Borrowing it
Nothing to install: this file belongs to arc-mcp/arc1-adt-abap-mcp-ext. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/arc-mcp/arc1-adt-abap-mcp-ext/main/CLAUDE.mdgit clone --depth 1 https://github.com/arc-mcp/arc1-adt-abap-mcp-extWrote 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/arc-mcp/arc1-adt-abap-mcp-ext/claude-md)<a href="https://agentmods.dev/instructions/arc-mcp/arc1-adt-abap-mcp-ext/claude-md"><img src="https://agentmods.dev/badge/instructions/arc-mcp/arc1-adt-abap-mcp-ext/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.
<a href="https://agentmods.dev/instructions/arc-mcp/arc1-adt-abap-mcp-ext/claude-md"><img src="https://agentmods.dev/badge/instructions/arc-mcp/arc1-adt-abap-mcp-ext/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.04018 | $0.04018 |
| Opus 5 | $0.02009 | $0.02009 |
| Sonnet 5 | $0.00804 | $0.00804 |
| Haiku 4.5 | $0.00402 | $0.00402 |
Grade A, and why
arc1-adt-abap-mcp-ext 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for AI assistants (and humans) working on com.arc1.mcp (the
Eclipse plugin in this repo). Read this first.
Project goal
Extend SAP's Model Context Protocol (MCP) server inside Eclipse-for-ABAP with extra read-only tools, so AI clients (Claude Code, GitHub Copilot, Cursor, Claude Desktop) can read your ABAP system without any extra process.
Requires ADT 3.60+, where SAP ships the MCP server as a supported feature.
The user installs one JAR, turns SAP's server on once (the ABAP Development →
MCP Server preference + -DadtMcpServerPrefEnabled=true in eclipse.ini),
and restarts. From then on, this plugin's tools register on SAP's authenticated
MCP endpoint (default http://localhost:2234/mcp) whenever the server runs.
Why this exists
SAP ships the MCP server inside ADT. In 3.58/3.59 it was dormant with no
activation surface; as of ADT 3.60 it is a supported feature with its own
preference page (ABAP Development → MCP Server) and a startup flag
(-DadtMcpServerPrefEnabled=true) — but it's off by default and, on its
own, only carries SAP's own tools. SAP exposes a public Eclipse extension point
com.sap.adt.mcp.core.adtMcpTools for contributing extra tools. This plugin
does exactly one thing:
- Contribute extra tools via that documented extension point. SAP's own
ToolRegistrationServiceregisters them whenever the server starts.
(It also optionally pre-warms the ABAP project logon so tools work on the first call — public API, not a hack.)
Earlier versions (≤ 0.3.x) also reflectively kickstarted the dormant 3.58
server. ADT 3.60 made that both unnecessary (SAP ships activation) and broken
(the startMCPServer signature changed to take a FileSystemMode), so v0.4.0
removed it — the plugin no longer touches the server lifecycle. See
docs/decisions.md D9 (supersedes D3).
Non-goals
This plugin is intentionally Eclipse-bound. It is NOT trying to be:
- A standalone MCP server (that's ARC-1, in TypeScript, runs anywhere).
- A managed multi-user service with admin policy ceilings, audit, BTP deployment (also ARC-1 territory).
- A write/activate platform — mutating tools belong in SAP's own MCP
surface (
abap_transport-create,abap_generators-generate_objects), which SAP ships and registers itself. - A headless / programmatic / CI driver for ABAP — that's
adt-ls(a TypeScript SDK over SAP's headlessadt-lslanguage server). We do not consume it as a dependency (it'd mean a Node process + a second headless ADT inside the real one) — seedocs/decisions.mdD10.
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.
- 11d ago First seen · 324 lines · 4,018 tokens per session scan A d355f1543a28
arc1-adt-abap-mcp-ext CLAUDE.md is an instructions file published in the GitHub repository arc-mcp/arc1-adt-abap-mcp-ext (8 stars, last pushed 3mo ago), licensed MIT. It adds 4,018 tokens to every session, about $0.0201 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 2026-08-31.
Other instructions, from other repositories
vibe-coding-prompt-template backend.instructions.md
Instructions for KhazP/vibe-coding-prompt-template: Read AGENTS.md, agentdocs/techstack.md, and agentdocs/codepatterns.md.
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.
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).
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.
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.