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.
git 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/commands/vigneshbarani24/sap-superpowers/sap-review)<a href="https://agentmods.dev/commands/vigneshbarani24/sap-superpowers/sap-review"><img src="https://agentmods.dev/badge/commands/vigneshbarani24/sap-superpowers/sap-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/commands/vigneshbarani24/sap-superpowers/sap-review"><img src="https://agentmods.dev/badge/commands/vigneshbarani24/sap-superpowers/sap-review.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 | $0.00041 | $0.00619 |
| Opus 5 | $0.00020 | $0.00309 |
| Sonnet 5 | $0.00008 | $0.00124 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
sap-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 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sap-review
Invokes the sap-reviewer agent with code-review skill enforcement to deliver a thorough, multi-dimensional code review. Checks are structured across four dimensions: code quality, performance, security, and S/4HANA clean core compliance. No review is complete until all four dimensions are addressed.
Usage
/sap-review [file or code block]
Arguments:
[file or code block]— Provide a file path, paste a code block, or describe the repository location. The reviewer will read the code directly if a path is given.
Examples:
/sap-review src/ZVENDOR_AGING_REPORT.abap/sap-review the CDS view I just created in the editor/sap-review agents/integration/iflow-error-handler.groovy
What Happens
- The
sap-revieweragent is dispatched and reads the provided code. - The
code-reviewskill activates and enforces a four-dimension review structure — it cannot be skipped or abbreviated. - In parallel, the
sap-security-auditoragent scans for authorization object usage, privilege escalation patterns, and hardcoded credentials. - If S/4HANA context is detected, the
sap-migration-analyzeragent checks clean core compliance — deprecated APIs, non-released objects, modification-based patterns. - All findings are classified by severity: Critical / High / Medium / Low / Informational.
- Critical findings block the review from being marked complete — they must be addressed.
- A unified report is assembled from all agents and delivered as a structured document.
Output
A Code Review Report containing:
| Dimension | What Is Checked |
|---|---|
| Code Quality | Naming conventions, modularity, error handling, dead code, complexity |
| Performance | Select efficiency, table buffering, loop optimization, memory usage |
| Security | Authorization checks, injection risks, hardcoded credentials, RFC exposure |
| Clean Core | Released API usage, extensibility compliance, modification risks |
| Summary | Finding counts by severity, recommended actions, approval status |
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 · 60 lines · 41 tokens per session scan A f8adedea6100
sap-review is a command published in the GitHub repository vigneshbarani24/sap-superpowers (9 stars, last pushed 18d ago), licensed MIT. It adds 41 tokens to every session and 619 once invoked, about $0.0002 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 commands, from other repositories
widget-lint
Analyzes SAC custom widget code for performance issues, security concerns, and best practice violations.
api-style-review
Review SAP API style compliance for REST, OData, OpenAPI, SDK naming, documentation, and lifecycle readiness.
btp-architecture-review
Review SAP BTP architecture decisions for account model, services, security, integration, operations, and rollout readiness.
abap-cds-model-check
Analyze ABAP CDS views for modeling correctness, annotations, performance, authorization, and activation risks.
abap-cloud-review
Review ABAP code for ABAP Cloud readiness, released API usage, syntax constraints, and upgrade-safe remediation steps.
audit-agents-skills
Audit quality of agents, skills, and commands in a Claude Code project.