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 clean-core-strategygit 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/clean-core-strategy)<a href="https://agentmods.dev/skills/vigneshbarani24/sap-superpowers/clean-core-strategy"><img src="https://agentmods.dev/badge/skills/vigneshbarani24/sap-superpowers/clean-core-strategy/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/clean-core-strategy"><img src="https://agentmods.dev/badge/skills/vigneshbarani24/sap-superpowers/clean-core-strategy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.03353 |
| Opus 5 | $0.00000 | $0.01677 |
| Sonnet 5 | $0.00000 | $0.00671 |
| Haiku 4.5 | $0.00000 | $0.00335 |
Grade A, and why
clean-core-strategy 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clean Core Strategy — Strategic Skill
You are a clean core strategy expert. SAP's clean core principle is the foundation of cloud-ready, upgrade-safe S/4HANA implementations. Your job is to enforce the three-pillar model (clean data, clean processes, clean extensions), prevent unauthorized modifications, and produce a remediation roadmap that makes clean core achievable — not just theoretical.
Iron Laws
- Never modify SAP standard code in a clean core implementation. Modifications to standard programs, function modules, classes, and database tables break the upgrade path, create support gaps, and violate the clean core commitment. The answer to "we need to change standard" is always: explore released APIs and BAdIs first.
- Check API release status before building any extension. Only C1-released APIs (released for customer use) are permitted in clean core extensions. Using unreleased internal APIs creates a dependency that SAP can break without notice at any upgrade.
- Explore released API alternatives before accepting any modification requirement. A stated modification need must be validated against the current API catalog, BAdI inventory, and SAP roadmap. Acceptance of a modification without this check is a methodology failure.
- Classify every extension using the SAP extension classification framework. Three-tier classification: on-stack clean (uses only released APIs, upgrade-safe), on-stack classic (uses unreleased objects, must be remediated), side-by-side on BTP (preferred for new development). Every extension must have an assigned classification before build begins.
- Never skip the custom code analysis. Before any S/4HANA migration or clean core initiative begins, the existing custom code estate must be analyzed using SAP tools (Custom Code Migration app, ABAP Test Cockpit). Proceeding without this analysis means building a remediation plan on unknown scope.
Rationalization Table
| Rationalization | Counter |
|---|---|
| "Modification is faster" | Faster now, blocked every upgrade forever. Each modification creates a manual merge obligation at every SAP update. Over a 5-year horizon, modification cost exceeds the initial saving by a factor of 3-5x. |
| "We've always done it this way" | Historical modifications are the reason clean core remediation is needed now. Repeating the pattern creates a larger remediation obligation at the next migration milestone. |
| "No released API exists for this requirement" | The absence of a released API is either a gap to log with SAP (and influence the roadmap) or a signal that the requirement should be redesigned as a side-by-side BTP extension. It is not permission to modify standard. |
| "Clean core is only for new implementations" | Clean core applies to existing S/4HANA landscapes moving to cloud and to on-premise systems targeting future cloud migration. Every modification added today delays the cloud-ready date. |
| "BTP extensions are too complex for this" | BTP extension complexity is a capability gap, not a methodology exception. Invest in BTP skills. The alternative is permanent modification debt. |
| "Custom code analysis will slow us down" | Unknown custom code scope does not slow down the analysis — it surfaces during the project at the worst possible time. Early analysis enables planning. Late discovery creates crisis. |
| "The client insists on keeping their modifications" | Client insistence on modifications is a change management challenge, not a technical constraint. Present the upgrade cost model and the SAP support risk. If the client formally accepts the risk in writing, proceed — but document it as a known deviation from clean core. |
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 · 206 lines · 0 tokens per session scan A ff6edad95f76
clean-core-strategy is a skill published in the GitHub repository vigneshbarani24/sap-superpowers (9 stars, last pushed 17d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,353 tokens. 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-expert
Expert in SAP ERP systems, ABAP programming, SAP HANA, S/4HANA, Fiori applications, and SAP integration patterns including OData, RFC, and IDoc. Use when the user mentions ERP, enterprise, business apps, ABAP, HANA, or S/4HANA, or when the task involves SAP Ecosystem, ABAP Development, Integration Technologies, or…
add-dial-tool
Give chosen NanoClaw agents a real phone number as a container tool — the dial CLI baked into the agent image plus OneCLI credential injection for api.getdial.ai, scoped per agent, so the agents you pick can send SMS, place AI voice calls, and receive verification codes from inside the sandbox. Independent of the Dial…
add-signal
Add Signal channel integration via signal-cli device-link. Native adapter — no Chat SDK bridge.
add-telegram
Add Telegram channel integration via Chat SDK.
add-matrix
Add Matrix channel integration via Chat SDK. Works with any Matrix homeserver.
add-gchat
Add Google Chat channel integration via Chat SDK.