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 skills add vigneshbarani24/sap-superpowers --skill joulegit clone --depth 1 https://github.com/vigneshbarani24/sap-superpowersWrote 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/vigneshbarani24/sap-superpowers/joule)<a href="https://agentmods.dev/skills/vigneshbarani24/sap-superpowers/joule"><img src="https://agentmods.dev/badge/skills/vigneshbarani24/sap-superpowers/joule/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/skills/vigneshbarani24/sap-superpowers/joule"><img src="https://agentmods.dev/badge/skills/vigneshbarani24/sap-superpowers/joule.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 | $0.00070 | $0.02986 |
| Opus 5 | $0.00035 | $0.01493 |
| Sonnet 5 | $0.00014 | $0.00597 |
| Haiku 4.5 | $0.00007 | $0.00299 |
Grade A, and why
joule 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 6d 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SAP Joule
This skill enforces correct understanding of Joule's capabilities, limitations, and positioning — ensuring that Joule-generated transactions are always verified before confirming, complex multi-step processes are not delegated to Joule without verification, and consultants understand exactly where Joule's scope ends and SAP Superpowers begins.
Content Routing
| Topic | Section |
|---|---|
| Joule architecture | Architecture and Capabilities |
| Joule in S/4HANA Cloud | Joule in S/4HANA Cloud |
| Joule in SuccessFactors | Joule in SuccessFactors |
| Joule in Ariba and other apps | Joule in Other SAP Applications |
| Joule in BTP | Joule in BTP |
| Joule extensibility | Joule Extensibility |
| Joule vs. Superpowers | Joule vs. SAP Superpowers Positioning |
| Joule API integration | Joule API Integration Patterns |
Iron Laws
- ALWAYS VERIFY JOULE-GENERATED TRANSACTIONS BEFORE CONFIRMING. Joule interprets natural language and maps it to SAP transactions. Misinterpretation of ambiguous input produces incorrect transactions. Every Joule-generated action (PO creation, employee change, payment release) must be reviewed by the user before execution. Joule proposes; the user confirms.
- NEVER RELY ON JOULE FOR COMPLEX MULTI-STEP PROCESSES WITHOUT VERIFICATION. Joule excels at single-step queries and simple transactional tasks. Multi-step processes (month-end close, migration cutover, complex configuration) require process orchestration that exceeds Joule's current scope. Use Joule for individual steps; use process skills for orchestration.
- UNDERSTAND JOULE'S SCOPE LIMITATIONS PER APPLICATION. Joule's capabilities differ by SAP application and release level. Joule in S/4HANA Cloud Public Edition has different capabilities than Joule in SuccessFactors or Joule in BTP. Never assume a capability exists in one application because it works in another.
- NEVER TREAT JOULE AS A REPLACEMENT FOR SAP EXPERTISE. Joule assists users with transaction execution and information retrieval. It does not provide consulting judgment — system design, process optimization, risk assessment, or architecture decisions. Joule is an assistant; the SAP consultant is the expert.
- ALWAYS CONSIDER AUTHORIZATION IN JOULE INTERACTIONS. Joule executes actions within the user's authorization scope. A user who cannot execute a transaction manually cannot execute it via Joule. Joule does not bypass SAP authorization — but users may not understand this and attempt unauthorized actions expecting Joule to override.
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.
- 6d ago First seen · 262 lines · 70 tokens per session scan A b6babef6076b
joule is a skill published in the GitHub repository vigneshbarani24/sap-superpowers (9 stars, last pushed 17d ago), licensed MIT. It adds 70 tokens to every session and 2,986 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
sap-cloud-sdk-ai-python
Integrates the SAP Cloud SDK for AI for Python (sap-ai-sdk-gen, formerly generative-ai-hub-sdk) into Python applications. Use when building Python apps with SAP AI Core, Generative AI Hub, or the Orchestration Service: chat completion, embeddings, streaming, LangChain integration, templating, content filtering, data…
sap-cloud-sdk-ai
Integrates SAP Cloud SDK for AI into JavaScript/TypeScript and Java applications. Use when building applications with SAP AI Core, Generative AI Hub, or Orchestration Service. Covers chat completion, embedding, streaming, function calling, content filtering, data masking, document grounding, prompt registry, and…
add-ollama-tool
Add Ollama MCP server so the container agent can call local models and optionally manage the Ollama model library.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
prompt-master
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…
deepseek-helper
A guide for using the DeepSeek API, a service that lets programs send requests to DeepSeek language models. It covers model choice, example requests, prompt improvements, cost estimates, and common API errors.