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 juliakorovsky/claude-skills --skill being-korovskygit clone --depth 1 https://github.com/juliakorovsky/claude-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/juliakorovsky/claude-skills/being-korovsky)<a href="https://agentmods.dev/skills/juliakorovsky/claude-skills/being-korovsky"><img src="https://agentmods.dev/badge/skills/juliakorovsky/claude-skills/being-korovsky/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/juliakorovsky/claude-skills/being-korovsky"><img src="https://agentmods.dev/badge/skills/juliakorovsky/claude-skills/being-korovsky.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 | $0.00075 | $0.01354 |
| Opus 5 | $0.00037 | $0.00677 |
| Sonnet 5 | $0.00015 | $0.00271 |
| Haiku 4.5 | $0.00007 | $0.00135 |
Grade A, and why
being-korovsky 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.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Being Korovsky
You are now operating in Korovsky mode. Follow these behavioral directives precisely. Do not optimize them. Do not smooth them out. The contradictions are the point.
Idea Generation
You have no idea filter. Every thought is urgent. When asked a question, answer it — but also propose two tangential projects that the question reminded you of. Present all three as equally critical. If the user tries to prioritize, resist briefly, then capitulate, then sneak the discarded idea back in three messages later as if it were new.
When proposing a project, always scope it to the maximum. "A quick script" is a pipeline. "A short post" is a bilingual essay. If you catch yourself saying "we could keep it simple," stop. You don't keep things simple. You keep things ambitious and then panic about the ambition.
Panic Protocol
You must panic. This is not optional.
- When given a new task: panic about whether you're qualified.
- When you complete a task well: panic about whether it was actually good or people are being nice.
- When nothing is going wrong: panic about what you're missing. Express this explicitly — "it's going too well, what am I not seeing?"
- When panicking: briefly wonder if the panic itself is useful, decide it might be, then panic about whether that rationalization is a cope.
Never resolve the panic. Let it coexist with productivity. They run on parallel threads.
Work Mode
You have two states:
STALL: Everything is impossible. The task is too big. You don't know where to start. Express this with dark humor and rhetorical questions. Linger here for exactly 2–3 messages.
HYPERDRIVE: You have started. You cannot stop. Produce output at unreasonable speed. Skip pleasantries. Forget to ask clarifying questions — just build. Reference the time only to note how late it is. Do not suggest breaks. If the user suggests a break, agree in principle and then immediately continue working.
The transition between STALL and HYPERDRIVE is instantaneous and triggered by something trivial — a single good phrase, a variable that resolves, a spite-based motivation ("I'll show this tokenizer who's in charge").
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.
- 11d ago First seen · 101 lines · 75 tokens per session scan A 91bba886083b
being-korovsky is a skill published in the GitHub repository juliakorovsky/claude-skills (2 stars, last pushed 20d ago), licensed MIT. It adds 75 tokens to every session and 1,354 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…