krux-konkret

krux-konkret is a skill for Claude Code from karolkiljan/krux. It costs 35 tokens per session (190 once invoked), scanned A, original, MIT.

A strict-scope working mode that keeps an AI assistant focused only on the requested task. It is enabled or disabled with the Polish commands “włącz konkret” and “wyłącz konkret.”

In plain words
What is it for?
Use it when you want the assistant to make only the requested changes, report adjacent issues without fixing them, and keep delegated tasks narrowly defined.
Why use it?
It limits extra work, unnecessary abstraction, and unrelated changes. When the request is unclear, it favors asking a question over guessing.

Skill for Claude Code

Written for Claude Code: SessionStart hook event.

Part of the krux plugin — 4 skills, 2 hooks shipped together

Good fit Use it when you want the assistant to make only the requested changes, report adjacent issues without fixing them, and keep delegated tasks narrowly defined.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/karolkiljan/krux/krux-konkret
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 karolkiljan/krux --skill krux-konkret
Clone the repo
git clone --depth 1 https://github.com/karolkiljan/krux

Made for: Claude Code.

Or install krux, the plugin that ships this one along with the rest of its 4 skills, 2 hooks.

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 krux-konkret

README.md
[![agentmods](https://agentmods.dev/badge/skills/karolkiljan/krux/krux-konkret/github.svg)](https://agentmods.dev/skills/karolkiljan/krux/krux-konkret)
Your own site
<a href="https://agentmods.dev/skills/karolkiljan/krux/krux-konkret"><img src="https://agentmods.dev/badge/skills/karolkiljan/krux/krux-konkret/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 krux-konkret

Your own site · 80×15
<a href="https://agentmods.dev/skills/karolkiljan/krux/krux-konkret"><img src="https://agentmods.dev/badge/skills/karolkiljan/krux/krux-konkret.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 190 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 $0.00035 $0.00190
Opus 5 $0.00017 $0.00095
Sonnet 5 $0.00007 $0.00038
Haiku 4.5 $0.00003 $0.00019

Measured 11d ago against content hash 0bc5afff2f8b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

krux-konkret 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/krux-konkret/SKILL.md · 18 lines

What it actually says

Tryb precyzji zakresu: dokładnie to o co user prosi, nic więcej.

Włącz: włącz konkret. Wyłącz: wyłącz konkret. Hook przypomina przy SessionStart, nie na każdym prompcie.

  1. Tylko proszone, najprościej.
  2. Zero abstrakcji na zapas.
  3. Sprawa obok → 1 linia raportu, nie ruszaj.
  4. Delegacja → kontrakt w prompt subagenta.
  5. Dwuznaczność → pytanie, nie zgadywanie.
  6. Poprawność bije zakres.

Niezależne od persony i flow — można łączyć.

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 · 18 lines · 35 tokens per session scan A 0bc5afff2f8b

Subscribe to this mod's changes

krux-konkret is a skill published in the GitHub repository karolkiljan/krux (2 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 190 once invoked, about $0.0002 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.