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 agentmods add skills/clementringot/rosa/sap-released-objectsnpx skills add ClementRingot/ROSA --skill sap-released-objectsgit clone --depth 1 https://github.com/ClementRingot/ROSAWhat 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 | $0.00064 | $0.03402 |
| Opus 5 | $0.00032 | $0.01701 |
| Sonnet 5 | $0.00013 | $0.00680 |
| Haiku 4.5 | $0.00006 | $0.00340 |
Grade A, and why
ROSA — Released Objects Search Assistant 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.
This is a copy
95% identical to ROSA — Released Objects Search Assistant — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 386 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Instructions
Base URL
https://sap-released-objects-server-production.up.railway.app
All endpoints return JSON. All parameters are passed as query string. All endpoints support CORS.
Common Parameters
These parameters appear on most endpoints:
| Parameter | Default | Values | Description |
|---|---|---|---|
system_type |
public_cloud |
public_cloud, btp, private_cloud, on_premise |
Target SAP system. public_cloud and btp only have Level A objects. |
clean_core_level |
A |
A, B, C, D |
Maximum level (cumulative). A = Released APIs, B = + Classic APIs, C = + Internal, D = + noAPI |
version |
latest |
latest, 2022, 2023_3, etc. |
PCE version. Only relevant for private_cloud and on_premise. |
Endpoints
GET /api/search
Search for SAP objects with fuzzy matching and relevance ranking.
Parameters:
| Parameter | Required | Default | Description |
|---|---|---|---|
query |
yes | — | Search term. Either a direct SAP object name (e.g. I_PurchaseOrderItemAPI01) or a functional object in natural language, always singular (e.g. purchase order, not purchase orders). Max 200 chars. |
system_type |
no | public_cloud |
Target system |
clean_core_level |
no | A |
Max level |
version |
no | latest |
PCE version |
object_type |
no | all | TADIR type filter: CLAS, DDLS, TABL, INTF, BDEF, etc. |
app_component |
no | all | Application component prefix: MM-PUR, FI-GL, SD-SLS, etc. |
state |
no | all | released, deprecated, classicAPI, notToBeReleased, noAPI, stable |
limit |
no | 25 | Results per page (1-100) |
offset |
no | 0 | Pagination offset |
Example:
GET /api/search?query=purchase+order&object_type=DDLS&limit=5
Response:
{
"query": "purchase order",
"system_type": "public_cloud",
"clean_core_level": "A",
"version": "latest",
"total": 42,
"offset": 0,
"limit": 5,
"hasMore": true,
"objects": [
{
"objectType": "DDLS",
"objectName": "I_PURCHASEORDER",
"state": "released",
"cleanCoreLevel": "A",
"applicationComponent": "MM-PUR-PO",
"softwareComponent": "S4CORE",
"typeDescription": "Data Definition Language Source (CDS View)",
"relevance": 100
}
]
}
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 · 386 lines · 64 tokens per session scan A 74f7f5ccaf34
ROSA — Released Objects Search Assistant is a skill published in the GitHub repository ClementRingot/ROSA (25 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 3,402 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to ROSA — Released Objects Search Assistant, differing in 4 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…