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 skills/babamba2/superclaude-for-sap/setupnpx skills add babamba2/superclaude-for-sap --skill setupgit 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/skills/babamba2/superclaude-for-sap/setup)<a href="https://agentmods.dev/skills/babamba2/superclaude-for-sap/setup"><img src="https://agentmods.dev/badge/skills/babamba2/superclaude-for-sap/setup.svg" alt="Measured on agentmods" 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 | $0.00103 | $0.02829 |
| Opus 5 | $0.00051 | $0.01414 |
| Sonnet 5 | $0.00021 | $0.00566 |
| Haiku 4.5 | $0.00010 | $0.00283 |
Grade A, and why
sc4sap:setup 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 5d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SC4SAP Setup
Use /sc4sap:setup as the unified setup and configuration entrypoint for SuperClaude for SAP.
<Response_Prefix>
Every response triggered by this skill MUST begin with [Model: <main-model> · Dispatched: <sub-summary>] per ../../common/model-routing-rule.md § Response Prefix Convention.
</Response_Prefix>
<Phase_Banner>
Multi-phase skill. Before each Agent(...) dispatch (including the two conditional error-escalation paths below), emit ▶ phase=<id> (<label>) · agent=<name> · model=<Opus 4.7|Sonnet 4.6|Haiku 4.5> per ../../common/model-routing-rule.md § Phase Banner Convention.
</Phase_Banner>
<Error_Escalation_Paths> Setup's happy path runs entirely on the main thread (Haiku 4.5 per frontmatter) — it's configuration work, not code generation. Two step-ranges escalate on failure:
| Source step(s) | Agent | Model | Why |
|---|---|---|---|
| 4bis RFC backend — preflight failure, handler install error, SICF service misconfigured, SM59 test fails, ZRFC ICF handler returns 5xx | sap-bc-consultant |
Opus 4.7 (frontmatter) | Pure Basis domain — RFC destinations, SICF, SM59, transport of handler class. Basis consultant owns this ground. |
| 5 Reconnect / 6 GetSession / 7 systemInfo persist / 8 GetInactiveObjects — any failure (HTTP error, auth reject, parse failure, timeout, authorization object missing) | general-purpose (with model: "opus" override) |
Opus 4.7 | 3-layer stack (SAP ADT + MCP server + Claude Code plugin). Most errors are cross-layer (MCP framework bugs, Node runtime issues, profile resolution) — pure SAP consultant has a blind spot. general-purpose + Opus spans Read/Grep/Bash/WebFetch/WebSearch across all three layers. |
Each escalation emits its own phase banner:
▶ phase=4bis.escalate (basis) · agent=sap-bc-consultant · model=Opus 4.7
▶ phase=5-8.escalate (triage) · agent=general-purpose · model=Opus 4.7
After the escalation agent returns a diagnosis + remediation checklist, the main thread (Haiku) surfaces it to the user and asks whether to retry the failed step or abort setup. </Error_Escalation_Paths>
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- customization-auto-generation.md 5.5 KB
- hud-statusline.md 4.3 KB
- odata-classes-install.md 5.1 KB
- rfc-backend-selection.md 13 KB
- spro-auto-generation.md 3.3 KB
- wizard-step-02-system-identification.md 3.2 KB
- wizard-step-04-profile-creation.md 7.6 KB
- wizard-step-09-abap-objects.md 14 KB
- wizard-step-11-optional-extraction.md 2.5 KB
- wizard-step-12-blocklist-hook.md 5.2 KB
- wizard-steps.md 12 KB
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.
- 5d ago First seen · 127 lines · 103 tokens per session scan A 596cd8ef3fc2
sc4sap:setup is a skill published in the GitHub repository babamba2/superclaude-for-sap (53 stars, last pushed 12d ago), licensed MIT. It adds 103 tokens to every session and 2,829 once invoked, about $0.0005 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…