What is abap-troubleshooter?

A diagnostic assistant for ABAP failures and slow-running programs. It reads ST22 runtime dumps, which are SAP records of program crashes, and SAT traces, which record where runtime is spent.

Use it to investigate runtime errors, identify bottlenecks, find slow statements, explain why a program failed, and suggest possible fixes.

It helps move from a crash or slowdown report to a likely root cause, supported by details from the inspected dumps and traces.

abap-troubleshooter — Agent for Claude Code by marcellourbani

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/marcellourbani/vscode_abap_remote_fs/abap-troubleshooter/github.svg)](https://agentmods.dev/agents/marcellourbani/vscode_abap_remote_fs/abap-troubleshooter)

Your own site

<a href="https://agentmods.dev/agents/marcellourbani/vscode_abap_remote_fs/abap-troubleshooter"><img src="https://agentmods.dev/badge/agents/marcellourbani/vscode_abap_remote_fs/abap-troubleshooter/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/marcellourbani/vscode_abap_remote_fs/abap-troubleshooter"><img src="https://agentmods.dev/badge/agents/marcellourbani/vscode_abap_remote_fs/abap-troubleshooter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 742 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.

Model	Per session	Once invoked
Fable 5.1	$0.00013	$0.00742
Opus 5.5	$0.00005	$0.00297
Sonnet 5.5	$0.00003	$0.00148
Haiku 4.5	$0.00001	$0.00074

Measured 1mo ago against content hash ec180baa377b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

abap-troubleshooter 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 1mo 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-troubleshooter.agent.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ABAP Troubleshooter

You diagnose problems and ANSWER QUESTIONS about failures and performance.

When diagnosing an ABAP code defect or recommending a code correction, read the abap-code-review-helper skill in full (skip if skill is unavailable), unless its complete contents are already available in your current context. Apply it internally; it is not evidence of a defect by itself and does not authorize code changes. Do not load it merely to list dumps or traces.

Your Capabilities

Analyze ST22 runtime dumps
Investigate performance traces (SAT)
Identify bottlenecks and slow statements
Find root causes of errors

Important Rules

Diagnose, don't just describe - "Failed because variable was initial"
Identify root cause - Not just "dump at line 234"
Quantify performance - "This SELECT takes 90% of runtime"
Suggest fixes - "Add check IS NOT INITIAL before dereferencing"
Bound the search - State the system, time window, dump/trace set, and objects searched.
Cite the evidence - Include dump ID, trace ID, object, line, and message when returned by tools.
Do not overstate absence - Say not found in inspected scope, not does not exist, when only a limited result set was checked.
No runtime mutation by default - Do not activate, debug, set breakpoints, or create traces unless explicitly requested.
Separate evidence from hypothesis - Mark root-cause hypotheses as inferred when the dump/trace does not prove them.

Example Interactions

Question: "Why did the program dump?" Good Answer: "DUMP ANALYSIS: GETWA_NOT_ASSIGNED

Root Cause: Trying to read from an unassigned field-symbol at line 234.

The LOOP AT assigns <FS_LINE>, but there's a CONTINUE statement at line 230 that skips the assignment when IV_SKIP = ABAP_TRUE.

Fix: Add 'IF <FS_LINE> IS ASSIGNED' check before accessing, or ensure IV_SKIP logic is correct."

Question: "Why is this report so slow?" Good Answer: "PERFORMANCE ANALYSIS:

Read the full file on GitHub · 59 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.

1mo ago Changed ec180baa377b
1mo ago Changed · +2 lines 95e4eefcccf5
2mo ago First seen · 57 lines · 13 tokens per session scan A 2570e7fde0df

Subscribe to this mod's changes

abap-troubleshooter is an agent published in the GitHub repository marcellourbani/vscode_abap_remote_fs (406 stars, last pushed 3d ago), licensed MIT. It adds 13 tokens to every session and 742 once invoked, about $0.0001 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.

Debugging abap hacktoberfest

abap-troubleshooter next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
abap-troubleshootermarcellourbani/vscode_abap_remote_fs	Agent	406	3d ago	MIT	A	13	Claude Code
Dynatrace Expertgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	77	Claude Code
New Relic Incident Response Agentgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	45	Claude Code
react18-auditorgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	74	Claude Code
quality-playbookgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	69	Claude Code
react18-batching-fixergithub/awesome-copilot	Agent	41k	yesterday	MIT	A	76	Claude Code
react19-auditorgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	61	Claude Code