agentmods.dev

mcp-sap-gui: Instructions file for Codex

AGENTS.md

mcp-sap-gui AGENTS.md is an instructions file for Codex, OpenCode from kts982/mcp-sap-gui. It costs 1,172 tokens per session, scanned A, original, MIT.

A repository instruction file for coding agents working on a Python server that controls SAP GUI on Windows. SAP GUI is software for using SAP business applications, and the file describes the project layout, setup, tests, and working rules.

In plain words
What is it for?
Use it when developing, testing, or reviewing the mcp-sap-gui repository, especially its SAP GUI connections, sessions, and transaction controls.
Why use it?
It gives an agent project-specific rules and technical context before it changes code. It also records platform limits and how the test suite handles Windows-only components.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is kts982/mcp-sap-gui's own configuration. It tells Codex and OpenCode how to work on mcp-sap-gui 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 mcp-sap-gui configures →

not rated 41repo +1 changed yesterday A scan 1,172 tokens original MIT
View source ↗ kts982/mcp-sap-gui pypi.org
Reuse

Borrowing it

Nothing to install: this file belongs to kts982/mcp-sap-gui. 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/kts982/mcp-sap-gui/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/kts982/mcp-sap-gui

Made for: Codex, OpenCode.

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 mcp-sap-gui AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kts982/mcp-sap-gui/agents-md/github.svg)](https://agentmods.dev/instructions/kts982/mcp-sap-gui/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/kts982/mcp-sap-gui/agents-md"><img src="https://agentmods.dev/badge/instructions/kts982/mcp-sap-gui/agents-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 mcp-sap-gui AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kts982/mcp-sap-gui/agents-md"><img src="https://agentmods.dev/badge/instructions/kts982/mcp-sap-gui/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,172 This file is loaded in full into every session.
When invoked 1,172 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 $0.01172 $0.01172
Opus 5.5 $0.00469 $0.00469
Sonnet 5.5 $0.00234 $0.00234
Haiku 4.5 $0.00117 $0.00117

Measured yesterday against content hash 784ff169e83f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-sap-gui AGENTS.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.

AGENTS.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guide for coding agents (and people) working on this repository. Process rules (scope, what a pull request should contain, security reports) are in CONTRIBUTING.md; this file adds the technical ground rules. Keep personal notes in a gitignored place (.dev/, .claude/). Claude Code users can import this file from their own CLAUDE.md with @AGENTS.md.

What this is

An MCP server (FastMCP 4.x, Python 3.11+) that drives SAP GUI for Windows through the SAP GUI Scripting API over COM (pywin32). It runs only on Windows; the test suite runs anywhere, with COM mocked.

Layout

  • src/mcp_sap_gui/server.py: the FastMCP app: the tools, the server instructions, the command-line flags and the middleware.
  • src/mcp_sap_gui/sap_controller.py: SAPGUIController, composed from the mixins in fields.py, tables.py, trees.py and discovery.py on top of controller.py (SAPGUIControllerBase: connecting, sessions, screen info, GetObjectTree reads).
  • session_manager.py: the SAP session bound to each MCP session, and the single COM thread.
  • confirmation.py: confirmation points and the dialog helpers. policy.py: the transaction policy (presets, policy file). audit.py: the JSON audit log. strict.py: --strict-errors. preview.py: sap_preview. prompts.py: workflow guides.
  • tests/: pytest, no SAP GUI needed.
  • docs/: user documentation, one page per task; docs/TOOLS.md lists every tool. README.md is also the PyPI project page, so it links by absolute GitHub URL (https://github.com/kts982/mcp-sap-gui/blob/master/...); scripts/check_docs.py checks those links against the local files.

Setup and checks

The same commands CI runs (Windows, Python 3.11 to 3.14):

uv sync --extra dev --extra screenshots --extra code-mode --extra apps
uv run ruff check src tests
uv run pytest -q
python scripts/check_docs.py

Ground rules

Safety

  • Never weaken a safety gate to make something work: the transaction policy, read-only mode, the Save confirmation (F11, the Save toolbar button, popup answers that may save) and the confirmation points. They fail closed: when a client cannot show the dialog, the call is refused.
  • A tool that changes SAP state is registered with annotations=_WRITE and tags=_TAGS_WRITE; a read tool with _READ_ONLY and _TAGS_READ. The tags drive the policy profiles and the all_writes confirmation point.
  • Every tool that can write the command field (wnd[0]/tbar[0]/okcd) checks the value against the transaction policy. Strip command prefixes such as /n with str.removeprefix, never lstrip.

Read the full file on GitHub · 62 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 · +1 lines · +44 tokens per session 784ff169e83f
  2. 10d ago First seen · 61 lines · 1,128 tokens per session scan A b6a0a686004d

Subscribe to this mod's changes

mcp-sap-gui AGENTS.md is an instructions file published in the GitHub repository kts982/mcp-sap-gui (41 stars, last pushed yesterday), licensed MIT. It adds 1,172 tokens to every session, about $0.0047 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 2026-10-20.

PythonTestingWriting and docsai-agentsautomationmcpmodel-context-protocolsap
Related

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).

microsoft/vscode · 9,715 tokens

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 · 7,461 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

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).

microsoft/vscode · 2,750 tokens

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.

denoland/deno · 3,077 tokens