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.
npx agentmods add commands/vigneshbarani24/sap-superpowers/sap-debuggit clone --depth 1 https://github.com/vigneshbarani24/sap-superpowersWrote 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.
[](https://agentmods.dev/commands/vigneshbarani24/sap-superpowers/sap-debug)<a href="https://agentmods.dev/commands/vigneshbarani24/sap-superpowers/sap-debug"><img src="https://agentmods.dev/badge/commands/vigneshbarani24/sap-superpowers/sap-debug.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00029 | $0.00576 |
| Opus 5 | $0.00015 | $0.00288 |
| Sonnet 5 | $0.00006 | $0.00115 |
| Haiku 4.5 | $0.00003 | $0.00058 |
Grade A, and why
sap-debug 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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sap-debug
Invokes the troubleshooting skill to run a structured, evidence-driven root cause analysis on any SAP issue. Prevents premature conclusions and enforces a systematic diagnostic path before any fix is attempted.
Usage
/sap-debug [description of issue]
Arguments:
[description of issue]— Describe the symptom, error message, transaction, or scenario. Include any error codes, dump IDs, or affected objects if known.
Examples:
/sap-debug ABAP dump CALL_FUNCTION_NOT_FOUND in program ZVENDOR_PROCESS/sap-debug Sales orders stuck in credit check — VKM1 shows hundreds of blocked orders/sap-debug Integration Suite iFlow failing intermittently with HTTP 503 on target system
What Happens
- The
troubleshootingskill is activated with your issue as input. - The skill enforces a structured diagnostic loop — symptom capture, scope determination, hypothesis generation, evidence collection, and root cause confirmation.
- Hard gates block progression until each stage is verified with evidence (logs, dumps, tcode output).
- If the issue touches code, the
sap-revieweragent is dispatched for code-level analysis. - If the issue involves authorizations, the
sap-security-auditoragent is dispatched in parallel. - A root cause is confirmed only when the evidence chain is complete — not when a plausible explanation is found.
Output
A Root Cause Analysis (RCA) document written to the working directory, containing:
| Section | Content |
|---|---|
| Issue Summary | Symptom, affected objects, scope, severity |
| Diagnostic Path | Steps taken, evidence collected, hypotheses tested |
| Root Cause | Confirmed cause with supporting evidence |
| Fix Applied | Exact change made (code, config, customizing) |
| Verification | How the fix was confirmed — test results, logs |
| Prevention | What to change to prevent recurrence |
Example
/sap-debug MIRO posting fails with error FF805 — tax code not allowed for company code
> Activating troubleshooting skill...
> Stage 1: Symptom confirmed — FF805 raised in FI-IV-IV, affects company code 1000 only
> Stage 2: Scope — all MIRO postings with tax code V1, started after transport TR1234 imported
> Stage 3: Evidence collected — FTXP config, OBY6 settings, FI customizing transport log
> Stage 4: Root cause confirmed — tax procedure TAXGB missing V1 condition type after transport
> Generating RCA document...
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.
- 5d ago First seen · 58 lines · 29 tokens per session scan A 9a609ad2dc29
sap-debug is a command published in the GitHub repository vigneshbarani24/sap-superpowers (9 stars, last pushed 12d ago), licensed MIT. It adds 29 tokens to every session and 576 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 2026-08-31.
Other commands, from other repositories
datasphere-cli
SAP Datasphere CLI command reference with examples.
datasphere-mcp-tools
List all available SAP Datasphere MCP tools with descriptions and usage examples.
widget-validate
Validates SAC custom widget JSON metadata and JavaScript structure for correctness and best practices.
sac-planning-checklist
Generate a comprehensive checklist for SAC planning implementation projects.
seamless-planning-guide
Quick guidance on implementing Seamless Planning with SAP Datasphere.
cap-setup-wizard
Interactive guide for setting up new CAP projects with framework and database selection.