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-performance-checkgit 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 | $0.00061 | $0.01644 |
| Opus 5 | $0.00030 | $0.00822 |
| Sonnet 5 | $0.00012 | $0.00329 |
| Haiku 4.5 | $0.00006 | $0.00164 |
Grade A, and why
sap-performance-check 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SAP 성능 점검 파이프라인
입력: $ARGUMENTS (기본값: system — 전체 점검)
🎯 목표
SAP 시스템 성능을 레이어별로 체계적으로 진단합니다:
- OS/Hardware
- Database (HANA/Oracle/DB2)
- SAP Kernel / Work Process
- ABAP / Application Logic
- Network / Client
🔒 안전 규칙
- ST05 SQL Trace는 짧은 세션만 (I/O 부하)
- SE30/SAT Runtime Analysis도 제한 시간 권장
- 운영 환경에서 장시간 trace 실행 금지 (모니터링 영향)
레이어 1 — OS / Hardware
OS 리소스 (ST06)
- ST06: OS 모니터 (CPU, Memory, Disk I/O, Network)
- RZ20 CCMS: 알림 기준 설정
- DB의 데이터 볼륨 성장 추이
Kernel 레벨
disp+work -v: Kernel 패치 레벨dev_w*.log: Work Process 로그 (/usr/sap///work/)disp+work.log: Dispatcher 로그
체크 항목
- CPU 사용률 80% 이하 유지
- Memory swap 거의 없음
- Disk I/O wait < 10%
- Network latency 안정
레이어 2 — Database
HANA (S/4HANA 필수)
- DBACOCKPIT → HANA Administration
- HANA Studio 또는 DBA Cockpit 사용
- 체크:
- Column Store vs Row Store 비율
- Delta merge 상태
- Expensive Statements (HANA Studio → Performance → Expensive Statements)
- Statistics Service 상태
Oracle (ECC)
- DB02 (ECC) / DB02 / DB02_OLD: Tablespace, Table stats
- ST04 (ECC): Oracle performance
- DB13: Backup / Reorg 스케줄
- 체크:
- Cache hit ratio > 95%
- Wait events (top 5)
- Table 통계 최신 여부
Index 건강성
- DB05 (ECC): Index analysis
- ST10: Table call statistics
- Full table scan 빈도
레이어 3 — SAP Kernel / Work Process
Work Process
- SM50: 로컬 WP 상태
- SM66: 전체 서버 WP (분산 환경)
- Running WP 오래 멈춘 것 확인
- Table 컬럼 — 같은 테이블 반복 접근 시 병목 의심
Update / Enqueue
- SM12: Lock entries — 좀비 락
- SM13: Update requests — 실패/대기
- SM21: System log — 경고/오류
메모리 버퍼
- ST02: 주요 버퍼 상태
- Program buffer: hit ratio ≥ 98%
- Table buffer: hit ratio ≥ 95%
- Roll / Paging: extended memory 사용률
- ST03: Workload Analysis — response time 분포
Job 스케줄
- SM37: Background job
- SM36: Job 정의
- 겹치는 job 부하 분산
레이어 4 — ABAP / Application
SQL Trace (ST05)
- ST05 → Activate Trace
- 문제 트랜잭션 실행
- ST05 → Deactivate
- Display Trace → Long runners, Full table scan
- Explain Plan — Index 사용 여부
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 · 207 lines · 61 tokens per session scan A adaa4bb5ec76
sap-performance-check is a command published in the GitHub repository BoxLogoDev/sapstack (18 stars, last pushed 2d ago), licensed MIT. It adds 61 tokens to every session and 1,644 once invoked, about $0.0003 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…