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/abap2UI5/abap2UI5Wrote 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/abap2ui5/abap2ui5/abap2ui5-check)<a href="https://agentmods.dev/commands/abap2ui5/abap2ui5/abap2ui5-check"><img src="https://agentmods.dev/badge/commands/abap2ui5/abap2ui5/abap2ui5-check/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/abap2ui5/abap2ui5/abap2ui5-check"><img src="https://agentmods.dev/badge/commands/abap2ui5/abap2ui5/abap2ui5-check.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 | $0.00042 | $0.01028 |
| Opus 5.5 | $0.00017 | $0.00411 |
| Sonnet 5.5 | $0.00008 | $0.00206 |
| Haiku 4.5 | $0.00004 | $0.00103 |
Grade A, and why
abap2ui5-check 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 today.
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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run the abap2UI5 gates on: the text after the command
1. Scope
- An argument names the files or folder to check.
- Without one: the
.clas.abap/.clas.xmlfiles thatgit status --porcelainandgit diff --name-onlyreport as changed or new. Nothing changed (or no git): the wholesrc/folder. Say which scope you took.
2. Run the gates
Pick the first that applies:
- The project has app-template's scripts (
package.jsonhas acheckscript that runsabaplintandabap2ui5lint):npm run check:abapandnpm run check:abap2ui5, as two commands -npm run checkchains them with&&, so an abaplint finding (a missing BOM is one) hides every linter finding until it is fixed. Both lint the whole project; report the findings in scope first. Withoutnode_modules, runnpm cifirst (ask before installing). - Otherwise, two commands:
- abaplint, when the project has an
abaplint.json/abaplint.jsonc:npx --yes @abaplint/cli <that file>. Without one, skip it and say so - do not invent a config. - the abap2UI5 linter:
npx --yes @abap2ui5/linter <files or folder>(add--no-renderwhen the render gate is not installed and says so). It honours the project'sabap2ui5lint.jsonc.
- abaplint, when the project has an
- No shell, or npm unavailable, but the MCP server is there:
validate_view { abap_source, project_dir }per class. That covers the linter, not abaplint - say so.
3. Explain
For every finding: file:line, the rule id, what it means in one sentence,
and the fix. The linter explains its own rules
(npx --yes -p @abap2ui5/linter abap2ui5lint --explain <rule-id>, or
validate_view { explain: true }). Group by file; errors before warnings
before hints.
Then go over what the gates cannot see, using the
abap-check and ui5-check skills (MCP pitfalls
lists both): the .clas.xml byte format (BOM, LF, final newline,
<CLSNAME>, <WITH_UNIT_TESTS>, '), activation traps, icons and
controls that do not exist in UI5 1.71. Report only what you actually find
in the files in scope.
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.
- today First seen · 74 lines · 42 tokens per session scan A 54dfbf350ea1
abap2ui5-check is a command published in the GitHub repository abap2UI5/abap2UI5 (385 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 1,028 once invoked, about $0.0002 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 2026-10-16.
Other commands, from other repositories
sap-debug
Trigger structured root cause analysis for SAP issues — runtime errors, dump analysis, integration failures, configuration problems, or unexpected system behavior.
sap-korean-tax-invoice-debug
A Korean-language troubleshooting command for electronic tax invoices, which are digital business invoices reported through Korea's tax systems, across SAP and several invoice providers.
sap-performance-check
A checklist for diagnosing SAP system performance across hardware, databases, SAP work processes, application code, and networks. SAP is business software used to run operations such as finance, purchasing, and production.
sap-session-start
A command guide for starting an evidence-based SAP troubleshooting session. It records an initial symptom, creates a session ID, and prepares folders for evidence, hypotheses, requests, and conclusions.
sap-transport-debug
A command guide for diagnosing failed SAP STMS transports. STMS is SAP's system for moving development changes between systems; the guide covers transport status, logs, return codes, and common dependency problems.
sap-payment-run-debug
A guided troubleshooting process for failed F110 payment runs in SAP, where F110 creates scheduled payments to vendors.