erpl-adt CLAUDE.md

erpl-adt CLAUDE.md is an instructions file for coding agents from DataZooDE/erpl-adt. It costs 6,798 tokens per session, scanned A, original, Apache-2.0.

Project instructions for erpl-adt, a C++ command-line tool and MCP server that connects AI agents and developers to SAP ABAP systems.

In plain words
What is it for?
Use them when changing SAP ADT API access, ABAP source operations, tests, transports, CMake builds, or release workflows.
Why use it?
They document the build, test, commit, and pull-request rules, along with the project's key dependencies and structure.

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/datazoode/erpl-adt/claude-md
Clone the repo
git clone --depth 1 https://github.com/DataZooDE/erpl-adt

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 erpl-adt CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/datazoode/erpl-adt/claude-md.svg)](https://agentmods.dev/instructions/datazoode/erpl-adt/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/datazoode/erpl-adt/claude-md"><img src="https://agentmods.dev/badge/instructions/datazoode/erpl-adt/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 6,798 This file is loaded in full into every session.
When invoked 6,798 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 $0.06798 $0.06798
Opus 5 $0.03399 $0.03399
Sonnet 5 $0.01360 $0.01360
Haiku 4.5 $0.00680 $0.00680

Measured yesterday against content hash 4c5aa0a0aad4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

erpl-adt 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 yesterday.

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 · 422 lines

How it starts

The opening of the file, as written. The whole thing — 422 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.

Git Commits and Pull Requests

Do NOT include Co-Authored-By, 🤖 Generated with Claude Code, or any AI attribution lines in commit messages or pull request bodies.

Project Overview

erpl-adt is a CLI and MCP server for the SAP ADT REST API — a single C++ binary that talks the same HTTP endpoints Eclipse ADT uses. It enables AI coding agents and human developers to search, read/write source code, run tests, manage transports, and more against ABAP systems. No Eclipse, no SAP NW RFC SDK, no JVM.

Part of the Datazoo ERPL family. Shares build conventions with flapi and library choices with erpl-web.

Build Commands

make release          # Full release build (CMake + Ninja + vcpkg)
make test             # Run unit tests (Catch2, no SAP system needed)
make clean            # Remove the build directory

For faster rebuilds during development:

cmake --build build --target erpl_adt_tests   # Rebuild tests only
ctest --test-dir build --output-on-failure     # Run tests only

Build requires: CMake, Ninja, vcpkg (git submodule at vcpkg/). Checkout with --recurse-submodules.

Architecture

main.cpp -> command_router -> {group handlers}
                                    |
         +---------+---------+------+------+---------+---------+
         v         v         v      v      v         v         v
      search    object    source  test   check   transport   mcp
      locking    ddic    packages abapgit activation  deploy_workflow
         |         |         |      |      |         |         |
         +---------+---------+------+------+---------+---------+
                                    v
                             i_adt_session <-- adt_session (cpp-httplib)
                                    |
                             i_xml_codec  <-- xml_codec   (tinyxml2)

All arrows point downward. No cycles. Every horizontal boundary is a pure abstract interface (abstract base class).

Read the full file on GitHub · 422 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. yesterday Changed · +15 lines · +255 tokens per session 4c5aa0a0aad4
  2. 5d ago First seen · 407 lines · 6,543 tokens per session scan A 3aaf1fdf3529

Subscribe to this mod's changes

erpl-adt CLAUDE.md is an instructions file published in the GitHub repository DataZooDE/erpl-adt (19 stars, last pushed 3d ago), licensed Apache-2.0. It adds 6,798 tokens to every session, about $0.0340 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.