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 ahmedawan-oracle/claude-code-plugins --skill aidp-analyzing-datagit clone --depth 1 https://github.com/ahmedawan-oracle/claude-code-pluginsWrote 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/ahmedawan-oracle/claude-code-plugins/aidp-analyzing-data)<a href="https://agentmods.dev/skills/ahmedawan-oracle/claude-code-plugins/aidp-analyzing-data"><img src="https://agentmods.dev/badge/skills/ahmedawan-oracle/claude-code-plugins/aidp-analyzing-data/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/ahmedawan-oracle/claude-code-plugins/aidp-analyzing-data"><img src="https://agentmods.dev/badge/skills/ahmedawan-oracle/claude-code-plugins/aidp-analyzing-data.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 | $0.00100 | $0.01071 |
| Opus 5.5 | $0.00040 | $0.00428 |
| Sonnet 5.5 | $0.00020 | $0.00214 |
| Haiku 4.5 | $0.00010 | $0.00107 |
Grade A, and why
aidp-analyzing-data 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 1mo 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aidp-analyzing-data — natural language → Spark SQL
Answer business questions by grounding in the catalog/semantic model, reusing verified queries when
possible, then executing Spark SQL via the bundled scripts/aidp_sql.py helper.
When to use
- Any data question, or "run this SQL on AIDP".
Source is an external / non-lakehouse system (Fusion, EPM, Oracle ADB/ExaCS, Snowflake, S3, …)? This skill is lakehouse-native Spark SQL. To pull from an external source, use the
oracle-ai-data-platform-workbench-spark-connectorsplugin'saidp-<source>skill (install it if absent; run itsaidp-connectors-bootstrapskill once to push the helper package to the cluster), oraidp-federateto join across sources.
Workflow (grounding-first — this is the accuracy lever)
- Verified-query match. Read
.aidp/verified-queries.md; if averified: trueentry closely matches the question (similar text + table overlap), reuse its SQL (adapt only dates/bind values) and say so. - Ground. Otherwise read
.aidp/catalog.md+.aidp/semantic.md: map concepts→tables via Quick Reference/synonyms, use recorded join keys (don't guess joins), use value dictionaries for WHERE literals, prefer metric SQL expressions from the semantic model. If the catalog cache is missing, runaidp-catalog-initfirst. - Scope small. Use the few tables the question needs; for big fact tables add date filters; consider a pre-joined view for repeated complex asks.
- Execute. Run the SQL via the bundled helper — it mints a UPST from the api_key DEFAULT profile and
auto-creates a scratch notebook on the target cluster (no MCP, no AIDP_SESSION required):
Returns JSONpython "$PLUGIN_DIR/scripts/aidp_sql.py" \ --region <region> --datalake <DATALAKE_OCID> --workspace <ws> --cluster <cluster-key> \ --code "spark.sql('''<SQL>''').show(50, truncate=False)"{status, execution_count, outputs, spark_job_ids, error}. Each invocation runs the cell; keep the same<SQL>shape across follow-ups. Smoke-test connectivity with--code "spark.sql('SELECT 1').show()". - Present the result clearly (table + a one-line read of what it shows). Show the SQL you ran.
- Cache the learning. Offer to save a new concept→table mapping to
.aidp/catalog.mdand/or register the working query viaaidp-verified-queries(which validates before marking it verified).
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.
- 1mo ago First seen · 58 lines · 100 tokens per session scan A 00057957cb55
aidp-analyzing-data is a skill published in the GitHub repository ahmedawan-oracle/claude-code-plugins (3 stars, last pushed 2mo ago), licensed MIT. It adds 100 tokens to every session and 1,071 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.
atlas-mssql
SQL Server specifics for Atlas (also Azure SQL and MSSQL): login, dev database and URL scope (mode=schema vs mode=database, the database query parameter), compatibility level and collation, system-generated constraint names, clustered index defaults and datetime2 precision in HCL, GO batches and the delimiter…
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
nornicdb-cypher-queries
Pick fast, predictable Cypher query shapes in NornicDB — point lookups, batch retrieval, pagination, search, traversal, batched UNWIND/MERGE writes, cleanup, multi-tenant isolation. Use when writing or reviewing Cypher whose latency or throughput matters; maps user intent to the executor's hot-path query templates.
volcengine-rds-postgresql
A tool for operating PostgreSQL databases hosted by Volcano Engine's managed database service. PostgreSQL is a relational database used to store structured application data.