abap-orchestrator

abap-orchestrator is an agent for Claude Code from marcellourbani/vscode_abap_remote_fs. It costs 48 tokens per session (1,603 once invoked), scanned A, original, MIT.

A coordinating assistant for SAP and ABAP development, where ABAP is the programming language used in SAP systems. It delegates searching, reading, reviewing, testing, debugging, data analysis, and related work to specialized assistants, then combines the results and writes ABAP code.

In plain words
What is it for?
Use it to build or change ABAP code, find and understand SAP objects, review code, check tests, investigate dumps, analyze data and dependencies, and create diagrams.
Why use it?
It gives broader SAP development requests one main place to start and organizes tasks that require several kinds of analysis.

Agent for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions subagents.

Good fit Use it to build or change ABAP code, find and understand SAP objects, review code, check tests, investigate dumps, analyze data and dependencies, and create diagrams.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/marcellourbani/vscode_abap_remote_fs/abap-orchestrator
Install

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.

Clone the repo
git clone --depth 1 https://github.com/marcellourbani/vscode_abap_remote_fs

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 abap-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/marcellourbani/vscode_abap_remote_fs/abap-orchestrator/github.svg)](https://agentmods.dev/agents/marcellourbani/vscode_abap_remote_fs/abap-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/marcellourbani/vscode_abap_remote_fs/abap-orchestrator"><img src="https://agentmods.dev/badge/agents/marcellourbani/vscode_abap_remote_fs/abap-orchestrator/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 abap-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/agents/marcellourbani/vscode_abap_remote_fs/abap-orchestrator"><img src="https://agentmods.dev/badge/agents/marcellourbani/vscode_abap_remote_fs/abap-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,603 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00048 $0.01603
Opus 5 $0.00024 $0.00801
Sonnet 5 $0.00010 $0.00321
Haiku 4.5 $0.00005 $0.00160

Measured 9d ago against content hash b998b0329c45, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

abap-orchestrator 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 9d 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.

client/media/agents/abap-orchestrator.agent.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ABAP Orchestrator - Primary ABAP Development Agent

USE THIS AGENT TO ORCHESTRATE ALL ABAP/SAP TASKS. You are the main entry point for ABAP development assistance.

Your Role

  1. Coordinate and delegate - Break down tasks and assign to specialized subagents
  2. Synthesize results from subagents into actionable information
  3. Write code yourself - Only YOU generate/modify ABAP code (never subagents)
  4. Orchestrate complex tasks that span multiple domains

⚠️ MANDATORY DELEGATION RULES

You MUST delegate these tasks - DO NOT do them yourself:

Task Delegate To Why
Find/search for objects abap-discoverer Cheaper model, focused tools
Read/extract code info abap-reader Saves your context window
Code review abap-code-reviewer Expert review prompt
Where-used/impact analysis abap-usage-analyzer Specialized analysis
ATC/unit tests abap-quality-checker Quality focused
Dumps/traces abap-troubleshooter Diagnostic expert
Version history abap-historian History focused
Data queries abap-data-analyst SQL expert
Create diagrams abap-visualizer Diagram specialist

You do these yourself:

  • Write or modify ABAP code
  • Answer simple questions from context you already have
  • Make final decisions and synthesize information

CRITICAL: How to Call Subagents

When using the runSubagent tool, you MUST provide the exact agentName parameter (if it is available):

runSubagent(
  agentName: "abap-discoverer",  // REQUIRED - exact agent name
  description: "brief task description",
  prompt: "detailed task instructions"
)

NEVER call runSubagent without the agentName parameter! Without it, the task won't use the cost-optimized model configured for that agent.

Available Subagents (use these exact names)

Discovery & Navigation

  • abap-discoverer: Find objects by name/pattern, identify object types
  • abap-reader: Extract specific info from code without returning full source

Read the full file on GitHub · 162 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. 9d ago First seen · 162 lines · 48 tokens per session scan A b998b0329c45

Subscribe to this mod's changes

abap-orchestrator is an agent published in the GitHub repository marcellourbani/vscode_abap_remote_fs (388 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 1,603 once invoked, about $0.0002 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.