agentmods.dev

sapstack markdown.instructions.md

A set of Markdown editing rules for files such as skill guides, agent instructions, commands, and documentation. It defines required front matter, English source text, suggested sections, and link rules.

In plain words
What is it for?
Use it when creating or editing Markdown files in the specified sapstack project, especially skills, agents, commands, and docs.
Why use it?
It gives contributors a consistent structure and catches missing metadata or broken internal-link practices. It also explains when SAP ECC and S/4HANA guidance should be separated.

Instructions file for GitHub Copilot

18 2d ago A scan 799 tokens original MIT
View the source file BoxLogoDev/sapstack
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 instructions/boxlogodev/sapstack/markdown
Clone the repo
git clone --depth 1 https://github.com/BoxLogoDev/sapstack

Made for: GitHub Copilot.

Per session 799 This file is loaded in full into every session.
When invoked 799 The same file — it is already loaded in full.
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 $0.00799 $0.00799
Opus 5 $0.00400 $0.00400
Sonnet 5 $0.00160 $0.00160
Haiku 4.5 $0.00080 $0.00080

Measured yesterday against content hash 6ffc6bd19f34, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sapstack markdown.instructions.md 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 yesterday.

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.

.github/instructions/markdown.instructions.md · 101 lines

What it actually says

Markdown Instructions (GitHub Copilot)

이 파일은 Markdown 파일을 편집할 때 적용되는 지침입니다. 특히 SKILL.md, agents/*.md, commands/*.md, docs/*.md에 해당합니다.

SKILL.md (plugins//skills//SKILL.md)

프론트매터 필수

---
name: sap-<module>
description: >
  This skill handles <module> tasks including ...
  Use when user mentions <trigger1>, <trigger2>, ...
allowed-tools: Read, Grep
---

규칙

  • name은 디렉토리명과 일치
  • description은 3인칭, 1024자 이하, 트리거 키워드 포함
  • 본문은 영문 유지 (한국어 번역은 references/ko/SKILL-ko.md로)
  • ECC vs S/4HANA 차이가 주요 주제라면 명시적으로 구분

본문 섹션 권장 순서

  1. Environment Intake Checklist
  2. 모듈별 주요 이슈 (T-code + 테이블 레벨)
  3. ECC vs S/4HANA 차이
  4. Standard Response Format
  5. References

agents/*.md

프론트매터

---
name: <agent-name>
description: (한국어) 이 에이전트가 하는 일 + 자동 위임 트리거
tools: Read, Grep, Glob
model: sonnet
---

본문 구조

  1. 역할 선언
  2. 핵심 원칙
  3. 응답 형식 (고정)
  4. 위임 프로토콜
  5. 금지 사항
  6. 참조 (관련 SKILL.md, 데이터 자산)

commands/*.md

프론트매터

---
description: 커맨드 설명 (한국어)
argument-hint: [인수 힌트]
---

본문 구조

  1. 🎯 목표
  2. 실행 순서 (Step 1, 2, ...)
  3. 각 단계의 체크 항목
  4. 출력 형식 템플릿
  5. 참조

기본 규칙

링크

  • 내부 링크는 상대 경로 사용 (절대 URL 금지)
  • 파일 이동 시 링크 업데이트
  • scripts/check-links.sh (v1.3.0)로 검증

코드 블록

  • 언어 지정 필수 (```bash, ```abap, ```yaml)
  • T-code는 bold (**MIRO**)
  • 테이블명/필드는 FS00, LFB1.ZWELS 형식

한국어 / 영문 혼용

  • Universal Rules와 Standard Response Format은 영문 유지 (글로벌 일관성)
  • 한국 사용자 가이드는 한국어 (references/ko/, docs/ 한국어 문서)
  • 기술 용어는 영문 병기 허용 (예: "환율평가(FX Valuation)")

하드코딩 금지

Markdown 예시에 회사코드·G/L·조직 단위 고정값을 쓰지 마세요:

  • ❌ "회사코드 1000에서..."
  • ✅ "사용자의 회사코드(예: <YOUR_COMPANY_CODE>)에서..."

검증

./scripts/lint-frontmatter.sh
./scripts/check-links.sh            # v1.3.0
./scripts/check-ko-references.sh    # v1.3.0
./scripts/check-hardcoding.sh --strict
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. yesterday First seen · 101 lines · 799 tokens per session scan A 6ffc6bd19f34

Subscribe to this mod's changes

sapstack markdown.instructions.md is an instructions file published in the GitHub repository BoxLogoDev/sapstack (18 stars, last pushed 2d ago), licensed MIT. It adds 799 tokens to every session, about $0.0040 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.

Data and AIWriting and docsabapai-agentsclaude-codedeveloper-toolserpllm-skills
Related

Other instructions, from other repositories

abap2UI5 AGENTS.md

Instructions for abap2UI5/abap2UI5, covering agents.md — ai assistant guide for abap2ui5, where knowledge lives, project overview, related repositories and architecture.

abap2UI5/abap2UI5 · 28,164 tokens

vibing-steampunk copilot-instructions.md

Instructions for oisee/vibing-steampunk, covering copilot instructions for vsp, project, build, test, lint, build and run all unit tests.

oisee/vibing-steampunk · 1,439 tokens

onebase CLAUDE.md

Instructions for ivanarama/onebase, covering claude.md, сборка и запуск, cli + сервер (без cgo) — основной бинарь, gui с нативным окном (cgo + webview2 на windows) and тесты.

ivanarama/onebase · 5,591 tokens

mcp-erpnext AGENTS.md

Instructions for Casys-AI/mcp-erpnext, covering agents.md, project overview, project structure & module organization, build, test, and development commands and run all tests (also: deno task test).

Casys-AI/mcp-erpnext · 6,458 tokens

abap2UI5 CLAUDE.md

Instructions for abap2UI5/abap2UI5: All project guidance lives in AGENTS.md — the single source of truth for this repository (architecture and the layered design, the src/00-99 packages, the generated app/webapp mirror, the build and delivery pipeline, the CI gates and ABAP code style).

abap2UI5/abap2UI5 · 79 tokens

balaka CLAUDE.md

Instructions for artivisi/balaka, covering claude instructions, project overview, current status, key files and development guidelines.

artivisi/balaka · 3,438 tokens