Borrowing it
Nothing to install: this file belongs to babamba2/superclaude-for-sap. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/babamba2/superclaude-for-sap/main/CLAUDE.mdgit clone --depth 1 https://github.com/babamba2/superclaude-for-sapWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/babamba2/superclaude-for-sap/claude-md)<a href="https://agentmods.dev/instructions/babamba2/superclaude-for-sap/claude-md"><img src="https://agentmods.dev/badge/instructions/babamba2/superclaude-for-sap/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/babamba2/superclaude-for-sap/claude-md"><img src="https://agentmods.dev/badge/instructions/babamba2/superclaude-for-sap/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02730 | $0.02730 |
| Opus 5 | $0.01365 | $0.01365 |
| Sonnet 5 | $0.00546 | $0.00546 |
| Haiku 4.5 | $0.00273 | $0.00273 |
Grade A, and why
superclaude-for-sap 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 9d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SuperClaude for SAP (sc4sap) — Development Rules
This file is the index of development rules — NOT a payload to preload. Detailed rules live in common/ and exceptions/. Consult files on demand per common/context-loading-protocol.md — 4-tier model: Tier 1 global mandatory safety baseline (always loaded: data-extraction-policy, sap-version-reference, naming-conventions, context-loading-protocol, model-routing-rule), Tier 2 role-mandatory per agent group, Tier 3 triggered reads, Tier 4 per-task kit. Everything referenced below is MANDATORY for every sc4sap session (agents, skills, direct user requests, pipelines).
Development Standards — References
| Topic | Reference |
|---|---|
| Naming conventions (Z/Y prefixes, module prefix, includes, FGs, tables, DEs, DOs) | common/naming-conventions.md |
Field typing priority (Standard DE → CBO DE → new CBO DE → Data Type+Length; never LIFNR CHAR 10) |
common/field-typing-rule.md |
| Function Module source convention (inline IMPORTING/EXPORTING/TABLES in FUNCTION statement; no placeholder, no shadow locals) | common/function-module-rule.md |
| SAP version awareness (ECC vs S/4HANA — tables, TCodes, BAPIs, patterns) | common/sap-version-reference.md |
ABAP release awareness (syntax availability per release, never emit newer features than ABAP_RELEASE) |
common/abap-release-reference.md |
| Clean ABAP coding standards (paradigm-split) | shared baseline common/clean-code.md + one of common/clean-code-oop.md or common/clean-code-procedural.md chosen from the Phase 1B Paradigm dimension; also pulls in constant-rule.md, text-element-rule.md, abap-release-reference.md |
| Procedural FORM naming (screen-bound suffix) | common/procedural-form-naming.md |
| OOP two-class split pattern | common/oop-pattern.md |
| Include structure (Main + conditional includes) | common/include-structure.md |
| ALV display rules | common/alv-rules.md |
OK_CODE binding pattern (TOP decl + screen NAME + PAI FORM routing; never CASE sy-ucomm) |
common/ok-code-pattern.md |
| SPRO lookup protocol (consultant agents, IMG/Customizing) | common/spro-lookup.md |
| Customization lookup protocol (existing Z*/Y* BAdI impl, CMOD, form-exits, appends — mandatory before recommending new enhancements/extensions) | common/customization-lookup.md |
Data extraction policy (blocklist rule, acknowledge_risk hard rule, refusal template) |
common/data-extraction-policy.md |
Transport client rule (every CreateTransport must receive explicit client from .sc4sap/sap.env SAP_CLIENT — never an implicit default) |
common/transport-client-rule.md |
| Blocklist (per-category table lists) | exceptions/table_exception.md (index) + exceptions/*.md section files |
| Industry business-context references (14 industries) | industry/README.md + industry/*.md |
| Country / localization references (16 countries + EU common) | country/README.md + country/*.md |
| Active modules — cross-module integration matrix (MM↔PS, SD↔CO, QM↔PP, …) | common/active-modules.md |
| Context loading protocol (CLAUDE.md is an index; every dispatch declares its minimal context kit) | common/context-loading-protocol.md |
| Model routing (Sonnet for reads + repetitive bulk; Opus for novel code, cross-file reasoning, ambiguity) | common/model-routing-rule.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.
- 9d ago First seen · 80 lines · 2,730 tokens per session scan A 0d17f29ff168
superclaude-for-sap CLAUDE.md is an instructions file published in the GitHub repository babamba2/superclaude-for-sap (54 stars, last pushed 16d ago), licensed MIT. It adds 2,730 tokens to every session, about $0.0136 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.