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 marcellourbani/vscode_abap_remote_fs --skill sap-background-jobsgit clone --depth 1 https://github.com/marcellourbani/vscode_abap_remote_fsWrote 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/marcellourbani/vscode_abap_remote_fs/sap-background-jobs)<a href="https://agentmods.dev/skills/marcellourbani/vscode_abap_remote_fs/sap-background-jobs"><img src="https://agentmods.dev/badge/skills/marcellourbani/vscode_abap_remote_fs/sap-background-jobs/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/marcellourbani/vscode_abap_remote_fs/sap-background-jobs"><img src="https://agentmods.dev/badge/skills/marcellourbani/vscode_abap_remote_fs/sap-background-jobs.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 | $0.00046 | $0.03726 |
| Opus 5 | $0.00023 | $0.01863 |
| Sonnet 5 | $0.00009 | $0.00745 |
| Haiku 4.5 | $0.00005 | $0.00373 |
Grade A, and why
sap-background-jobs 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 3d 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 — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SAP Background Job Investigation
Overview
This is an investigation procedure, not a callable background-job connector. Use the read-only SQL and dump tools with TBTCO, TBTCP, TBTCJOBLOG0-9, and T100 as described below. The procedure covers finding job instances, reading logs, and diagnosing failures including runtime dumps.
Rules
- ALWAYS identify the exact job instance with both
JOBNAMEandJOBCOUNTbefore investigating it - Treat every SQL error as a likely agent query defect. Stop the investigation, diagnose the reported table, field, type, grouping, or ABAP SQL syntax problem, correct the query, and rerun the same query before continuing. Do not treat a failed query as an empty result or switch to unrelated tables/tools without explaining why the corrected query cannot run.
- ALWAYS follow the partition lookup and fallback sequence in Step 4, then count the matching entries before retrieving a log
- NEVER attempt to build the full job log for large logs (>100 entries) — use targeted queries instead (filter by msgtype, or read only last N entries)
- ALWAYS check TBTCP for every job step, including its program, variant, status, and
AUTHCKNAMexecution user - NEVER use the job scheduler to identify the runtime context of a failed step.
TBTCO-SDLUNAMEis the user who scheduled the job, whileTBTCP-AUTHCKNAMis the execution user for that specific step. A multi-step job can use a different execution user for each step - ALWAYS resolve every message through T100 as described in Step 8 before interpreting its text or
MSGV1-MSGV4values; treat any business meaning inferred beforehand as unproven - For aborted jobs (status = 'A'), ALWAYS check the last few log entries first — they contain the failure reason
- When message 00/671 appears, follow the dump investigation in Step 9
- Custom messages (message class starting with Z* or Y*) indicate custom code is writing to the job log — these are often the most informative for business logic failures
- For periodic jobs, check
TBTCO.periodic = 'X'and the period fields (prdmins,prdhours,prddays,prdweeks,prdmonths) to understand scheduling
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.
- 3d ago First seen · 290 lines · 46 tokens per session scan A ffb0c8f348af
sap-background-jobs is a skill published in the GitHub repository marcellourbani/vscode_abap_remote_fs (389 stars, last pushed 2d ago), licensed MIT. It adds 46 tokens to every session and 3,726 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 2026-09-08.
Other skills, from other repositories
mma-investigator
Expert system for investigating MMA (Multi-Metric Allocator) behavior on CockroachDB clusters. Helps oncall engineers diagnose load imbalances, understand rebalancing decisions, and identify why MMA did or didn't act.
triage-issues
Triage GitHub issues in the googleapis/mcp-toolbox repo: propose the correct labels (type / priority / product / status), check for duplicates, verify a bug has enough info to act on, and draft a triage comment. Use whenever a maintainer asks you to triage, label, categorize, prioritize, or "look at" an issue (or a…
oh-my-posh
Install, configure, or troubleshoot Oh My Posh/ohmyposh: shell init, themes, segments, Nerd Font icons, and prompt setup on PowerShell, zsh, bash, or fish.
postgresql-indexing
PostgreSQL indexing best practices for Prowler: index design, partial indexes, partitioned table indexing, EXPLAIN ANALYZE validation, concurrent operations, monitoring, and maintenance. Trigger: When creating or modifying PostgreSQL indexes, analyzing query performance with EXPLAIN, debugging slow queries, reviewing…
graphjin-eval
Create, extend, run, baseline, and diagnose GraphJin agent evaluations through the graphjin eval CLI.
redux-to-swr
Migrate React components from Redux + Saga to SWR hooks. Use when converting data fetching from Redux store (reducers, sagas, selectors, connect HOC) to SWR-based hooks in CockroachDB DB Console or cluster-ui.