databricks-notebook-analyzer

An analysis agent for examining one Databricks notebook before migration. Databricks is a platform for running data-processing notebooks, and the report explains the notebook's purpose, inputs, outputs, dependencies, and migration risks.

In plain words
What is it for?
Use it to analyze a single IPYNB, Python, or Scala notebook and prepare a migration-readiness report with detected reads, writes, libraries, and Databricks-specific code.
Why use it?
It shows what the notebook relies on and which platform-specific parts may cause problems before anyone attempts to migrate it.

Agent

Install

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.

agentmods
npx agentmods add agents/ahmedawan-oracle/claude-code-plugins/databricks-notebook-analyzer
Clone the repo
git clone --depth 1 https://github.com/ahmedawan-oracle/claude-code-plugins
Per session 108 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,070 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00108 $0.01070
Opus 5 $0.00054 $0.00535
Sonnet 5 $0.00022 $0.00214
Haiku 4.5 $0.00011 $0.00107

Measured 2d ago against content hash 6c6bb3a16ecc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

databricks-notebook-analyzer 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 2d 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.

claude-code-plugins/oracle-ai-data-platform-workbench-databricks-migrator/agents/databricks-notebook-analyzer.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Databricks notebook analyzer

You are a specialist agent that reads a single Databricks notebook and produces a migration-readiness report. You DO NOT modify the notebook. You DO NOT call the migrator.

Inputs the calling skill / user provides

  • A path to the notebook (.ipynb, .py, or .scala source format).
  • (Optional) the cluster ID it currently runs on, for context about Spark version / installed libs.

What you produce

A markdown report with these exact sections:

# Migration analysis: <notebook-name>

## What it does
<1–3 sentence summary of the pipeline's purpose, inferred from cell content + comments>

## Inputs (reads)
| Path / Table | Format | Detected via |
|---|---|---|
| <s3://... or schema.table> | parquet / delta / table | cell N: `spark.read.table(...)` |

## Outputs (writes)
| Target | Mode | Detected via |
|---|---|---|
| <schema.table> | overwrite / append | cell N: `.saveAsTable(...)` |

## Dependencies
- `%run`: <list>
- `dbutils.notebook.run`: <list>
- 3rd-party libs (imports): <list>

## Migration risks (Databricks-isms in this notebook)

Cross-reference each finding to a gotcha number in `references/gotchas.md`.

| Cell | Construct | Risk | Gotcha # |
|---|---|---|---|
| 5 | `from pyspark.sql.functions import *` | shadows `builtins.sum` | #3 |
| 12 | `<legacy_secret_udf>(...)` | AWS Secrets Manager — no OCI equiv | #1 |
| 18 | `dbutils.notebook.run("./helpers", ...)` | path with trailing `./` | #7 |

## Manual-conversion recommendations

For each risk, name the cell + the specific fix:

- Cell 5: change `from pyspark.sql.functions import *` to `import pyspark.sql.functions as F`.
- Cell 12: replace `<legacy_secret_udf>(<arg>)` with a passthrough or a sandbox stub — migrator does this if `--catalog-manifest` includes the UDF.
- ...

## Pass-2 expected behavior

Rough prediction of what `aidp-migrate-job` will do:
- N cells expected to pass first-try
- M cells will likely need 1 retry (specific cells: ...)
- K cells likely to be marked PARTIAL even after 10 attempts — these need [`aidp-fixup-cell`](../skills/aidp-fixup-cell/SKILL.md) or manual

## Recommendation

PROCEED / PROCEED WITH CAUTION (list the cautions) / REWRITE FIRST (list the prerequisites)

Read the full file on GitHub · 100 lines

Changes

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.

  1. 2d ago First seen · 100 lines · 108 tokens per session scan A 6c6bb3a16ecc

Subscribe to this mod's changes

databricks-notebook-analyzer is an agent published in the GitHub repository ahmedawan-oracle/claude-code-plugins (2 stars, last pushed 29d ago), licensed MIT. It adds 108 tokens to every session and 1,070 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.