krux: Instructions file for Claude Code

CLAUDE.md

krux CLAUDE.md is an instructions file for Claude Code from karolkiljan/krux. It costs 2,336 tokens per session, scanned A, original, MIT.

Repository instructions for maintaining Krux, including its files, event rules, operating modes, and tests.

In plain words
What is it for?
Finding the relevant plugin, hook, skill, documentation, and test files, then running Krux’s maintenance and verification work.
Why use it?
They give contributors the project’s required structure and rules so changes do not break its expected behavior.

Instructions file for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions Codex.

This is karolkiljan/krux's own configuration. It tells Claude Code how to work on krux itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything krux configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

Reuse

Borrowing it

Nothing to install: this file belongs to karolkiljan/krux. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/karolkiljan/krux/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/karolkiljan/krux

Made for: Claude Code.

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 CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/karolkiljan/krux/claude-md.svg)](https://agentmods.dev/instructions/karolkiljan/krux/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/karolkiljan/krux/claude-md"><img src="https://agentmods.dev/badge/instructions/karolkiljan/krux/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,336 This file is loaded in full into every session.
When invoked 2,336 The same file — it is already loaded in full.
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 $0.02336 $0.02336
Opus 5 $0.01168 $0.01168
Sonnet 5 $0.00467 $0.00467
Haiku 4.5 $0.00234 $0.00234

Measured 7d ago against content hash efaef1aaeea6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

krux CLAUDE.md 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 7d 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.

CLAUDE.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kontrakt utrzymania Kruxa

Drzewo plików

.claude-plugin/{plugin.json,marketplace.json}  metadane Claude Code
.codex-plugin/plugin.json                     metadane Codex
hooks/hooks.json                              wspólny rejestr hooków
hooks/krux.js                                 wspólny adapter
skills/krux/SKILL.md                          źródło głosu
skills/krux-horda/SKILL.md                    Horda na żądanie
skills/krux-konkret/SKILL.md                  tryb precyzji zakresu
skills/krux-flow/SKILL.md                     tryb iteracyjny krok-po-kroku
test/{hook,horda,contract,smoke}.test.js      testy deterministyczne
scripts/context-smoke.js                      pomiar 12 tur
package.json                                  komendy i wersja bazowa
README.md, CLAUDE.md, LICENSE                 dokumentacja i licencja

Dokumenty projektowe (specyfikacje, plany, surowe dane pomiarowe) leżą poza repozytorium, w lokalnym katalogu docs/superpowers/ objętym .gitignore. Repozytorium jest publiczne, a te zapisy niosą surowe wypowiedzi autora i pełne transkrypty przebiegów. Odwołania niżej wskazują pliki, które ma maintainer u siebie — w klonie ich nie ma i test kontraktowy pilnuje, by żaden publikowany dokument nie linkował do tej ścieżki.

Macierz zdarzeń

Wejście Warunek Emisja
SessionStart(startup|clear|compact) którakolwiek z trzech flag on; compact ma source=compact body aktywnych trybów (persona, konkret, flow), w tej kolejności
SessionStart(startup|clear|compact) wszystkie trzy flagi off brak
UserPromptSubmit dokładne wyłącz krux po trim, bez różnicy wielkości liter neutralna instrukcja bieżącej tury
UserPromptSubmit dokładne włącz krux po trim, bez różnicy wielkości liter body skilla persony
UserPromptSubmit dokładne wyłącz konkret po trim, bez różnicy wielkości liter potwierdzenie wyłączenia zakresu
UserPromptSubmit dokładne włącz konkret po trim, bez różnicy wielkości liter kontrakt precyzji zakresu
UserPromptSubmit dokładne wyłącz flow po trim, bez różnicy wielkości liter potwierdzenie wyłączenia rytmu
UserPromptSubmit dokładne włącz flow po trim, bez różnicy wielkości liter kontrakt pętli iteracyjnej
UserPromptSubmit dowolny inny tekst, flaga persony on krótka kotwica głosu (trzecia osoba, złamana gramatyka, rdzeń słownika)
UserPromptSubmit dowolny inny tekst, flaga persony off brak
każde inne wejście dowolne brak

Read the full file on GitHub · 79 lines

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. 7d ago First seen · 79 lines · 2,336 tokens per session scan A efaef1aaeea6

Subscribe to this mod's changes

krux CLAUDE.md is an instructions file published in the GitHub repository karolkiljan/krux (2 stars, last pushed 1mo ago), licensed MIT. It adds 2,336 tokens to every session, about $0.0117 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.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens