sapstack CLAUDE.md

Project instructions for the sapstack repository, a codebase containing SAP-related skills and tools. They define which project documents to read, how Claude Code should route work, and which checks apply before commits.

In plain words
What is it for?
Use them when changing sapstack or answering SAP questions. They direct the agent to read AGENTS.md, choose relevant skills or commands, use diagnosis sessions when needed, and follow contribution gates.
Why use it?
They give coding agents a shared operating contract so answers and repository changes follow the project’s rules. They reduce the risk of skipping required evidence, references, or quality checks.

Instructions file

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/claude-md
Clone the repo
git clone --depth 1 https://github.com/BoxLogoDev/sapstack
Per session 388 This file is loaded in full into every session.
When invoked 388 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 $0.00388 $0.00388
Opus 5 $0.00194 $0.00194
Sonnet 5 $0.00078 $0.00078
Haiku 4.5 $0.00039 $0.00039

Measured 2d ago against content hash 26af302dfafe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sapstack CLAUDE.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 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.

CLAUDE.md · 45 lines

What it actually says

CLAUDE.md — sapstack

Project operating contract

Before changing this repository or answering any SAP question, read AGENTS.md. Universal Rules, the dual-mode response format (Quick Advisory / Evidence Loop), plugin and subagent routing, the compatibility matrix, multilingual behavior, and the reference map all live there. ETHOS.md holds the why behind those rules, and CONTRIBUTING.md holds the contribution gates.

Keep this file limited to Claude Code / gstack routing so project instructions do not diverge across agents. Do not restate project facts here — point at AGENTS.md instead.

Claude Code entry points

  • Knowledge source: plugins/*/skills/*/SKILL.md (Korean: references/ko/)
  • Slash commands: commands/*.md
  • Subagents: agents/*.md
  • Install as a marketplace plugin: /plugin marketplace add https://github.com/BoxLogoDev/sapstack

Skill routing

When the user's request matches an available skill, invoke it via the Skill tool. When in doubt, invoke the skill.

  • Evidence Loop diagnosis session → /sap-session-start, then /sap-session-add-evidence and /sap-session-next-turn
  • Module-specific workflows → the matching commands/sap-*.md slash command
  • Bugs/errors in this repository's own code → /investigate
  • Code review / diff check → /review
  • Ship / deploy / PR → /ship or /land-and-deploy
  • Save progress → /context-save; resume → /context-restore

Quality gates before committing

./scripts/lint-frontmatter.sh
./scripts/check-marketplace.sh
./scripts/check-hardcoding.sh --strict
./scripts/check-tcodes.sh
npm run check:doc-stats
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 · 45 lines · 388 tokens per session scan A 26af302dfafe

Subscribe to this mod's changes

sapstack CLAUDE.md is an instructions file published in the GitHub repository BoxLogoDev/sapstack (18 stars, last pushed 2d ago), licensed MIT. It adds 388 tokens to every session, about $0.0019 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 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