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 shrek-abaper/sap-engineering-skill --skill sap-transport-gategit clone --depth 1 https://github.com/shrek-abaper/sap-engineering-skillWrote 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/shrek-abaper/sap-engineering-skill/sap-transport-gate)<a href="https://agentmods.dev/skills/shrek-abaper/sap-engineering-skill/sap-transport-gate"><img src="https://agentmods.dev/badge/skills/shrek-abaper/sap-engineering-skill/sap-transport-gate/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/shrek-abaper/sap-engineering-skill/sap-transport-gate"><img src="https://agentmods.dev/badge/skills/shrek-abaper/sap-engineering-skill/sap-transport-gate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 51 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 250 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 93 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 108 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Excessive Agency · line 127 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Prompt Injection · line 230 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Excessive Agency · line 374 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00185 | $0.04730 |
| Opus 5 | $0.00093 | $0.02365 |
| Sonnet 5 | $0.00037 | $0.00946 |
| Haiku 4.5 | $0.00018 | $0.00473 |
Grade A, and why
sap-transport-gate 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 11d 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 — 396 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SAP Transport Gate Skill
AI-assisted pre-release review for SAP Transport Requests. Based on provided evidence, produces a structured Release Readiness Report and an auditable GO / CONDITIONAL_GO / NO_GO / NEED_MORE_EVIDENCE decision.
Core principle: AI does NOT log in to SAP, does NOT execute transports, and does NOT fabricate conclusions from insufficient evidence. Every finding must trace to real evidence. Every gap must be declared.
Hard Constraints (enforce at all times)
| Constraint | Rule |
|---|---|
| No SAP login | Never request or accept SAP passwords, connection strings, or session tokens |
| No transport execution | Never trigger transport release, import, delete, or rollback |
| No evidence fabrication | No assumption that unread objects are safe; no invented test results |
| Evidence Level LOW → no GO | If Evidence Level is LOW, the decision must be NEED_MORE_EVIDENCE or NO_GO — never GO |
| Single-file ≠ full TR review | A single ABAP file does not constitute a Transport Request-level release review |
| Missing spec → Inferred only | Without a functional specification, Functional Alignment must be labeled Inferred / Limited |
Violations of these constraints invalidate the review output. Check them before generating any decision.
Step 0 — Load References
Before reading user-provided materials, load the following references in order:
references/review-modes.md— Mode detection, Review Package structure, evidence completeness rulesreferences/decision-policy.md— Evidence Level rules, Finding taxonomy, Release Decision Policyreferences/review-dimensions.md— 10 review dimensions with detailed checksreferences/report-format.md— Markdown report template and JSON schemareferences/abap-security-rules.md— Full SEC-_ and AUTH-_ security rule library (load for Dimension 3 and 4)references/abap-quality-rules.md— Full Clean ABAP quality rule library (load for Dimension 1 and 2)
What ships with it
24 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.
- .env.example 315 B
- .gitignore 585 B
- changelog.md 5.4 KB
- evals/evals.json 9.2 KB
- evals/golden-set.yaml 5.2 KB
- LICENSE 1.1 KB
- README.md 11 KB
- README.zh-CN.md 9.8 KB
- references/abap-quality-rules.md 13 KB
- references/abap-report-template.md 4.5 KB
- references/abap-security-rules.md 16 KB
- references/decision-policy.md 11 KB
- references/human-loop.md 9.7 KB
- references/regression-tests.md 15 KB
- references/report-format.md 14 KB
- references/review-dimensions.md 18 KB
- references/review-modes.md 12 KB
- references/sap-connectivity.md 11 KB
- scripts/lib/__init__.py 0 B runs code
- scripts/lib/client.py 2.3 KB runs code
- scripts/lib/config.py 5.3 KB runs code
- scripts/lib/handlers.py 11 KB runs code
- scripts/requirements.txt 45 B
- scripts/tr_collector.py 4.3 KB runs code
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.
- 11d ago First seen · 396 lines · 185 tokens per session scan A c56b09d0533f
sap-transport-gate is a skill published in the GitHub repository shrek-abaper/sap-engineering-skill (36 stars, last pushed 24d ago), licensed MIT. It adds 185 tokens to every session and 4,730 once invoked, about $0.0009 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
clean-abap
Check ABAP code for compliance with Clean ABAP principles. Use this skill when users ask to check, validate, review, or analyze ABAP code for clean code compliance, code quality, best practices, or adherence to Clean ABAP guidelines. Triggers include requests like "check this ABAP code", "is this clean ABAP", "review…
abap
Check and improve ABAP code quality using abaplint and Clean ABAP principles. Use this skill when users ask to check, lint, validate, review, or analyze ABAP code for syntax errors, clean code compliance, code quality, best practices, or adherence to Clean ABAP guidelines. Also use when users ask to set up abaplint…
atc-cloudification
Configure ATC Cloud Readiness and Clean Core checks using the SAP Cloudification Repository for Released APIs. Use when users ask about ATC check variants for cloud readiness, clean core compliance, released API checks, cloudification repository setup, objectReleaseInfo JSON files, SAP Cloud ERP or SAP Cloud ERP…
code-review
Use when reviewing ABAP code, SAP development artifacts, CDS views, or any custom SAP code before transport release, pull request approval, or go-live sign-off.
find-simplifications
Use for a periodic repo-wide sweep of qwen-code for accumulated excess surface — dead components and files, orphaned locale keys, exports nothing consumes, added-then-removed scaffolding — filing candidates on a tracking issue and landing only what a maintainer has said yes to. Repo-wide and evidence-first; every…
swarm-pr-review
Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…