K-LEAN CLAUDE.md

K-LEAN CLAUDE.md is an instructions file for coding agents from calinfaja/K-LEAN. It costs 1,583 tokens per session, scanned A, original, Apache-2.0.

Project instructions for K-LEAN, a code-review and knowledge-capture system for Claude Code. The documentation covers its commands, architecture, virtual environment, tests, formatting, and health checks.

In plain words
What is it for?
Installing, testing, linting, formatting, syncing, and checking the K-LEAN project.
Why use it?
It tells an AI coding assistant how this project is organised and which development commands and environment it must use.

Instructions file

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.

agentmods
npx agentmods add instructions/calinfaja/k-lean/claude-md
Clone the repo
git clone --depth 1 https://github.com/calinfaja/K-LEAN

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 K-LEAN CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/calinfaja/k-lean/claude-md.svg)](https://agentmods.dev/instructions/calinfaja/k-lean/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/calinfaja/k-lean/claude-md"><img src="https://agentmods.dev/badge/instructions/calinfaja/k-lean/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,583 This file is loaded in full into every session.
When invoked 1,583 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01583 $0.01583
Opus 5 $0.00792 $0.00792
Sonnet 5 $0.00317 $0.00317
Haiku 4.5 $0.00158 $0.00158

Measured 5d ago against content hash af291d5b467e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

K-LEAN 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 5d 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 · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

K-LEAN is a multi-model code review and knowledge capture system for Claude Code. It provides consensus reviews from multiple LLMs via LiteLLM proxy, a persistent per-project knowledge database with hybrid semantic search, and 8 specialist agents for domain-specific analysis.

Package name: kln-ai (PyPI) Entry points: kln (main CLI), kln-smol (agent executor)

Development Commands

IMPORTANT: Always use the project venv at .venv/. System python lacks required dependencies (platformdirs, psutil, etc.) and will fail on import.

# Install in editable mode
pipx install -e .

# Run tests (MUST use .venv)
.venv/bin/pytest tests/ -v
.venv/bin/pytest tests/unit/test_hooks.py -v
.venv/bin/pytest tests/unit/test_hooks.py::TestClassName::test_method -v

# Lint (MUST use .venv)
.venv/bin/ruff check src/
.venv/bin/ruff check src/ --fix

# Format
.venv/bin/black src/

# Sync data files to ~/.claude/ after editing data/*
kln admin sync

# Check installation health
kln doctor -f

Architecture

Core Flow

Claude Code
    |
    v
/kln:* commands (data/commands/kln/*.md)
    |
    +---> LiteLLM Proxy (localhost:4000) ---> NanoGPT/OpenRouter
    |
    +---> Knowledge DB (.knowledge-db/) - fastembed hybrid search
    |
    +---> SmolKLN Agents (src/klean/smol/) - smolagents framework

Key Modules

Module Purpose
src/klean/cli.py Click CLI with subgroups: model, provider, admin
src/klean/discovery.py Dynamic model discovery from LiteLLM proxy
src/klean/config_generator.py LiteLLM config generation with non-destructive merging
src/klean/model_defaults.py Default model configurations per provider
src/klean/model_utils.py Model name extraction and parsing utilities
src/klean/smol/executor.py Single agent execution with tool use
src/klean/smol/multi_agent.py Multi-agent orchestration and consensus
src/klean/smol/loader.py Agent definition loading from markdown (YAML frontmatter + system prompt)
src/klean/smol/models.py LiteLLM model wrapper with thinking model support

Read the full file on GitHub · 174 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. 5d ago First seen · 174 lines · 1,583 tokens per session scan A af291d5b467e

Subscribe to this mod's changes

K-LEAN CLAUDE.md is an instructions file published in the GitHub repository calinfaja/K-LEAN (36 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 1,583 tokens to every session, about $0.0079 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 2026-08-30.

Related

Other instructions, from other repositories

river-review GEMINI.md

Gemini CLI instructions for s977043/river-review, covering gemini instructions (river-review), 必須チェック, gemini-specific tips, prompt assembly and development tips.

s977043/river-review · 318 tokens

living-manual CLAUDE.md

Instructions for dougstanford/living-manual, covering living-manual, start of every session, how work lands — non-negotiable, user's manual (living-manual) and releasing.

dougstanford/living-manual · 1,108 tokens

ship-it open-pr.instructions.md

Instructions for khrichtchatyi/ship-it: When the user asks to open, create, or submit a pull request, follow the skill in skills/open-pr/SKILL.md in full: verify gh is authenticated, resolve the target repository and default branch, push the current branch, open one pull request with a title and body derived from the…

khrichtchatyi/ship-it · 84 tokens

agent-skills CLAUDE.md

Instructions for mindbox-cloud/agent-skills, covering agent-skills — developer guide for claude code, repository purpose, repository structure, how to add a new plugin and step 1 — create the directory structure.

mindbox-cloud/agent-skills · 1,143 tokens

my-claude-skills CLAUDE.md

Instructions for brody-0125/my-claude-skills, covering claude code skills repository, validation commands, sub-kopring-engineer: kotlin/java 코드 컨벤션 검증, numerical: 수치 연산 코드 검증 and sub-test-engineer: 문서 일관성 검증.

brody-0125/my-claude-skills · 1,093 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