A read-only workflow for investigating SAP short dumps, which are recorded runtime failures in SAP. It groups related failures, reads their details, finds the source line involved, and prioritizes the causes.

Use it to review recent ST22 dumps, group recurring ABAP failures, inspect the termination details and source code, and get a suggested fix for each dump family.

It turns a large list of technical crash reports into a shorter action list organized by likely root cause.

dump-triage — Skill for Claude Code and Codex by yzonur/sap-adt-mcp

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.

Any agent

npx skills add yzonur/sap-adt-mcp --skill dump-triage

Clone the repo

git clone --depth 1 https://github.com/yzonur/sap-adt-mcp

Made for: Claude Code, Codex.

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/skills/yzonur/sap-adt-mcp/dump-triage/github.svg)](https://agentmods.dev/skills/yzonur/sap-adt-mcp/dump-triage)

Your own site

<a href="https://agentmods.dev/skills/yzonur/sap-adt-mcp/dump-triage"><img src="https://agentmods.dev/badge/skills/yzonur/sap-adt-mcp/dump-triage/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/skills/yzonur/sap-adt-mcp/dump-triage"><img src="https://agentmods.dev/badge/skills/yzonur/sap-adt-mcp/dump-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,205 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	$0.00107	$0.01205
Opus 5.5	$0.00043	$0.00482
Sonnet 5.5	$0.00021	$0.00241
Haiku 4.5	$0.00011	$0.00120

Measured 2mo ago against content hash 38676a4d8282, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dump-triage 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 2mo 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.

skills/dump-triage/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dump Triage

Turn a pile of ST22 short dumps into a short, prioritized action list. The workflow is read-only end to end, so it is safe to point at production systems.

Prerequisites

sap-adt-mcp ≥ 0.8.1 connected to the target system (adt_ping to verify).
NetWeaver 7.50+ or S/4HANA recommended — the ADT runtime-dumps feed (/sap/bc/adt/runtime/dumps) is not exposed on older releases. If adt_list_dumps 404s, the system doesn't serve the feed; tell the user to use ST22 directly and stop.
SAP user authorizations: runtime-dump display (typically S_ADT / basis display roles). No write authorizations needed.
Read-only mode: fully supported. This skill never writes. If a fix is agreed and the user wants it applied, that's a separate (write-mode) edit via adt_set_source — confirm explicitly before leaving read-only territory.
Date filters use YYYYMMDD on on-prem systems (e.g. 20260611).

Workflow

1. Collect

adt_list_dumps with a sensible window — default to the last 24h unless the user says otherwise (from: <yesterday YYYYMMDD>). Filter by user only when asked; note the user filter is enforced client-side. Respect maxResults (default 20; raise for a weekly review).

2. Group before reading

Don't fetch every dump's detail. Group the list by (runtimeError, program) — that pair defines a dump family. 200 TYPELOAD_NEW_VERSION entries from one job are one problem, not 200. Rank families by:

frequency (count in window),
blast radius (PRD > QAS > DEV; batch users hitting it every minute),
severity of the error class (data-loss-ish errors like CONVT_NO_NUMBER, ITAB_DUPLICATE_KEY in update tasks rank above one-off TIME_OUTs).

3. Deep-read the top families

For the top 3–5 families: adt_get_dump with the family's most recent dump id. The default chapter set (shortText, whatHappened, errorAnalysis, howToCorrect, whereTerminated, sourceCodeExtract) is usually enough; request more chapters only when the analysis is inconclusive.

Read the full file on GitHub · 99 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.

2mo ago First seen · 99 lines · 107 tokens per session scan A 38676a4d8282

Subscribe to this mod's changes

dump-triage is a skill published in the GitHub repository yzonur/sap-adt-mcp (21 stars, last pushed 7d ago), licensed MIT. It adds 107 tokens to every session and 1,205 once invoked, about $0.0004 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 adt ai-agent anthropic claude developer-tools

dump-triage next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
dump-triageyzonur/sap-adt-mcp	Skill	21	7d ago	MIT	A	107	Claude Code, Codex
systematic-debuggingNousResearch/hermes-agent	Skill	261k	yesterday	MIT	A	16	Claude Code, Codex
cookie-debuggingasgeirtj/system_prompts_leaks	Skill	71k	2d ago	CC0-1.0	A	71	Claude Code, Codex
a11y-debuggingasgeirtj/system_prompts_leaks	Skill	71k	2d ago	CC0-1.0	A	50	Claude Code, Codex
observability-langsmithdavila7/claude-code-templates	Skill	33k	yesterday	MIT	A	44	Claude Code, Codex
bug-reportDonchitos/Claude-Code-Game-Studios	Skill	36k	18d ago	MIT	A	23	Claude Code
bug-triageDonchitos/Claude-Code-Game-Studios	Skill	36k	18d ago	MIT	A	30	Claude Code