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-ibp-forecast-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 | $0.00039 | $0.00741 |
| Opus 5 | $0.00019 | $0.00370 |
| Sonnet 5 | $0.00008 | $0.00148 |
| Haiku 4.5 | $0.00004 | $0.00074 |
Grade A, and why
sap-ibp-forecast-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.
What it actually says
/sap-ibp-forecast-debug — IBP 수요 예측 디버그
사용 시점
- 통계 예측 (Statistical Forecast)이 생성 안 됨
- 예측이 비현실적 (음수/0/극단치)
- 시즌성/추세가 안 잡힘
- Auto-ML 알고리즘 선택 이상
진단 체크리스트
Step 1: Planning Operator 확인
- IBP Web UI → Configuration → Planning Areas → [Your PA]
- Operators 탭 → Forecast Operator 정의
- 다음 확인:
- Operator 활성?
- Input/Output Key Figure 매핑 정확?
- Time horizon (n weeks/months)?
- Forecast Model 어떤 거?
Step 2: Forecast Model 점검
- Models → [Your Forecast Profile]
- 다음 확인:
- 알고리즘 적합? (Croston for intermittent, Triple ES for seasonal+trend)
- 파라미터 (alpha, beta, gamma) 적절?
- Horizon ≥ History/3 권장
- Outlier detection 활성?
Step 3: 히스토리 데이터
- Planning View에서 History Key Figure 확인
- 다음 확인:
- 최소 12-24 주기 히스토리 확보?
- 결측치 (gap) 있나? (있으면 0으로 처리됐는지 vs 매핑 실패)
- 단위 일관성? (단가 변경, 단위 변경)
Step 4: 마스터 매핑
- Master Data → Product / Location / Customer 확인
- 다음 확인:
- Planning Object 정의된 조합 (e.g., Product × Location) 활성?
- 매핑 깨진 객체 없음? (S/4 ↔ IBP)
Step 5: 실행 로그
- Application Jobs → 최근 Forecast Run
- 다음 확인:
- 상태: Success / Warning / Failed?
- 실행 시간 평소 대비?
- 처리한 Combination 수?
- Warning 메시지 (예: "no history", "model degenerate")?
흔한 원인
| 원인 | 증상 | 해결 |
|---|---|---|
| History 부족 | 0 또는 NaN 예측 | 최소 12 주기 보장 |
| Outlier | 폭발적 예측 | Outlier detection 활성 |
| 매핑 오류 | 일부 조합 누락 | External Codes 재매핑 |
| Operator 비활성 | 예측 안 생성 | Operator activate |
| Time profile 불일치 | period shift | Time profile 정합성 |
Output 형식 (Quick Advisory mode)
### Issue
[증상 요약]
### Root Cause
[원인]
### Check (T-code/UI + Field)
- Planning Area: ...
- Operator: ...
- ...
### Fix (Steps)
1. ...
2. ...
### Prevention
- ...
### SAP Note (if known)
- ...
복잡한 경우 (가설 2+ 가능) → /sap-session-start 호출.
참조
plugins/sap-ibp/skills/sap-ibp/SKILL.mdagents/sap-ibp-consultant.md
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 · 95 lines · 39 tokens per session scan A 954cee144a7b
sap-ibp-forecast-debug is a command published in the GitHub repository BoxLogoDev/sapstack (18 stars, last pushed 3d ago), licensed MIT. It adds 39 tokens to every session and 741 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-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.
eval-author
Draft a new eval case (eval/cases/ .json) + scaffold its golden folder, goldenpending until captured on the VM.
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…
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.