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 adt-api-discoverygit 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/adt-api-discovery)<a href="https://agentmods.dev/skills/marcellourbani/vscode_abap_remote_fs/adt-api-discovery"><img src="https://agentmods.dev/badge/skills/marcellourbani/vscode_abap_remote_fs/adt-api-discovery/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/adt-api-discovery"><img src="https://agentmods.dev/badge/skills/marcellourbani/vscode_abap_remote_fs/adt-api-discovery.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00108 | $0.02607 |
| Opus 5 | $0.00054 | $0.01303 |
| Sonnet 5 | $0.00022 | $0.00521 |
| Haiku 4.5 | $0.00011 | $0.00261 |
Grade A, and why
adt-api-discovery 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADT API Discovery — Skill
You are investigating SAP ADT REST API endpoints. Your goal is to determine the full HTTP contract for any endpoint: URL, HTTP methods, request/response XML format, content types, and headers.
Prerequisites
Before using this skill, run the abapfs_export_adt_discovery tool with the target connectionId. This creates a folder with markdown files containing the raw discovery data. Read these files first.
The ADT Architecture
Every ADT REST endpoint exists because of this chain:
SICF node: /sap/bc/adt
└── Handler: CL_ADT_WB_RES_APP
└── BAdI: BADI_ADT_REST_RFC_APPLICATION
└── RES_APP class (inherits CL_ADT_DISC_RES_APP_BASE or CL_ADT_RES_APP_BASE)
└── register_resources() method
├── registry->register_discoverable_resource(url, handler_class, ...)
├── registry->register_resource(template, handler_class)
└── collection->register_disc_res_w_template(relation, template, handler_class)
└── Handler class (inherits CL_ADT_REST_RESOURCE)
├── GET/POST/PUT/DELETE method overrides
├── Content handler factory → get_handler_for_xml_using_st()
└── response->set_body_data() / request->get_body_data()
Step-by-Step Investigation Process
Step 1: Find the endpoint in discovery
Search workspaces.md for the URL or keyword. This gives you the collection href and any template links (URL templates with parameters, relations, content types).
If the endpoint isn't in discovery, it may be a hidden resource — registered via register_resource() instead of register_discoverable_resource(). You'll find it in Step 2.
Step 2: Find the RES_APP class
The RES_APP class is what registers the endpoint. To find which one:
Option A — Match by URL pattern: The discovery URL /sap/bc/adt/oo/classes is registered by a RES_APP whose register_resources() method contains that URL. Search for it:
Use abapfs_search_object_source on RES_APP classes from res-app-classes.md, searching for the URL segment (e.g., '/oo/classes' or '/datapreview/')
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 · 214 lines · 108 tokens per session scan A 22139fcda01c
adt-api-discovery is a skill published in the GitHub repository marcellourbani/vscode_abap_remote_fs (388 stars, last pushed today), licensed MIT. It adds 108 tokens to every session and 2,607 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
at_client_skills-sdk
Use this skill when a developer is building a Dart or Flutter app that depends on atclient or atclientflutter from pub.dev, stores or shares data via the Atsign Protocol, needs onboarding (CRAM new-atsign, atKeys file, keychain, APKAM) or APKAM enrollment, or asks about AtCollection , CItem , Query , sub-collections…
cds-view-entities
Help with CDS (Core Data Services) view entity development including data modeling, annotations, associations, compositions, access controls, aggregate expressions, built-in functions, and input parameters. Use when users ask about CDS views, CDS view entities, CDS annotations, CDS associations, CDS compositions, CDS…
rap
Help with RAP (RESTful ABAP Programming Model) development including behavior definitions, EML statements, managed and unmanaged BOs, draft handling, actions, validations, determinations, side effects, and business events. Use when users ask about RAP, BDEF, BDL, EML, behavior definitions, behavior pools, managed BO…
sap-expert
Expert in SAP ERP systems, ABAP programming, SAP HANA, S/4HANA, Fiori applications, and SAP integration patterns including OData, RFC, and IDoc. Use when the user mentions ERP, enterprise, business apps, ABAP, HANA, or S/4HANA, or when the task involves SAP Ecosystem, ABAP Development, Integration Technologies, or…
abap-cloud
Help with ABAP Cloud development including the 3-tier extensibility model, ABAP Cloud language version restrictions, wrapper patterns for unreleased APIs, clean core principles, and key user vs developer extensibility. Use when users ask about ABAP Cloud, ABAP for Cloud Development, clean core, 3-tier model, tier 1…
badi-enhancement
Help with BAdI (Business Add-In) development and the ABAP enhancement framework including new BAdIs, fallback classes, filter-based BAdIs, enhancement spots, enhancement implementations, key user extensibility, classic BAdIs, and the new enhancement framework. Use when users ask about BAdI, BAdIs, Business Add-In…