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/ahmedawan-oracle/claude-code-plugins/aidp-engineer-overviewnpx skills add ahmedawan-oracle/claude-code-plugins --skill aidp-engineer-overviewgit 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-engineer-overview)<a href="https://agentmods.dev/skills/ahmedawan-oracle/claude-code-plugins/aidp-engineer-overview"><img src="https://agentmods.dev/badge/skills/ahmedawan-oracle/claude-code-plugins/aidp-engineer-overview.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 | $0.00091 | $0.02276 |
| Opus 5 | $0.00046 | $0.01138 |
| Sonnet 5 | $0.00018 | $0.00455 |
| Haiku 4.5 | $0.00009 | $0.00228 |
Grade A, and why
aidp-engineer-overview 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 5d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aidp-engineer-overview — router & shared environment rules
Pick the right skill for an AIDP task, and own the cross-cutting setup/auth rules every other skill relies on.
When to use
- The user mentions AIDP but the specific operation is unclear, or names several at once.
- The user asks "how do I … in AIDP" / "what can this do".
- Any
aidp-*skill fails with an auth, workspace, or cluster error.
First run
If .aidp/catalog.md does not exist, route to aidp-engineer-bootstrap (one-time setup), then
aidp-catalog-init (grounding), before answering data questions. The plugin is self-contained — it
does not require a bootstrap of any MCP server to run.
Routing table
| User intent | Skill |
|---|---|
| First-run setup / resolve env (region, DataLake OCID, workspace, cluster) | aidp-engineer-bootstrap |
| Create a DataLake instance or workspace (incl. private network) | aidp-workspace-admin |
| Build the catalog map / "discover my lakehouse" | aidp-catalog-init |
| Answer a business question / run read Spark SQL | aidp-analyzing-data |
| Write SQL — INSERT/UPDATE/DELETE/MERGE, CREATE/ALTER/DROP, OPTIMIZE/VACUUM/time-travel | aidp-sql-ddl |
| Create/alter/drop table·view·schema·catalog (control-plane); register an external catalog | aidp-table-management |
| Browse catalogs/schemas/tables/volumes, resolve a name→key | aidp-catalog-explore |
| Profile a table (nulls/distinct/min-max) | aidp-profiling-tables |
| Data-quality rule checks | aidp-data-quality |
| Recent activity / async operations | aidp-observability |
| Load a file into a table | aidp-ingest-file-to-table |
| Workspace files / notebooks CRUD | aidp-workspace-files |
| Volumes (PAR up/down, dirs) | aidp-volumes |
| Build/run/monitor a Job (pipeline, schedule) | aidp-pipelines |
| Author/run a notebook + kernel session | aidp-notebooks |
| Cluster lifecycle / libraries | aidp-cluster-ops |
| Debug a slow/failed Spark job | aidp-spark-debugging |
| Tune/optimize a slow Spark job (skew, spill, shuffle, small files, joins, AQE, Delta, JDBC reads) | aidp-spark-optimization |
| Define metrics / logical model | aidp-semantic-model |
| Register/validate reusable verified queries | aidp-verified-queries |
| Federate / join across multiple sources | aidp-federate |
LLM inside SQL (ai_generate) |
aidp-ai-sql |
| Secrets / credential store | aidp-credentials |
| Delta sharing (shares/recipients) | aidp-data-sharing |
| Git in the workspace | aidp-git |
| Author/deploy/run an agent flow (13 node types, guardrails) | aidp-agent-flows |
| Code an agent in Python (LangGraph / aidputils, high-code) | aidp-agent-highcode |
| Create a reusable standalone tool (SQL/Prompt/RAG/HTTP/Custom/MCP) | aidp-tools |
| Build a Knowledge Base / RAG / vector index | aidp-knowledge-bases |
| Deploy/purge a resource bundle | aidp-bundle |
| Roles / permissions / access (incl. per-resource grants, masking) | aidp-roles-access |
| MLflow experiments / models | aidp-mlops |
| Installed models catalog | aidp-models-catalog |
| Audit logs (enable/retention, search) | aidp-audit |
| User settings / preferences | aidp-user-settings |
| Databricks → AIDP migration | aidp-migration |
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.
- 5d ago First seen · 113 lines · 91 tokens per session scan A c8b086a1b0b7
aidp-engineer-overview is a skill published in the GitHub repository ahmedawan-oracle/claude-code-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 91 tokens to every session and 2,276 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 2026-08-31.
Other skills, from other repositories
pinecone
Managed vector DB for production RAG and search.
embeddings
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.
cognee-community
Use when the user needs something that ships outside cognee core — community database adapters (Qdrant, Milvus, Weaviate, Redis, Pinecone, FalkorDB, Memgraph, DuckDB, NetworkX, …), data-source connectors (Slack, Gmail, Notion, Confluence, Google Drive), custom tasks/pipelines/retrievers (Exa, ScrapeGraph, codify)…
data-engineer
Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms.
similarity-search-patterns
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.
ingesting-into-data-lake
Import data into the AWS data lake from S3 files, local uploads, JDBC databases (Oracle, SQL Server, PostgreSQL, MySQL, RDS, Aurora), Amazon Redshift, Snowflake, BigQuery, DynamoDB, or existing Glue catalog tables (migration). Default target is S3 Tables; standard Iceberg on a general purpose bucket is supported where…