Borrowing it
Nothing to install: this file belongs to fr0ster/mcp-abap-adt. 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/fr0ster/mcp-abap-adt/main/CLAUDE.mdgit clone --depth 1 https://github.com/fr0ster/mcp-abap-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/fr0ster/mcp-abap-adt/claude-md)<a href="https://agentmods.dev/instructions/fr0ster/mcp-abap-adt/claude-md"><img src="https://agentmods.dev/badge/instructions/fr0ster/mcp-abap-adt/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/fr0ster/mcp-abap-adt/claude-md"><img src="https://agentmods.dev/badge/instructions/fr0ster/mcp-abap-adt/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 | $0.06004 | $0.06004 |
| Opus 5.5 | $0.02402 | $0.02402 |
| Sonnet 5.5 | $0.01201 | $0.01201 |
| Haiku 4.5 | $0.00600 | $0.00600 |
Grade A, and why
mcp-abap-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 5d 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 — 403 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP ABAP ADT - Development Guide
Testing
Integration Tests
Integration tests run against a real SAP system. Two modes:
- Soft mode (default,
integration_hard_mode.enabled: false): calls handlers directly, no MCP subprocess. - Hard mode (
integration_hard_mode.enabled: true): spawns full MCP server via stdio, calls tools through MCP protocol.
Strategy: Run soft mode for mass regression testing. Use hard mode only for targeted verification of recent changes.
Shared objects: Before the first test run, create shared SAP objects (tables, CDS views, service definitions, classes) that some tests depend on:
npm run shared:setup # first run only, persists across test runs
npm run shared:check # verify they exist
Important: Shared object setup and SAP environment verification require collaboration with the user. Don't try to automate everything — run shared:setup once, show the result, and ask the user to verify activation in ADT. If activation fails, ask the user what they see rather than retrying blindly.
Running integration tests: Always save full output to a log file — do NOT truncate with tail. Tests take 15-25 minutes; use timeout 1800 (30 min) or run_in_background with no timeout truncation. This avoids re-running long tests just to see errors.
# Soft mode (mass run) — save full log
npm run test:integration 2>&1 | tee /tmp/integration-test.log
# Hard mode (targeted, in test-config.yaml set integration_hard_mode.enabled: true)
npm test -- --testPathPatterns=<specific-test>
Test Configuration
All test parameters live in tests/test-config.yaml (gitignored). The template (tests/test-config.yaml.template) works out of the box with sensible defaults.
Setup:
cp tests/test-config.yaml.template tests/test-config.yaml
# Edit ONLY the lines marked "# ← CHANGE"
Required changes (marked # ← CHANGE):
environment.env— session .env file name ("your-system.env","another-system.env") from standard sessions folderenvironment.system_type—"onprem","cloud", or"legacy"environment.connection_type—"http"(default) or"rfc"environment.default_package— dev package (ZMCP_TEST,$TMP)environment.default_transport— transport request or""for local packagesshared_dependencies.package— package for shared test objectsshared_dependencies.software_component—"LOCAL","HOME", etc.
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.
- 5d ago Changed · +27 lines · +456 tokens per session 31e0544e8699
- 15d ago Changed · +63 lines · +936 tokens per session 3da52e8beff0
- 16d ago Changed · +35 lines · +423 tokens per session 68a414694245
- 29d ago Changed · +49 lines · +829 tokens per session af6e42f0b1d5
- 1mo ago Changed · +106 lines · +1,722 tokens per session 35e780c5482f
- 1mo ago Changed · +47 lines · +679 tokens per session 048f776f03ca
- 1mo ago First seen · 76 lines · 959 tokens per session scan A af0d5eba247a
mcp-abap-adt CLAUDE.md is an instructions file published in the GitHub repository fr0ster/mcp-abap-adt (100 stars, last pushed today), licensed Apache-2.0. It adds 6,004 tokens to every session, about $0.0240 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 2026-08-30.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.