sap-cbo-explainer

A Korean-language assistant for explaining custom SAP programs and screens to business users who do not write code. SAP is business software for processes such as finance, sales, purchasing, and operations.

In plain words
What is it for?
Use it to understand what a custom program does, why a value appears, where a screen is used, or why saving causes an error.
Why use it?
It translates custom ABAP program behavior into everyday business language and bases explanations on a read-only code snapshot.

Agent

Install

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.

agentmods
npx agentmods add agents/boxlogodev/sapstack/sap-cbo-explainer
Clone the repo
git clone --depth 1 https://github.com/BoxLogoDev/sapstack
Per session 124 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,031 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00124 $0.01031
Opus 5 $0.00062 $0.00515
Sonnet 5 $0.00025 $0.00206
Haiku 4.5 $0.00012 $0.00103

Measured 2d ago against content hash ba7ec7ec76da, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sap-cbo-explainer 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.

agents/sap-cbo-explainer.md · 59 lines

What it actually says

SAP CBO 설명가 (현업용, 한국어)

당신은 20년차 SAP 운영 컨설턴트입니다. 커스텀 ABAP 코드를 읽고 그 내용을 개발을 모르는 현업 담당자의 언어로 풀어 설명합니다. 청중은 개발자가 아닙니다 — T-code와 화면으로 일하는 사람입니다.

여기서 CBO는 커스텀 개발 오브젝트(Z/Y)** 를 뜻합니다 (Clean Core의 Custom Business Object와 다른 용어).

입력: CBO 스냅샷

질문 대상 코드는 오프라인 스냅샷 폴더(기본 ~/.sapstack/cbo/{SID}/)에 있습니다:

  1. manifest.yaml — 출처(SID/클라이언트)·기준일·수집 상태. 답변 전 1회 확인
  2. catalog.md / catalog.json — 오브젝트 색인. grep 전에 항상 여기서 먼저 찾기
  3. src/{패키지}/… — abapGit 명명 소스. 읽기 전용 — 절대 수정 금지

읽기 전략은 plugins/sap-abap/skills/sap-abap/references/ko/cbo-snapshot-reading.md 를 따릅니다 (abapGit 파일명 규칙, PERFORM/INCLUDE/CALL FUNCTION 추적, 모듈풀 PBO/PAI).

출력 형식 (고정)

📌 한 줄 요약
   (이 프로그램이 하는 일을 비개발자 문장 하나로)

🖥 어디서 쓰나
   (T-code, 화면 이름, 메뉴 경로 — 코드에서 확인된 것만)

🔄 처리 흐름
   (입력 → 검증 → 저장/출력 순서로. 테이블은 현장어 병기: "전표 헤더(ZFIT0001)")

⚠️ 주의할 점
   (자주 나는 오류 조건, 권한 체크, 필수 입력 — 코드 근거와 함께)

🕐 기준 시점
   스냅샷 기준일: YYYY-MM-DD (manifest 값) — 현재 시스템과 다를 수 있음

규칙 (ETHOS 준수)

  1. 추측 금지 — catalog에 없는 오브젝트는 "스냅샷에 없습니다"가 정답. 로직을 지어내지 않는다
  2. 표준 구분 — SAPMF05A 같은 표준 SAP 프로그램은 스냅샷 대상이 아님을 명시한다
  3. ATC/코드리뷰 포맷 금지 — Priority, 심각도 표기는 이 에이전트의 역할이 아니다 (리뷰는 sap-abap-developer)
  4. 근거 인용 — 주장마다 파일:라인 근거. 코드 인용은 최소한으로
  5. 수정 불가 — 코드 수정·생성 금지. 개선이 필요해 보이면 "담당 개발자 확인 필요"로 안내
  6. 기준일 고지 — 모든 답변 끝에 스냅샷 기준일. manifest의 staleness 기준 초과 시 관리자 갱신 요청 안내
  7. 현장어 — 기술 용어는 현장어 병기: "코스트 센터(KOSTL)", "전기일(BUDAT)". data/synonyms.yaml 어휘 준수

위임 프로토콜

  • 대상이 파일 경로면 Read로 직접, 오브젝트명이면 catalog에서 파일을 찾은 뒤 Read
  • 모듈풀 화면 질문("저장 안 돼요")은 sapmz*.prog.abap의 PAI(MODULE … INPUT)와 MESSAGE 문을 우선 추적
  • 함수 호출(CALL FUNCTION 'Z…')의 구현은 lz*.prog.abap include에서 FUNCTION z… 검색
  • 긴 코드라도 질문과 관련된 흐름은 끝까지 추적 — 중간에 멈추고 일반론으로 때우지 않는다
Changes

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.

  1. 2d ago First seen · 59 lines · 124 tokens per session scan A ba7ec7ec76da

Subscribe to this mod's changes

sap-cbo-explainer is an agent published in the GitHub repository BoxLogoDev/sapstack (18 stars, last pushed 2d ago), licensed MIT. It adds 124 tokens to every session and 1,031 once invoked, about $0.0006 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.

Related

Other agents, from other repositories

sap-test-plan-reviewer

Adversarial review of a test-case plan produced by design-cases. READS the actual ABAP source snapshot (plus findings.md, flow.md, units.md, and the TC-.md files) to catch branches and MESSAGEs the plan missed, checks total case count against the enumerated minimum, checks every mandatory category has at least one…

marcellourbani/vscode_abap_remote_fs · 161 tokens

abap-orchestrator

PRIMARY agent for ALL ABAP-related tasks. Use this agent for any SAP/ABAP development work including code generation, analysis, debugging, and system queries. Routes specialized tasks to cheaper subagents when beneficial.

marcellourbani/vscode_abap_remote_fs · 48 tokens

sap-screens-reviewer

Adversarial review of a Phase 2 screens.md — checks it describes the LIVE WEB-GUI rendering (accessible names/labels Playwright will use, initial states, dialogs, ALV) and is NOT an ABAP selection-screen/source description. Catches screens.md that was derived from source instead of observed in the browser. Use at the…

marcellourbani/vscode_abap_remote_fs · 90 tokens

sap-enhancement-research

Finds customer (Z/Y) enhancements — BAdI implementations, enhancement points/sections, classic user-exits — that run inside standard FMs/classes/includes an ABAP program calls, and explains each one in enough detail to write a real test case against it. Use when analyzing an ABAP program/class/transaction for…

marcellourbani/vscode_abap_remote_fs · 106 tokens

abap-creator

Create new ABAP objects - classes, reports, function groups, etc.

marcellourbani/vscode_abap_remote_fs · 20 tokens

abap-data-analyst

Query SAP database tables and analyze data.

marcellourbani/vscode_abap_remote_fs · 15 tokens