klaws: Instructions file for Claude Code

CLAUDE.md

klaws CLAUDE.md is an instructions file for Claude Code from rostradamus/klaws. It costs 881 tokens per session, scanned A, original, MIT.

A set of Claude Code instructions for klaws, a codebase scanner that checks for possible risks related to Korean privacy law. It also describes the project's architecture, build commands, and tests.

In plain words
What is it for?
Use it when building, testing, scanning, or changing the klaws codebase, including its MCP server, command-line tool, detectors, and reports.
Why use it?
It gives the coding agent the project's rules and terminology, including how to discuss possible legal risks without presenting the results as legal advice.

Instructions file for Claude Code

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

This is rostradamus/klaws's own configuration. It tells Claude Code how to work on klaws 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 klaws configures →

Reuse

Borrowing it

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

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 klaws CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rostradamus/klaws/claude-md/github.svg)](https://agentmods.dev/instructions/rostradamus/klaws/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/rostradamus/klaws/claude-md"><img src="https://agentmods.dev/badge/instructions/rostradamus/klaws/claude-md/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 klaws CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/rostradamus/klaws/claude-md"><img src="https://agentmods.dev/badge/instructions/rostradamus/klaws/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 881 This file is loaded in full into every session.
When invoked 881 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 $0.00881 $0.00881
Opus 5.5 $0.00352 $0.00352
Sonnet 5.5 $0.00176 $0.00176
Haiku 4.5 $0.00088 $0.00088

Measured 2mo ago against content hash 2569384d6459, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

klaws 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 2mo 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 · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 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.

About

klaws is a Korean compliance risk scanner for codebases. It identifies possible risks related to Korean laws (currently PIPA) and maps them to specific law provisions. It operates as an MCP server (primary) and CLI tool (secondary).

Critical Rules

  • This tool does NOT provide legal advice
  • All user-facing text must use hedged language: "possible risk", "may require review", "related provision"
  • Never use: "violation", "illegal", "non-compliant", "you must"

Build & Test

go build -o klaws ./cmd/klaws/          # Build binary
go test ./...                            # Run all tests
go test ./internal/detector/ -v          # Run one package
go test ./internal/detector/ -run TestLogging  # Run one test
go run ./cmd/klaws/ scan ./testdata      # Quick smoke test

Architecture

The scan pipeline flows: Walker → ScannerService → Detectors → Report

  • cmd/klaws/main.go — Entry point. Wires dependencies and defines cobra commands (scan, detectors, law, serve).
  • internal/scanner/ — ScannerService orchestrates scanning. FileWalker walks directories matching glob patterns. The service reads each file and passes source code through all registered detectors.
  • internal/detector/ — Detector interface with Scan(sourceCode, filePath) []Finding. Each detector uses regex patterns to identify risks. Registry holds all detectors and runs them collectively via ScanAll().
  • internal/law/ — Registry loads law provisions from laws.yaml (embedded via go:embed, overridable with --laws flag). Client fetches live law text from law.go.kr XML API. LookupLive falls back to bundled data on fetch failure.
  • internal/report/ — Finding and Report models. FormatJSON and FormatText formatters.
  • internal/mcp/ — MCP server exposing 4 tools: scan_directory, scan_file, list_detectors, get_law_reference. Uses mcp-go SDK with stdio transport.

Read the full file on GitHub · 67 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. 2mo ago First seen · 67 lines · 881 tokens per session scan A 2569384d6459

Subscribe to this mod's changes

klaws CLAUDE.md is an instructions file published in the GitHub repository rostradamus/klaws (1 stars, last pushed 3mo ago), licensed MIT. It adds 881 tokens to every session, about $0.0035 per session on Opus 5.5. 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

klaws CLAUDE.md compared with instructions from other repositories

klaws CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
klaws CLAUDE.mdrostradamus/klawsInstructions file13mo agoMITA881Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot
generative-ai-for-beginners AGENTS.mdmicrosoft/generative-ai-for-beginnersInstructions file124ktodayMITA2,981Codex, OpenCode