kurdyuk-lite: Instructions file for Claude Code

CLAUDE.md

kurdyuk-lite CLAUDE.md is an instructions file for Claude Code from LARIkoz/kurdyuk-lite. It costs 411 tokens per session, scanned A, original, MIT.

Un conjunto de instrucciones para trabajar en el repositorio de código de Kurdyuk Lite, un marco de trabajo para organizar proyectos mediante etapas de definición y desarrollo. Indica dónde está el contrato principal y cómo se estructura el repositorio.

In plain words
What is it for?
Sirve para mantener el contrato operativo, preparar su instalación en otros proyectos y trabajar con los archivos de documentación, plantillas y scripts de Kurdyuk Lite.
Why use it?
Reduce el riesgo de editar una copia equivocada de las reglas o de romper la relación entre el contrato, las plantillas y las herramientas del marco.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is LARIkoz/kurdyuk-lite's own configuration. It tells Claude Code how to work on kurdyuk-lite 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 kurdyuk-lite configures →

Reuse

Borrowing it

Nothing to install: this file belongs to LARIkoz/kurdyuk-lite. 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/LARIkoz/kurdyuk-lite/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/LARIkoz/kurdyuk-lite

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 kurdyuk-lite CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/larikoz/kurdyuk-lite/claude-md.svg)](https://agentmods.dev/instructions/larikoz/kurdyuk-lite/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/larikoz/kurdyuk-lite/claude-md"><img src="https://agentmods.dev/badge/instructions/larikoz/kurdyuk-lite/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 411 This file is loaded in full into every session.
When invoked 411 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 $0.00411 $0.00411
Opus 5 $0.00205 $0.00205
Sonnet 5 $0.00082 $0.00082
Haiku 4.5 $0.00041 $0.00041

Measured 7d ago against content hash d397bdf784d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

kurdyuk-lite 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 · 29 lines

What it actually says

Kurdyuk Lite — Framework Source Repo

This repository is the Kurdyuk Lite framework. You are editing the framework itself, not using it.

The contract lives in one place

CLAUDE-contract.md is the canonical operating contract — the Brief → Charter → Spec → Plan → Implement → Final Review pipeline. kurdyuk-lite init injects it as a marked block into a target project's CLAUDE.md.

One source of truth: edit the contract in CLAUDE-contract.md. Never maintain a second copy of the pipeline rules here — divergence between the two is exactly the bug this layout prevents.

Map

  • CLAUDE-contract.md — the operating contract (injected into target projects)
  • concept.md — framework methodology + charter deep dive
  • charter-for-charter.md — meta-rules for writing any charter
  • reference/examples.md — reference charters to study
  • templates/ — the phase templates init copies into a target project
  • bin/kurdyuk-liteinit / check engine · bin/kurdyuk-install — one-command bootstrap
  • README.md — install + usage · BOOTSTRAP.md — paste-into-Claude installer · MIGRATION.md — v2→v3 upgrade

Working in this repo (developing the framework)

  • Touching a charter or the contract → obey charter-for-charter.md: no heuristics, no HOW, testable, write-then-cut.
  • Smallest clean diff. No decorative docs outside the file map above.
  • The contract is hash-anchored (bin/kurdyuk-lite check) — after editing CLAUDE-contract.md, bump VERSION.
  • Dogfooding (running the pipeline on a product inside this repo) → that run is governed by CLAUDE-contract.md; read it.
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 · 29 lines · 411 tokens per session scan A d397bdf784d4

Subscribe to this mod's changes

kurdyuk-lite CLAUDE.md is an instructions file published in the GitHub repository LARIkoz/kurdyuk-lite (2 stars, last pushed 1mo ago), licensed MIT. It adds 411 tokens to every session, about $0.0021 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