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-verifygit 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-verify)<a href="https://agentmods.dev/skills/aidvizhhub/caveman-dvizh-skills/caveman-verify"><img src="https://agentmods.dev/badge/skills/aidvizhhub/caveman-dvizh-skills/caveman-verify/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-verify"><img src="https://agentmods.dev/badge/skills/aidvizhhub/caveman-dvizh-skills/caveman-verify.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 | $0.00255 | $0.03023 |
| Opus 5 | $0.00128 | $0.01511 |
| Sonnet 5 | $0.00051 | $0.00605 |
| Haiku 4.5 | $0.00026 | $0.00302 |
Grade A, and why
caveman-verify 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
caveman-verify (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. 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: дотошность = дешёвая страховка (закон 32, авг 2026) — РЕШЕНО ✅
Канон (41 источник, кауфми 24 авг 2026: Google SRE Book/Workbook + Google Cloud Well-Architected — blameless postmortem: критерии ДО инцидента, таймлайн из объективных источников, 5 Whys от симптома к системному фактору, action items с владельцем и сроком, «incidents expose the gap between how you think systems work and how they actually work», «filing the document is not the deliverable — action items are»; whytrace/em-tools/Atlassian/Rootly/beefed — поверхностный фикс = повторные падения; Braintrust/Arize/Microsoft/Langfuse agent observability — снимать каждый шаг: вызовы тулов, переходы состояний, память, ретраи, «final response hides the path», «wrong tool/arguments/drifted plan»; processcamp/visual-paradigm/thinkcloudly as-is vs to-be gap analysis — зафиксируй КАК ЕСТЬ, сравни с КАК ДОЛЖНО, расхождение = чинить; sachith/orkes/agent-axiom/myrobertson/harness idempotency + retry + rollback — повтор безопасен (идемпотентность), откат по явным границам, бэкап ДО: «агент падает и перезапускается БЕЗ памяти первого шага»):
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 · 154 lines · 255 tokens per session scan A 6e14a42ee9ff
caveman-verify is a skill published in the GitHub repository aidvizhhub/caveman-dvizh-skills (6 stars, last pushed 18d ago), licensed MIT. It adds 255 tokens to every session and 3,023 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.
Other skills, from other repositories
root-cause
Use when any test fails, bug appears, or behaviour surprises you, before proposing a fix - find the cause and prove it, by reading real evidence, tracing bad values back to their origin, comparing against a working case, and testing one hypothesis at a time.
refactor
Refactor and optimize [code].
go-logging
Use when choosing a Go logger, configuring slog, writing structured log statements, picking log levels, or attaching request-scoped fields. Apply proactively whenever code calls log/fmt to emit operational information, migrates off log/logrus/zap/zerolog, or sets up production logging. Covers structured logging only …
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
gke-ai-troubleshooting-jobset-interruption
Diagnoses GKE JobSet interruptions, restarts, and preemptions for AI/ML training workloads autonomously. Use when troubleshooting JobSet restart loops, spot VM preemptions, node readiness failures, host VM issues, or coordinator worker crashes. Don't use for general GKE cluster creation, basic workload deployment, or…
gke-node-notready
Diagnoses GKE nodes reporting NotReady or Unknown status by inspecting node conditions, events, kubelet/containerd logs, and node metrics, then proposing safe remediations. Use when nodes show NotReady, when the kubelet stops posting node status, or when workloads are evicted or stuck Pending due to node health. Don't…