SAP Automation Pilot is an automation engine for SAP Business Technology Platform in which Commands define operational workflows. SAP teams use it to generate, review, deploy, run, monitor, and troubleshoot these automations. The catalogue skills provide an AI-assisted workflow for developing and operating SAP Automation Pilot Commands.
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 SAP/automation-pilot-agent-skills --skill automation-pilot-command-reviewgit clone --depth 1 https://github.com/SAP/automation-pilot-agent-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/sap/automation-pilot-agent-skills/automation-pilot-command-review)<a href="https://agentmods.dev/skills/sap/automation-pilot-agent-skills/automation-pilot-command-review"><img src="https://agentmods.dev/badge/skills/sap/automation-pilot-agent-skills/automation-pilot-command-review/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/sap/automation-pilot-agent-skills/automation-pilot-command-review"><img src="https://agentmods.dev/badge/skills/sap/automation-pilot-agent-skills/automation-pilot-command-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Data Exfiltration · line 274 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00053 | $0.03452 |
| Opus 5 | $0.00026 | $0.01726 |
| Sonnet 5 | $0.00011 | $0.00690 |
| Haiku 4.5 | $0.00005 | $0.00345 |
Grade A, and why
automation-pilot-command-review 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 — 407 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Validate production commands meet structural, security, and quality standards.
AI Assistant Guidelines
⚠️ CRITICAL - When reviewing as an AI assistant:
- DO NOT suggest or make any changes to expressions, response body transformers, or execution properties unless there is a clear error
- Review comments should be added ONLY when there is a concern, warning, or an issue. When something is fine, do not add comments or suggest changes
- Never write code comments in the properties fields of the commands
- Do not add newline at end of a file - files should end without trailing newline
- Flag violations immediately - critical issues (file structure, security, naming) must be caught
⚠️ JSON FILES DO NOT SUPPORT COMMENTS:
- NEVER suggest adding
//or/* */comments - JSON syntax doesn't allow comments - NEVER suggest documenting status codes inline - this would break the JSON
- Standard retry status codes are well-known - do not ask to document them:
-1= Network/connection failure (standard in this codebase)408= Request Timeout429= Too Many Requests500, 502, 503, 504= Server errors
- If documentation is needed, it belongs in SKILL.md files, not in JSON
❌ WRONG - Never suggest this:
// Consider defining these in a comment
"expression": "$([408, 429, -1] | filter(...))"
✅ CORRECT - This pattern is standard and needs no comment:
"expression": "$([408, 429, 500, 502, 503, 504, -1] | filter(. == $.<httpExecutorAlias>.output.status) | length)"
Standard patterns that should NOT be flagged:
semantic: "AND"/semantic: "OR"conditions - these are clear, not "confusing"$({...} | toObject)for building JSON objects - this IS the cleanest approach- Empty body checks combined with error message checks - valid error handling
- NO trailing newlines in JSON files - this is our convention (contrary to POSIX)
Critical File Structure Rules
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 · 407 lines · 53 tokens per session scan A fbaa8e7f67a6
automation-pilot-command-review is a skill published in the GitHub repository SAP/automation-pilot-agent-skills (11 stars, last pushed 8d ago), licensed Apache-2.0. It adds 53 tokens to every session and 3,452 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 2026-08-31.
Other skills, from other repositories
platform-apex-generate
Primary Apex authoring skill for class generation, refactoring, and review. ALWAYS ACTIVATE when the user mentions Apex, .cls, triggers, or asks to create/refactor a class (service, selector, domain, batch, queueable, schedulable, invocable, DTO, utility, interface, abstract, exception, REST resource). Use this skill…
flow-next-impl-review
Carmack-level implementation review of changes via the configured backend. Use when asked to review code or a diff in a flow-next repo.
flow-next-resolve-pr
Resolve PR review feedback. Fetches unresolved threads, triages, fixes, replies and resolves via GraphQL. Use when asked to address review comments.
api-contract-review
Use when auditing CloudBase cloud API wrappers, MCP tools, generated action metadata, or related docs for outdated or incorrect action names, parameters, casing, request shapes, or missing contract tests, especially during periodic quality review or before preparing corrective PRs.
principle-model-the-domain
Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files. Encode the domain in a structure instead of scattered conditionals.
api-reviewer
A review of an API contract, the agreed description of how software systems exchange requests, responses, events, or files.