub/caveman-dvizh-skills/caveman-teach)<a href="https://agentmods.dev/skills/aidvizhhub/caveman-dvizh-skills/caveman-teach"><img src="https://agentmods.dev/badge/skills/aidvizhhub/caveman-dvizh-skills/caveman-teach/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.
<a href="https://agentmods.dev/skills/aidvizhhub/caveman-dvizh-skills/caveman-teach"><img src="https://agentmods.dev/badge/skills/aidvizhhub/caveman-dvizh-skills/caveman-teach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00276 | $0.01676 |
| Opus 5 | $0.00138 | $0.00838 |
| Sonnet 5 | $0.00055 | $0.00335 |
| Haiku 4.5 | $0.00028 | $0.00168 |
Grade A, and why
caveman-teach 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
caveman-teach (модуль полного канона)
🇬🇧 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.
⚡ 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: не отчитывайся — обучай (закон 40, авг 2026) — РЕШЕНО ✅
Канон (41 источник, кауфми 25 авг 2026: NN/g + ScienceDirect + timgraf mental models — «что юзер думает о системе»: цель — сблизить модель агента с моделью юзера, тогда интуитивно и без трения; Homan/Mueller/Klein/Litman (XAI measures) — хорошее объяснение = юзер достиг прагматического понимания, меряем его ментальную модель; Gerstenberg/Tenenbaum (MIT, intuitive theories, Oxford Handbook) — люди учатся через причинные модели и КОНТРФАКТУАЛЫ: «если бы не X — было бы Y»; Psychology Today contrast sets + teaching anticipation guide — предвидеть, ГДЕ запутается, и давать пары «похоже, но разное»; MIT Open Learning pre/post testing — показывать знания ДО и после (юзер видит, чему научился); NSW explicit teaching + Stanford concept mapping — явные связи со старым (schema); The Effortful Educator — конкретика сначала, абстракция потом; Springer/UNESCO AI-TEACH — агент-обучатель):
Смысл: юзер не должен «догадываться». После дела — маленький урок из нашего понимания ЕГО понимания: на его уровне, со связями и почему, с закрытыми (предвиденными) местами запутывания и наглядным ДО → ПОСЛЕ.
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.
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.
- 12d ago First seen · 99 lines · 276 tokens per session scan A 86bfc17ad773
caveman-teach is a skill published in the GitHub repository aidvizhhub/caveman-dvizh-skills (6 stars, last pushed 18d ago), licensed MIT. It adds 276 tokens to every session and 1,676 once invoked, about $0.0014 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.
Other skills, from other repositories
diffler
Generate and deliver a graded comprehension quiz from the current Git branch diff, either in the local terminal or through Google Forms. Use when a user asks to prove, test, or verify understanding of branch changes, a feature branch, or a pull request.
guided-learning
Turn-by-turn guided learning tutor. Use when the user asks to learn/explain a concept OR when they continue an ongoing lesson (answering the last question, asking for hints, saying “next”, choosing a branch). Teach in small chunks, keep a visible lesson TODO checklist, include a simple visual when useful, then end…
math-olympiad
Solve competition math problems (IMO, Putnam, USAMO, AIME) with adversarial verification that catches the errors self-verification misses. Activates when asked to 'solve this IMO problem', 'prove this olympiad inequality', 'verify this competition proof', 'find a counterexample', 'is this proof correct', or for any…
google-agents-cli-onboarding
Onboarding entrypoint for agents-cli in Agent Platform. It should be used when the user wants to "create a new agent", "develop an agent", "build an agent using ADK", "run the agent locally", "debug agent code", "test an agent", "evaluate an agent", "deploy an agent", "publish an agent", "monitor an agent", or needs…
practice-cognition
A method for testing ideas in practice, learning from the results, and improving the next attempt through repeated cycles.
scandinavia-transit
Search trains, buses, and ferries in Norway (Entur), Sweden (ResRobot), and Denmark (Rejseplanen). Intra-Scandinavia ground transport with schedules and Danish fare pricing.