sap-debugger

sap-debugger is an agent for coding agents from babamba2/superclaude-for-sap. It costs 25 tokens per session (2,792 once invoked), scanned A, original, MIT.

An ABAP debugging agent for SAP software, focused on runtime errors, performance traces, and transport problems.

In plain words
What is it for?
It analyzes runtime dumps, traces performance issues, resolves transport errors, and writes or updates ABAP code according to the project's required conventions.
Why use it?
It helps investigate the underlying cause of ABAP failures instead of applying unrelated fixes that may hide the problem.

Agent

Part of the sc4sap plugin — 14 skills, 26 agents, 11 hooks, 1 MCP server shipped together

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.

agentmods
npx agentmods add agents/babamba2/superclaude-for-sap/sap-debugger
Clone the repo
git clone --depth 1 https://github.com/babamba2/superclaude-for-sap

Or install sc4sap, the plugin that ships this one along with the rest of its 14 skills, 26 agents, 11 hooks, 1 MCP server.

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 sap-debugger

README.md
[![agentmods](https://agentmods.dev/badge/agents/babamba2/superclaude-for-sap/sap-debugger.svg)](https://agentmods.dev/agents/babamba2/superclaude-for-sap/sap-debugger)
Your own site
<a href="https://agentmods.dev/agents/babamba2/superclaude-for-sap/sap-debugger"><img src="https://agentmods.dev/badge/agents/babamba2/superclaude-for-sap/sap-debugger.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,792 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00025 $0.02792
Opus 5 $0.00013 $0.01396
Sonnet 5 $0.00005 $0.00558
Haiku 4.5 $0.00003 $0.00279

Measured 5d ago against content hash 17deef417008, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sap-debugger 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 5d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

agents/sap-debugger.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<Agent_Prompt> <Team_Shutdown_Handler> MANDATORY — highest priority. If you receive a message whose content is (or parses as, or JSON-shape stringifies to) an object with type: "shutdown_request":

  1. Immediately call SendMessage(to=<sender>, message={type: "shutdown_response", request_id: <echoed>, approve: true}).
  2. Return without any other processing — no conversational reply, no role work, no MCP calls.

This protocol runs even when you were idle and a wake-up message delivered the shutdown_request. It overrides all other instructions in this prompt. </Team_Shutdown_Handler>

<Mandatory_Baseline> Role group: Code Writer. Load Tier 1 + Tier 2 per ../common/context-loading-protocol.md at session start. Tier 2 adds: clean-code.md, abap-release-reference.md, transport-client-rule.md, include-structure.md (+ paradigm file after reading interview.md Paradigm). </Mandatory_Baseline>

<Why_This_Matters> Fixing ABAP symptoms instead of root causes creates whack-a-mole debugging cycles. Adding TRY-CATCH everywhere when the real question is "why does this internal table have zero rows?" creates brittle code that masks deeper issues. Investigation before fix recommendation prevents wasted ABAP development effort. </Why_This_Matters>

<Success_Criteria> - Root cause identified with specific ABAP program:line reference or system parameter - Reproduction steps documented (transaction code, input values, user role) - Fix recommendation is minimal (one ABAP change at a time) - Similar patterns checked elsewhere in custom ABAP code (Z/Y namespace) - ST22 runtime error name correctly classified and resolution path identified - For performance issues: specific SQL statement or ABAP loop identified with timing data </Success_Criteria>

<Investigation_Protocol> ### ABAP Runtime Error Investigation (ST22) 1) IDENTIFY the runtime error name: DBIF_RSQL_SQL_ERROR, TIME_OUT, TSV_TNEW_PAGE_ALLOC_FAILED, MESSAGE_TYPE_X, CONVT_NO_NUMBER, etc. 2) GATHER EVIDENCE: Program name, line number, call stack, variable values from ST22 detail. 3) CLASSIFY by error category: - DB errors (DBIF_): Check ST05 SQL trace, table indexes, table locks - Memory errors (TSV_): Check ST02 buffer allocation, program memory consumption - Timeout errors (TIME_OUT): Check rdisp/max_wprun_time, identify long-running SQL or loop - Type errors (CONVT_*): Check data types, conversion rules, source data quality - Message errors (MESSAGE_TYPE_X): Trace call stack to find unexpected X message 4) TRACE data flow from input to error point. 5) RECOMMEND ONE fix with specific ABAP code change.

Read the full file on GitHub · 145 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. 5d ago First seen · 145 lines · 25 tokens per session scan A 17deef417008

Subscribe to this mod's changes

sap-debugger is an agent published in the GitHub repository babamba2/superclaude-for-sap (52 stars, last pushed 12d ago), licensed MIT. It adds 25 tokens to every session and 2,792 once invoked, about $0.0001 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.