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 efeumutaslan/SAP-SKILLS --skill sap-security-authorizationgit clone --depth 1 https://github.com/efeumutaslan/SAP-SKILLSWrote 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/efeumutaslan/sap-skills/sap-security-authorization)<a href="https://agentmods.dev/skills/efeumutaslan/sap-skills/sap-security-authorization"><img src="https://agentmods.dev/badge/skills/efeumutaslan/sap-skills/sap-security-authorization/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/efeumutaslan/sap-skills/sap-security-authorization"><img src="https://agentmods.dev/badge/skills/efeumutaslan/sap-skills/sap-security-authorization.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 | $0.00101 | $0.02831 |
| Opus 5 | $0.00051 | $0.01416 |
| Sonnet 5 | $0.00020 | $0.00566 |
| Haiku 4.5 | $0.00010 | $0.00283 |
Grade A, and why
sap-security-authorization 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 10d 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 Security & Authorization
Related Skills
sap-s4hana-extensibility— Extension authorization patternssap-build-process-automation— Approval workflow designsap-rap-comprehensive— RAP authorization (global/instance)sap-cap-advanced— CAP-level auth with XSUAA/IAS scopessap-kyma-runtime— Kubernetes API Rule JWT validationsap-successfactors— RBP (Role-Based Permissions) model
Quick Start
Authorization error? Start here:
- Run SU53 (or for another user: SU53 → Other User)
- Check which authorization object failed and what values were needed
- If SU53 is not enough, use STAUTHTRACE for full trace (captures all checks, not just failures)
Design a role:
- SU24 — Check authorization defaults for the transaction
- PFCG — Create single role, add transactions to menu
- Generate profile → Adjust authorization values → Save
- Create derived roles for org-level variations (company code, plant)
- Assign role to user via SU01
BTP authorization:
- Define scopes and role-templates in
xs-security.json - Create role collections in BTP cockpit
- Assign role collections to users/groups
Core Concepts
On-Premise Authorization Hierarchy
User (SU01)
└── Role (PFCG)
└── Profile (auto-generated)
└── Authorization Object
└── Field = Value
Role Types
| Type | Description | Use Case |
|---|---|---|
| Single | Contains tcodes, auth objects, field values | Job-based access |
| Composite | Groups single roles; no own authorizations | Combining functions |
| Derived (Child) | Inherits from master; only org-level values differ | Multi-org access |
Naming convention: Z_<MODULE>_<FUNCTION>_<TYPE> (e.g., Z_FI_AP_CLERK_S, _C for composite, _D for derived)
Critical Authorization Objects
| Object | Fields | Controls |
|---|---|---|
| S_TCODE | TCD | Transaction access |
| S_RFC | RFC_TYPE, RFC_NAME, ACTVT | RFC/function module execution |
| S_SERVICE | SRV_NAME, SRV_TYPE | Fiori/OData service access |
| S_TABU_DIS | DICBERCLS, ACTVT | Table access by auth group |
| S_TABU_NAM | TABLE | Table access by name |
| S_DEVELOP | DEVCLASS, OBJTYPE, OBJNAME, ACTVT | ABAP development |
| S_USER_GRP | CLASS, ACTVT | User master maintenance |
| S_USER_AGR | ACT_GROUP, ACTVT | Role assignment |
| S_PROGRAM | P_ACTION, P_GROUP | Program execution |
What ships with it
8 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.
- references/authorization-objects.md 7.6 KB
- references/btp-xsuaa-guide.md 8.8 KB
- references/cloud-identity-services.md 6.7 KB
- references/compliance-checklist.md 5.7 KB
- references/pfcg-role-design.md 8.3 KB
- references/sod-matrix.md 5.1 KB
- templates/role-naming-convention.md 3.2 KB
- templates/xs-security.json 1.9 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.
- 10d ago First seen · 262 lines · 101 tokens per session scan A 182b7bca8510
sap-security-authorization is a skill published in the GitHub repository efeumutaslan/SAP-SKILLS (5 stars, last pushed 5mo ago), licensed MIT. It adds 101 tokens to every session and 2,831 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 2026-08-31.
Other skills, from other repositories
lov-review-doc
A contract review assistant for agreements such as NDAs, service contracts, data agreements, employment contracts, licences, and investment documents. It can analyse risks, add comments, and suggest revised wording.
lov-china-website-filing
A workflow for preparing and launching websites in mainland China, including ICP filing and public-security filing. ICP filing is the registration required for many mainland websites, while public-security filing is a separate police registration.
contract-review-pro
Professional-grade contract review skill that adds comment-based issue annotations without changing original text. Enforces a four-layer review (entity verification, basic, business, legal), writes structured comments (issue type, risk reason, revision suggestion) with risk level encoded via reviewer name, and…
lov-legal-pages
A website content tool that drafts privacy policy and terms-of-service pages from the project’s real business and data-handling facts. These pages explain how a service uses information and what rules apply to its users.
lov-filing-monitor
A recurring checker for website filing status on official Chinese government or service-provider pages. It compares the latest status with the previous check and keeps a record.
lov-filing-readiness
A pre-submission checklist for mainland China website ICP filing. It checks the filing subject, domain ownership, hosting resources, website type, required materials, and possible special-approval concerns.