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.
npx agentmods add instructions/datazoode/erpl-adt/claude-mdgit clone --depth 1 https://github.com/DataZooDE/erpl-adtWrote 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.
[](https://agentmods.dev/instructions/datazoode/erpl-adt/claude-md)<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>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.
| Model | Per session | Once 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 |
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.
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).
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.
- yesterday Changed · +15 lines · +255 tokens per session 4c5aa0a0aad4
- 5d ago First seen · 407 lines · 6,543 tokens per session scan A 3aaf1fdf3529
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.
Other instructions, from other repositories
sap-engineering-skill CLAUDE.md
Instructions for shrek-abaper/sap-engineering-skill, covering claude.md, repository overview, skills, repository structure and archived standalone repositories (historical).
sap-superpowers CLAUDE.md
Claude Code instructions for vigneshbarani24/sap-superpowers, covering sap superpowers v3.1, skills (53+), meta skills (5), consulting skills (9) and development skills (8).
aibap.mcp CLAUDE.md
Claude Code instructions for Hochfrequenz/aibap.mcp, covering claude.md, project overview, build & run, testing and workflow.
sap-adt-mcp CLAUDE.md
Claude Code instructions for engoetz/sap-adt-mcp, covering claude.md, what this is, commands, architecture and invariants that are easy to break.
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.
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).