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-customizinggit 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-customizing)<a href="https://agentmods.dev/skills/marcellourbani/vscode_abap_remote_fs/sap-customizing"><img src="https://agentmods.dev/badge/skills/marcellourbani/vscode_abap_remote_fs/sap-customizing.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00103 | $0.04294 |
| Opus 5 | $0.00051 | $0.02147 |
| Sonnet 5 | $0.00021 | $0.00859 |
| Haiku 4.5 | $0.00010 | $0.00429 |
Grade A, and why
sap-customizing 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 8d 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SAP Customizing — Tracing SPRO to Data
Critical Warning
Your training data about SAP customizing is almost certainly wrong. Do NOT guess which tables store which customizing data. Follow the lookup procedures below to discover the truth from the system itself.
Always read table structures with get_object_lines before querying. Never hardcode field names from memory.
Text fields are case-sensitive. Use aggressive wildcards: %aterial%ype% finds "Material Types", "material type", etc.
Minimize SQL round-trips. Use JOINs to combine lookups into single queries.
Present only useful information to the user. Internal IDs like activity IDs (SIMG_CFMENUOLMSOMS2), tree GUIDs (368DDFAB...), and node IDs are technical plumbing — never include them in your answer. Only show the user: SPRO menu path, table names, view/cluster names, transaction codes, and descriptions.
Metadata Tables
IMG Activity Layer (SPRO tree → activity)
| Table | Purpose | Key Fields |
|---|---|---|
| CUS_IMGACH | IMG activity header | activity, c_activity (links to CUS_ACTH), tcode |
| CUS_IMGACT | IMG activity texts (language-dependent) | spras, activity, text |
Customizing Activity Layer (activity → objects)
| Table | Purpose | Key Fields |
|---|---|---|
| CUS_ACTH | Activity header | act_id, act_type, tcode |
| CUS_ACTT | Activity texts (language-dependent) | spras, act_id, text |
| CUS_ACTOBJ | Core — links activities to maintenance objects | act_id, objecttype, objectname, tcode |
CUS_ACTH.act_type: C = customizing (most common), E = BAdI definition, I = BAdI implementation. Note: filtering by act_type = 'E' is unreliable — many BAdI activities use act_type = 'C'. To find BAdIs, search CUS_IMGACT text for %BAdI% or %Business Add-In%. This mainly works for IS solutions (IS-Retail, IS-Utilities, HR). Core modules (MM, FI, SD, PP) often do not register BAdIs in the IMG at all — for those, use SE18 directly with patterns like MB_*, ME_*, MM_*.
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.
- 8d ago First seen · 278 lines · 103 tokens per session scan A 7ff29cb8ab5c
sap-customizing is a skill published in the GitHub repository marcellourbani/vscode_abap_remote_fs (388 stars, last pushed 6d ago), licensed MIT. It adds 103 tokens to every session and 4,294 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
markdown
Markdown formatting rules for this project. Apply when writing or editing any .md or .mdx file, including documentation and website content.
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.
research
Run deep research on any topic using the Deep Research MCP server. Use this skill whenever the user wants to research a topic, gather information, find sources, or create a research document. Triggers on: 'research this', 'find out about', 'gather information on', 'I need to understand', 'deep dive into', or any…
date-formatter
Converts dates between formats and handles timezone differences.
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.
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.