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-estimate)<a href="https://agentmods.dev/commands/vigneshbarani24/sap-superpowers/sap-estimate"><img src="https://agentmods.dev/badge/commands/vigneshbarani24/sap-superpowers/sap-estimate/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-estimate"><img src="https://agentmods.dev/badge/commands/vigneshbarani24/sap-superpowers/sap-estimate.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 | $0.00034 | $0.00614 |
| Opus 5.5 | $0.00014 | $0.00246 |
| Sonnet 5.5 | $0.00007 | $0.00123 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
sap-estimate 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 1mo 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-estimate
Invokes the sap-estimator agent with estimation skill enforcement to produce rigorous, decomposed effort estimates. Single-number estimates are blocked by design — every output uses three-point estimation (optimistic / most likely / pessimistic) with a full Work Breakdown Structure.
Usage
/sap-estimate [scope description]
Arguments:
[scope description]— Describe the work to be estimated. Can be a project, a phase, a module, a feature, or a list of requirements. More detail yields more accurate WBS decomposition.
Examples:
/sap-estimate Full S/4HANA greenfield for a mid-size manufacturing company — FI, CO, MM, PP, SD/sap-estimate Custom ABAP report — vendor payment due date aging with multi-currency support/sap-estimate SAP Integration Suite: 12 iFlows connecting S/4 to Salesforce CRM
What Happens
- The
sap-estimatoragent is dispatched with theestimationskill active. - The skill enforces scope decomposition before any numbers are given — the agent must produce a WBS first.
- Each WBS line item receives a three-point estimate: optimistic (O), most likely (M), pessimistic (P).
- PERT formula is applied:
E = (O + 4M + P) / 6per line item. - Risk adjustments, contingency factors, and dependency impacts are layered on.
- Assumptions and exclusions are captured explicitly — nothing is left implicit.
- The skill hard-gates prevent delivery until all line items have supporting rationale.
Output
An Effort Estimate Document containing:
| Section | Content |
|---|---|
| Scope Summary | What is and is not included |
| WBS | Full work breakdown to task level |
| Three-Point Estimates | O / M / P / PERT per line item |
| Total Summary | Hours by phase, by role, by module |
| Risk Register | Estimate risks with probability and impact |
| Assumptions | Explicit assumptions underpinning the numbers |
| Exclusions | What is explicitly out of scope |
Example
/sap-estimate FI-AP implementation for a retail client — 3 company codes, SEPA payments, automatic payment run
> Activating sap-estimator agent with estimation skill...
> Stage 1: Scope decomposition — 8 WBS items identified
> Stage 2: Three-point estimates applied to each item
> Stage 3: Risk adjustments — SEPA config complexity flagged (+15%)
> Stage 4: Assumptions captured — 4 explicit, 2 exclusions noted
> Generating effort estimate document...
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.
- 1mo ago First seen · 60 lines · 34 tokens per session scan A a4161af86f65
sap-estimate is a command published in the GitHub repository vigneshbarani24/sap-superpowers (10 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 614 once invoked, about $0.0001 per session on Opus 5.5. 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
add-ai
Add an AI / LLM feature to an existing abap2UI5 app - a chat or a summarize-this-data panel, on a local provider first, then on a real model through the samples-stack LLM classes, with secrets kept out of the code.
check
Run the abap2UI5 gates (abaplint and the abap2UI5 linter) over the project or the changed classes, explain every finding and fix the ones that are clearly safe.
find-sample
Search the three abap2UI5 sample catalogues (samples, samples-controls, samples-stack) and show the best three matches with class, what it shows and a link.
abap2ui5-find-sample
Search the three abap2UI5 sample catalogues (samples, samples-controls, samples-stack) and show the best three matches with class, what it shows and a link.
datasphere-mcp-tools
List all available SAP Datasphere MCP tools with descriptions and usage examples.
widget-validate
Validates SAC custom widget JSON metadata and JavaScript structure for correctness and best practices.