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-quarter-closegit 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 | $0.00043 | $0.01290 |
| Opus 5 | $0.00022 | $0.00645 |
| Sonnet 5 | $0.00009 | $0.00258 |
| Haiku 4.5 | $0.00004 | $0.00129 |
Grade A, and why
sap-quarter-close 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SAP 분기 결산 파이프라인
입력: $ARGUMENTS
🎯 목표
분기 결산을 단계별로 실행하며, K-IFRS 공시와 K-SOX 내부통제 요구사항을 함께 만족시킵니다. 월결산(/sap-fi-closing)과 달리 공시 준비와 3개월 누적 조정이 포함됩니다.
🔒 안전 규칙
- 모든 단계는 Test Run 먼저
- 실제 포스팅 전 사용자 명시적 승인
- K-SOX — 실행자 ≠ 승인자 로그 필수
Phase 1 — 환경 확인
질문:
- SAP 릴리스
- 회사코드 + Controlling Area
- 분기 대상 (2026/Q1, 2026/Q2 ...)
- K-IFRS 공시 대상 여부 (상장사)
- 연결재무제표 통합 대상 여부
Phase 2 — 월결산 선행 완료 검증
3개월 각각 월결산 완료 여부 확인:
- OB52: 해당 월 기간 닫힘 상태
- S_ALR_87012301: 미처리 전표 조회
- FBL3N: 주요 계정 잔액 안정성
미완료 발견 시 → /sap-fi-closing로 되돌아가기
Phase 3 — 분기 특화 조정
3-1. 외화평가 — 분기 단위
- FAGL_FC_VAL: 분기말 환율로 재평가 (월결산 대비 큰 조정)
- Test Run → 결과 검토 → 실행
- 환율 유형: BOK 고시일자 (한국은행)
3-2. 자산 감가상각 — 분기 누적 검증
- AFAB: 월별 test run 완료된 상태여야 함
- S_ALR_87011963: 자산 잔액 분기 대비 검증
3-3. GR/IR — 분기 Aging
- MB5S (ECC) / GRIR Fiori (S/4)
- 3개월 이상 노후 항목은 수동 처리 판단
- MR11 Test Run → 청산
3-4. Intercompany — 분기 조정
- F.19: IC Recon (ECC)
- FBICR: IC Recon Reports
- 다수 회사코드 간 불일치 분석
Phase 4 — CO 분기 활동
4-1. 배부 사이클
- KSU5 Assessment 실행 (3개월 모두)
- KSV5 Distribution 실행
- KO88 내부주문 정산 (누적)
4-2. 원가 요소 차이 분석
- KKS1: Variance 계산
- 분기 대비 비정상 증감 탐지
4-3. CO-PA
- KE30: 분기 수익성 보고서
- Top-down 배부 (
KEU5— Costing-based only)
Phase 5 — K-IFRS 공시 준비
5-1. 재무상태표 & 손익계산서
- F.01: Balance Sheet
- F.08: P&L (or S_ALR_87012284)
- Preview 단계에서 분개 검증
5-2. 주석 공시 항목
- 리스(IFRS 16) — Right-of-use assets
- 금융상품(IFRS 9) — 평가·손상
- 수익(IFRS 15) — Performance obligation
- 법인세(IAS 12) — 이연법인세
5-3. 연결재무제표 (해당 시)
- CX2X: EC-CS (ECC)
- S/4 Group Reporting: 통합 reporting 환경
- 회사 간 내부거래 제거
Phase 6 — K-SOX 내부통제 문서화
통제 체크리스트
- 분기 결산 담당자 서명 + 승인자 서명 (분리)
- 비정상 증감 분석 보고서
- 수동 조정 전표 사유서
- SU53 권한 실패 로그 검토
- SM21 시스템 로그 이상 여부
감사 흔적
- S_ALR_87012276: Audit Trail Report
- CHANGEDOCUMENT 테이블 조회
- 분개 승인 워크플로 이력
Phase 7 — 보고 & 공시
- 대표이사 보고
- 감사위원회 보고 (상장사)
- DART 공시 (상장사) — 분기보고서
- 연결보고 (그룹사)
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 · 146 lines · 0 tokens per session scan A e136943ad681
sap-quarter-close is a command published in the GitHub repository BoxLogoDev/sapstack (18 stars, last pushed 2d ago), licensed MIT. It adds 43 tokens to every session and 1,290 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…