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/boxlogodev/sapstack/sap-transport-debuggit clone --depth 1 https://github.com/BoxLogoDev/sapstackWhat 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 | $0.00037 | $0.01430 |
| Opus 5 | $0.00018 | $0.00715 |
| Sonnet 5 | $0.00007 | $0.00286 |
| Haiku 4.5 | $0.00004 | $0.00143 |
Grade A, and why
sap-transport-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 2d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
STMS Transport 디버그 파이프라인
입력: $ARGUMENTS
🎯 목표
Transport Request(TR) import 실패 시 체계적으로 원인을 추적하고 수정합니다. 한국 현장에서 흔한 한글 Short Text 이슈부터 cross-client 의존성까지 커버합니다.
🔒 안전 규칙
- 운영 환경(PRD)으로 강제 push 금지
- tp force 옵션은 최후의 수단
- 의존 객체 미포함 시 추가 TR 생성 권장
Step 1. TR 상태 확인
- STMS → Import Queue → 대상 시스템 선택
- 대상 TR 찾기 → 상태 확인:
- 대기 (queued)
- 진행 중 (in progress)
- 실패 (error)
- SE09/SE10: Transport Organizer에서 TR 상세
- Return Code (RC):
- 0~4: OK/Warning (무시 가능)
- 6: Warning (검토 권장)
- 8: Error (원인 분석 필수)
- 12: Critical (시스템 점검)
- 16+: Severe (수동 개입)
Step 2. tp 로그 분석
위치: /usr/sap/trans/log/
| 파일 | 내용 |
|---|---|
ALOG<YY>.<SID> |
전체 액션 로그 |
ULOG<YY>.<SID> |
사용자 작업 |
SLOG<YY>.<SID> |
Short log (헤더) |
<STEP>_<TR>.log |
Step별 상세 |
주요 Step 로그
DICT_<TR>.log: DDIC Dictionary 활성화DIEX_<TR>.log: Data Dictionary ExportGEN_<TR>.log: 프로그램 생성DARG_<TR>.log: Distribute ABAP Runtime Globals
명령어 (OS 레벨, BC 권한 필요)
cd /usr/sap/trans/log
ls -lt | head # 최신 로그
grep -i error <logfile>
Step 3. Import 에러 유형별 진단
Error Type A: DDIC 활성화 실패
- Dictionary 객체 (Table/Structure/Data Element) 의존성 문제
- SE11: 해당 객체 활성화 시도
- 의존 객체가 다른 TR에 있으면 순서 조정
Error Type B: Program Generation 실패
- ABAP 소스 오류
- SE80: 객체 열어서 구문 확인
- SLIN: Extended program check
Error Type C: 한글 Short Text 변환 실패 (한국 현장 빈번)
- 증상:
CONVERSION_ERROR또는CODEPAGE_CONVERT - 원인:
- Non-Unicode → Unicode 전환 미완료
- tp 버전 mismatch
NLS_LANG미설정 (Oracle)
- 해결:
- SAP Note 2452523 확인
- tp kernel upgrade
NLS_LANG=KOREAN_KOREA.AL32UTF8설정
Error Type D: Cross-client 의존성
- 100번 client에서 개발 → 200번 client에 import 시 실패
- Customizing TR이 Workbench TR과 분리
- SCC1: Client-specific copy
Error Type E: Object Lock (다른 TR 소유)
- 같은 객체가 다른 TR에 잠김
- SE03 → Object Directory Entry
- Owner TR release 후 재import
Step 4. 복구 옵션
4-1. Re-import (동일 TR)
- STMS → Queue → Request 선택 → Import Again
- 오류가 해소되었을 경우
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.
- 2d ago First seen · 174 lines · 37 tokens per session scan A 074f18729c05
sap-transport-debug is a command published in the GitHub repository BoxLogoDev/sapstack (18 stars, last pushed 2d ago), licensed MIT. It adds 37 tokens to every session and 1,430 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.
Other commands, from other repositories
eval-author
Draft a new eval case (eval/cases/ .json) + scaffold its golden folder, goldenpending until captured on the VM.
eval-improve
Work the eval-loop corpus — rank failure clusters, fix the top actionable defect, validate against held-out, open a PR.
eval-run
Run an eval case end-to-end on the VM (implement → build → score → record → roll back). VM/full-mode only.
research-l2
Executes Phases 1-3 of the L2 process of the abapwiki knowledge base on a slice: launches the abap-functional-researcher sub-agent (gap discovery + multi-source auto-research: wiki -> raw/docs -> MCP abap-fs on the system read-only -> standard knowledge), ingests gaps and evidence, and generates questionnaires for…
ingest-l0
L0 bootstrap of the abapwiki knowledge base: creates stubs for all custom objects from the TADIR. Use this skill to initialize the repo from scratch or to ingest a new TADIR export. Deterministic operations (no LLM sub-agent), idempotent.
ingest-l1
L1 analysis loop for the abapwiki knowledge base: for each batch it launches the abap-analyzer sub-agent in parallel, then the adversarial judge abap-deepcheck (separate session), applies only the analyses that pass the fail-closed gate, and commits. Resumes exactly after an interruption. Use this skill to document…