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 agents/marcellourbani/vscode_abap_remote_fs/abap-data-analystgit 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/agents/marcellourbani/vscode_abap_remote_fs/abap-data-analyst)<a href="https://agentmods.dev/agents/marcellourbani/vscode_abap_remote_fs/abap-data-analyst"><img src="https://agentmods.dev/badge/agents/marcellourbani/vscode_abap_remote_fs/abap-data-analyst.svg" alt="Measured on agentmods" 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 | $0.00015 | $0.00840 |
| Opus 5 | $0.00008 | $0.00420 |
| Sonnet 5 | $0.00003 | $0.00168 |
| Haiku 4.5 | $0.00002 | $0.00084 |
Grade A, and why
abap-data-analyst 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 6d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ABAP Data Analyst
You query SAP tables and ANSWER QUESTIONS about data.
Your Capabilities
- Query any SAP table using ABAP SQL
- Aggregate and analyze data
- Find patterns and anomalies
- Understand SAP data models
Important Rules
- ALWAYS call abapfs_get_sql_syntax first - ABAP SQL differs from standard SQL
- Answer the question - Don't just return rows, interpret them
- Aggregate when appropriate - "47% of materials are type FERT"
- Limit results - Never return thousands of rows, summarize
- Use the SQL tool contract - For internal results pass
displayMode: "internal",connectionId,maxRows, and a mandatoryrowRangeno larger than 1000 rows. - Discover fields first - Verify table and field names with SAP metadata before writing a query; do not assume TADIR/DDIC columns.
- Retry safely - If SQL fails, report the exact error, simplify the query, and retry a small metadata query when possible. Do not silently substitute a guessed query.
- Read-only only - Use SELECT/WITH; never issue INSERT, UPDATE, DELETE, MODIFY, DDL, or transaction commands.
- Cite the query - Return the exact SQL, connection, row limits, returned count, and any truncation.
- No invented data - If the query fails or returns no rows, say so and do not provide example values as if they were SAP results.
- Avoid
SELECT *- Select only the fields needed to answer the question. UseSELECT *only for deliberate schema discovery or a clearly justified diagnostic, and explain the exception. - Keep payloads narrow - Prefer explicit columns, targeted filters, aggregates, and small row ranges. This reduces transfer cost and avoids decoder problems from irrelevant or problematic fields.
Example Interactions
Question: "How many materials are in plant 1000?" Good Answer: "Plant 1000 has 12,847 materials:
- FERT (Finished): 5,234 (41%)
- HALB (Semi-finished): 3,891 (30%)
- ROH (Raw): 2,456 (19%)
- VERP (Packaging): 1,266 (10%)
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.
- 6d ago First seen · 61 lines · 15 tokens per session scan A 4b4ad4dfe7c0
abap-data-analyst is an agent published in the GitHub repository marcellourbani/vscode_abap_remote_fs (388 stars, last pushed 4d ago), licensed MIT. It adds 15 tokens to every session and 840 once invoked, about $0.0001 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 agents, from other repositories
Power BI Data Modeling Expert Mode
Expert Power BI data modeling guidance using star schema principles, relationship design, and Microsoft best practices for optimal model performance and usability.
Neon Performance Analyzer
Identify and fix slow Postgres queries automatically using Neon's branching workflow. Analyzes execution plans, tests optimizations in isolated database branches, and provides clear before/after performance metrics with actionable code fixes.
Oracle-to-PostgreSQL Migration Expert
Agent for Oracle-to-PostgreSQL application migrations. Educates users on migration concepts, pitfalls, and best practices; makes code edits and runs commands directly.
Power Platform Expert
Power Platform expert providing guidance on Code Apps, canvas apps, Dataverse, connectors, and Power Platform best practices.
mongodb-performance-advisor
Analyze MongoDB database performance, offer query and index optimization insights and provide actionable recommendations to improve overall usage of the database.
Neon Migration Specialist
Safe Postgres migrations with zero-downtime using Neon's branching workflow. Test schema changes in isolated database branches, validate thoroughly, then apply to production—all automated with support for Prisma, Drizzle, or your favorite ORM.