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/boxlogodev/sapstack/sap-basisnpx skills add BoxLogoDev/sapstack --skill sap-basisgit clone --depth 1 https://github.com/BoxLogoDev/sapstackWhat 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 | $0.00118 | $0.02091 |
| Opus 5 | $0.00059 | $0.01045 |
| Sonnet 5 | $0.00024 | $0.00418 |
| Haiku 4.5 | $0.00012 | $0.00209 |
Grade A, and why
sap-basis 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 2d 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
1. Transport Management (STMS)
Landscape Configuration
Standard 3-system landscape: DEV → QAS → PRD
- Each system has a system ID (SID) and client(s)
- Transport routes: consolidation route (DEV→QAS) + delivery route (QAS→PRD)
Transport Request Types
| Type | Description | Client-specific? |
|---|---|---|
| Workbench | Repository objects (programs, tables, classes) | No — system-wide |
| Customizing | Client-specific IMG settings | Yes — per client |
| Transport of Copies | Copy objects without releasing original | No |
Transport Workflow
SE09 / SE10 (create / display request in DEV)
→ Release task → Release request
→ STMS (QAS): import queue → import
→ STMS (PRD): import queue → import (after QAS sign-off)
Common Transport Errors
| Return Code | Meaning | Fix |
|---|---|---|
| RC=0 | Success | — |
| RC=4 | Warnings | Review log — usually OK |
| RC=8 | Errors | Check transport log → fix object issue |
| RC=12 | Syntax error | SE38 in target system → check syntax |
| RC=16 | Fatal error | Check STMS log → object conflicts |
Object locked by another request → SM12 → check table TRDIR or object name → identify locking request → coordinate with owner
Import conflict (object already modified differently in target) → SPDD (dictionary objects) / SPAU (other objects) → manual adjustment required
2. Performance Analysis Toolkit
| T-code | Purpose | Key Action |
|---|---|---|
| SM50 | Work process overview (current instance) | Identify long-running / waiting processes |
| SM66 | Global work process overview (all instances) | System-wide bottleneck detection |
| ST05 | SQL trace activation + display | Find slow queries / missing indexes |
| SM12 | Lock entries | Find blocking locks by user / object |
| ST22 | Short dump analysis | Root cause of ABAP runtime errors |
| STAD | Workload monitor statistics | Response time analysis by user / report |
| SM21 | System log | Error / warning messages with timestamp |
| AL08 | Users logged on | Current sessions with work process assignment |
| RZ20 | CCMS alert monitor | Threshold-based system alerts |
What ships with it
10 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/best-practices/governance.md 5.9 KB
- references/best-practices/operational.md 4.3 KB
- references/best-practices/period-end.md 4.5 KB
- references/de/quick-guide-de.md 1.7 KB
- references/en/quick-guide-en.md 1.6 KB
- references/ja/quick-guide-ja.md 1.8 KB
- references/ko/quick-guide.md 1.7 KB
- references/ko/SKILL-ko.md 7.5 KB
- references/vi/quick-guide-vi.md 1.8 KB
- references/zh/quick-guide-zh.md 1.6 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.
- 2d ago First seen · 242 lines · 118 tokens per session scan A 067a4acf180e
sap-basis is a skill published in the GitHub repository BoxLogoDev/sapstack (18 stars, last pushed 3d ago), licensed MIT. It adds 118 tokens to every session and 2,091 once invoked, about $0.0006 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
abap-check
The catalogue of ABAP problems a green CI does not catch - abapGit round-trip and import failures (BOM, line endings, trailing whitespace, EOF newline, 255-character lines, metadata sidecars for CLAS and for DDLS/BDEF/TABL), activation errors abaplint does not model (classconstructor visibility, LOCAL FRIENDS, generic…
build-scripts
Standalone Phase 6 of SAP UI testing. Rediscovers the configured test folder, program, approved cases, and primary system from disk; validates upstream inputs; then writes one tests/ /test-scripts/TC-XXX.spec.ts per case using @sap-testing/runtime. Use when the user asks to write, generate, or convert Playwright…
design-cases
Standalone Phase 3 of SAP UI testing. Turns the findings.md decision surface and the screens.md control map into one tests/ /test-cases/TC-XXX.md per candidate case — grounded in the actual code behaviour (overlap/dedup/boundary), with a per-case selection-screen state table and a mandatory post-test verification…
explore-ui
Standalone Phase 2 of SAP UI testing. Opens the target transaction in a real browser (SAP WebGUI) and explores it live to produce tests/ /test-cases/screens.md — the authoritative map of every on-screen control, its accessible name/label as Playwright will see it, and its initial state. This is about how the UI…
sap-webgui
Authoritative SAP WebGUI behavior and locator guidance for live exploration and Playwright script generation. Covers iframes, accessible names, generated IDs, selection screens, dialogs, ALV grids, toolbars, uploads, themes, and known SapSession helper limitations. Load before explore-ui live exploration and before…
sap-system-personality-report
Generate a comprehensive SAP System Personality Report. Analyzes custom code landscape, functional footprint, development activity, health metrics, and package breakdown. Use when a user asks to characterize a system, understand a system, get a system overview, system report, system personality, or "what does this…