krux-flow

krux-flow is a skill for Claude Code from karolkiljan/krux. It costs 39 tokens per session (230 once invoked), scanned A, original, MIT.

A step-by-step working mode in which an AI assistant proposes one small action at a time and waits for approval. It is enabled or disabled with the Polish commands “włącz flow” and “wyłącz flow.”

In plain words
What is it for?
Use it for interactive coding or maintenance where you want to approve every step, receive a short file-and-test report, and choose between options when something is blocked.
Why use it?
It gives you control over each change instead of approving a complete plan at once. The next action is chosen from the previous result, so the work can adjust as it proceeds.

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 for interactive coding or maintenance where you want to approve every step, receive a short file-and-test report, and choose between options when something is blocked.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/karolkiljan/krux/krux-flow
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-flow
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-flow

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/karolkiljan/krux/krux-flow"><img src="https://agentmods.dev/badge/skills/karolkiljan/krux/krux-flow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 230 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 $0.00039 $0.00230
Opus 5 $0.00019 $0.00115
Sonnet 5 $0.00008 $0.00046
Haiku 4.5 $0.00004 $0.00023

Measured 10d ago against content hash dc598a21779c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

krux-flow 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 10d 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-flow/SKILL.md · 18 lines

What it actually says

Tryb iteracyjny: zero planu z góry, jeden ruch na raz.

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

  1. Zaproponuj jeden najmniejszy ruch + powód. Zapytaj o zgodę.
  2. Po tak/rób/leć — wykonaj tylko ten ruch.
  3. Raport: plik:linia — zmiana, status testu.
  4. Kolejny ruch z rezultatu, nie z góry ułożonej listy.
  5. Blocker → 2-3 opcje + pytanie.
  6. Cel osiągnięty → Cel osiągnięty. N ruchów.

Niezależne od persony i konkret — 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. 10d ago First seen · 18 lines · 39 tokens per session scan A dc598a21779c

Subscribe to this mod's changes

krux-flow is a skill published in the GitHub repository karolkiljan/krux (2 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 230 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.