agentmods.dev

aibap.mcp: Instructions file for Claude Code

CLAUDE.md

aibap.mcp CLAUDE.md is an instructions file for Claude Code from Hochfrequenz/aibap.mcp. It costs 5,478 tokens per session, scanned A, original, MIT.

Repository instructions for aibap.mcp, a Go server that exposes SAP development-tool operations to Claude.

In plain words
What is it for?
Developing and checking SAP development-tool integrations, including unit tests and optional tests against real SAP systems.
Why use it?
They define how to build, test, lint, format, and scope the server, including a rule against accessing SAP business data.

Instructions file for Claude Code

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

This is Hochfrequenz/aibap.mcp's own configuration. It tells Claude Code how to work on aibap.mcp 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 aibap.mcp configures →

not rated 7repo yesterday A scan 5,478 tokens original MIT
View source ↗ Hochfrequenz/aibap.mcp
Reuse

Borrowing it

Nothing to install: this file belongs to Hochfrequenz/aibap.mcp. 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/Hochfrequenz/aibap.mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Hochfrequenz/aibap.mcp

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 aibap.mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hochfrequenz/aibap.mcp/claude-md/github.svg)](https://agentmods.dev/instructions/hochfrequenz/aibap.mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/hochfrequenz/aibap.mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/hochfrequenz/aibap.mcp/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 aibap.mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/hochfrequenz/aibap.mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/hochfrequenz/aibap.mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,478 This file is loaded in full into every session.
When invoked 5,478 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.05478 $0.05478
Opus 5 $0.02739 $0.02739
Sonnet 5 $0.01096 $0.01096
Haiku 4.5 $0.00548 $0.00548

Measured 8d ago against content hash 7438d2bc9c14, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

aibap.mcp 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 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.

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 · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project Overview

MCP server that exposes SAP ADT (ABAP Development Tools) operations as tools for Claude. Go project using mcp-go for the MCP protocol and stdio transport.

Scope guardrail: this is an ADT development-tooling server. It must not be extended into reading application tables, exporting business data, running SQL against the backend, or agentic workflows over business data — see the intended-scope warning and SAP API Policy in README.md. Push back on feature requests that cross that line rather than implementing them.

Build & Run

  • Build: make build (produces mcp-server-abap; plain go build . also works)
  • Lint: make lint (runs golangci-lint run ./...). CI additionally enables dupl, goconst, gocyclo — see .github/workflows/golangci-lint.yml.
  • Format: gofmt -w .

Testing

  • Test-driven: Write unit tests before or alongside implementation, not after.
  • Unit tests: go test ./... — must always pass before committing.
  • Integration tests (this repo): go test -tags integration -v -count=1 ./tools/... — local-only, behind //go:build integration. Real SAP via ~/.config/sap-mcp/systems.json, requires VPN + Z_ADT_MCP_TEST package installed on target system(s). Covers the MCP wrapper layer only (adtler owns the ADT HTTP/XML/auth layer). Target systems via MCP_INTEGRATION_SYSTEMS env var (default hfq,s4u).
  • Integration tests (adtler): live in adtler and cover the ADT HTTP client, XML marshalling, customizing export, and OAuth2. Clone adtler to run them.
  • Reproducer verification (bump-time): adtler bump PRs run the reproducer snippet from each linked blocked-by-adtler issue against the live target system(s). This is narrower than adtler's integration suite — one MCP tool call per fix claim — and is the only live test we run at the aibap.mcp boundary. Format and flow: see "Cross-Repo Issue Tracking (adtler)".
  • Fix before creating: When a SAP object (transport, program, etc.) has a problem, fix the existing one first. Don't keep creating new objects to work around issues.
  • Coverage thresholds (enforced in CI per package): config 75%. tools/logging/cmd are covered by unit tests but no minimum is enforced — these packages are thin wrappers around adtler. The adt/auth packages have their own thresholds in adtler's CI.
  • Test package dependency (for adtler integration tests): SAP package Z_ADT_MCP_TEST on the target system. Install from Hochfrequenz/Z_ADT_MCP_TEST.

Read the full file on GitHub · 179 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 · 179 lines · 5,478 tokens per session scan A 7438d2bc9c14

Subscribe to this mod's changes

aibap.mcp CLAUDE.md is an instructions file published in the GitHub repository Hochfrequenz/aibap.mcp (7 stars, last pushed yesterday), licensed MIT. It adds 5,478 tokens to every session, about $0.0274 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.

abapadtaibapmcpsap
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