kleinanzeigen-reader: Instructions file for Claude Code

CLAUDE.md

kleinanzeigen-reader CLAUDE.md is an instructions file for Claude Code from its-me-prash/kleinanzeigen-reader. It costs 834 tokens per session, scanned A, original, MIT.

A project instruction file for kleinanzeigen-reader, a Python toolkit and Claude skill that extracts structured information from Kleinanzeigen.de classified listings.

In plain words
What is it for?
Use it when working on listing extraction, comparison, category-specific analysis, or the project’s command-line and Python interfaces.
Why use it?
It tells the coding agent which instructions, scripts, and category references to use instead of recreating the listing-extraction process.

Instructions file for Claude Code

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

This is its-me-prash/kleinanzeigen-reader's own configuration. It tells Claude Code how to work on kleinanzeigen-reader 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 kleinanzeigen-reader configures →

Reuse

Borrowing it

Nothing to install: this file belongs to its-me-prash/kleinanzeigen-reader. 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/its-me-prash/kleinanzeigen-reader/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/its-me-prash/kleinanzeigen-reader

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 kleinanzeigen-reader CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/its-me-prash/kleinanzeigen-reader/claude-md"><img src="https://agentmods.dev/badge/instructions/its-me-prash/kleinanzeigen-reader/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 834 This file is loaded in full into every session.
When invoked 834 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.00834 $0.00834
Opus 5 $0.00417 $0.00417
Sonnet 5 $0.00167 $0.00167
Haiku 4.5 $0.00083 $0.00083

Measured 8d ago against content hash 5d984df47033, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

kleinanzeigen-reader CLAUDE.md scanned grade A with 1 finding 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 8d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

5. **Never hardcode credentials** — fetch URLs with the curl command in SKILL.md
CLAUDE.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — kleinanzeigen-reader

This file is auto-read by Claude Code at session start. It tells Claude what this repo is, how to use it, and what to load.

What this repo is

kleinanzeigen-reader is a Claude skill + Python toolkit for extracting structured data from kleinanzeigen.de listings. It works on any category: vehicles, electronics, real estate, furniture.

Maintained by: github.com/its-me-prash
Part of: Balan's Group Brain OS skill ecosystem
Repo: https://github.com/its-me-prash/kleinanzeigen-reader


Auto-load instructions for Claude Code

When this repo is in context, Claude should:

  1. Always read SKILL.md first before responding to any Kleinanzeigen-related request
  2. Use scripts/extract.py for single listings — do not rewrite extraction logic inline
  3. Use scripts/compare.py for 2+ listings
  4. Load the relevant category reference from references/categories/ based on listing type
  5. Never hardcode credentials — fetch URLs with the curl command in SKILL.md

Quick command reference

# Fetch a listing
curl -s -L \
  -H "User-Agent: Mozilla/5.0 (iPhone; CPU iPhone OS 17_4 like Mac OS X) AppleWebKit/605.1.15" \
  -H "Referer: https://www.kleinanzeigen.de/" \
  "[URL]" > /tmp/listing.html

# Extract
python3 scripts/extract.py /tmp/listing.html

# Compare
python3 scripts/compare.py /tmp/l1.html /tmp/l2.html

Key data sources inside Kleinanzeigen HTML

Source Where What it contains
JSON-LD <script type="application/ld+json"> Title, price, images
ad_attributes GTM JS block All vehicle/item attributes
li field GTM JS block 0=private, 1=dealer
DFP block GTM JS block Clean price, km, EZ values
Hidden JSON page JSON Exact lat/long, userSince, originalPrice, status

Mobile API (RE): references/mobile-api.md maps the app's CAPI (endpoints, auth scheme, hidden fields). Reference only — the shipping code reads the public web page. Signals: kl_reader/signals.py = view counter, seller portfolio, status (reserved/sold), native price reduction, and a local PriceTracker. Authenticated mode: kl_reader/auth.py Session (bring-your-own-token) = 👀 views + ⭐ watchers for any ad, full ad JSON, your own paused ads. Never reads browser creds from disk; token via arg or KA_BEARER. Not live-validated — treat 401/403 as "refresh token".

Read the full file on GitHub · 85 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. 8d ago First seen · 85 lines · 834 tokens per session scan A 5d984df47033

Subscribe to this mod's changes

kleinanzeigen-reader CLAUDE.md is an instructions file published in the GitHub repository its-me-prash/kleinanzeigen-reader (4 stars, last pushed 1mo ago), licensed MIT. It adds 834 tokens to every session, about $0.0042 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

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

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 · 5,153 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

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

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

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