aidp-aws-s3

aidp-aws-s3 is a skill for Claude Code from oracle-samples/oracle-aidp-samples. It costs 80 tokens per session (1,673 once invoked), scanned A, original, UPL-1.0.

A connector for reading and writing AWS S3 from an AIDP notebook. Amazon S3 is a cloud service that stores files and objects, and s3a is the path format used by Spark's S3 connector.

In plain words
What is it for?
Loading data from S3, writing data back to S3, and listing or copying S3 objects with AWS credentials.
Why use it?
It removes the need to configure Spark's S3 connection from scratch. It can also use boto3, an AWS Python library, for file-management tasks outside Spark.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the oracle-ai-data-platform-workbench-spark-connectors plugin — 28 skills shipped together

Good fit Loading data from S3, writing data back to S3, and listing or copying S3 objects with AWS credentials.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/oracle-samples/oracle-aidp-samples/aidp-aws-s3
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.

Any agent
npx skills add oracle-samples/oracle-aidp-samples --skill aidp-aws-s3
Clone the repo
git clone --depth 1 https://github.com/oracle-samples/oracle-aidp-samples

Made for: Claude Code.

Or install oracle-ai-data-platform-workbench-spark-connectors, the plugin that ships this one along with the rest of its 28 skills.

Wrote 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.

agentmods badge for aidp-aws-s3

README.md
[![agentmods](https://agentmods.dev/badge/skills/oracle-samples/oracle-aidp-samples/aidp-aws-s3/github.svg)](https://agentmods.dev/skills/oracle-samples/oracle-aidp-samples/aidp-aws-s3)
Your own site
<a href="https://agentmods.dev/skills/oracle-samples/oracle-aidp-samples/aidp-aws-s3"><img src="https://agentmods.dev/badge/skills/oracle-samples/oracle-aidp-samples/aidp-aws-s3/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.

agentmods 80×15 button for aidp-aws-s3

Your own site · 80×15
<a href="https://agentmods.dev/skills/oracle-samples/oracle-aidp-samples/aidp-aws-s3"><img src="https://agentmods.dev/badge/skills/oracle-samples/oracle-aidp-samples/aidp-aws-s3.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,673 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown 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 5.1 $0.00080 $0.01673
Opus 5 $0.00040 $0.00837
Sonnet 5 $0.00016 $0.00335
Haiku 4.5 $0.00008 $0.00167

Measured 6d ago against content hash 7f7aa46e0dc1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

aidp-aws-s3 scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

import os, urllib.request
ai/claude-code-plugins/oracle-ai-data-platform-workbench-spark-connectors/skills/aidp-aws-s3/SKILL.md · 106 lines

The source is not reproduced here

Licensed UPL-1.0

The repository is licensed UPL-1.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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. 6d ago First seen · 106 lines · 80 tokens per session scan A 7f7aa46e0dc1

Subscribe to this mod's changes

aidp-aws-s3 is a skill published in the GitHub repository oracle-samples/oracle-aidp-samples (46 stars, last pushed yesterday), licensed UPL-1.0. It adds 80 tokens to every session and 1,673 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

ray-data

Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.

synthetic-sciences/openscience · 70 tokens

spark-serverless-reliability-and-state-management

Enforces timeout-aware rollbacks, resumable checkpoints, and orphan cleanup for serverless Spark workloads on AWS Lambda, Glue, and similar runtimes. Use when writing or reviewing Spark jobs in serverless environments, S3 checkpoint patterns, partial-failure recovery, or IceGuard-style state management.

vaquarkhan/data-engineering-agent-skills · 69 tokens

ds-deploy

Stands a packaged model up as a callable endpoint with prediction logging against the live baseline, drift detection, and a rollback pointer. Hard gate — refuses full traffic without all three, and stops before any remote or cloud push. Use when someone asks to serve, deploy, or stand up a model endpoint. Use when…

StamKavid/last-ds-mile · 85 tokens

alterlab-modal

Runs Python code in the cloud with Modal — serverless containers, on-demand GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that need GPU acceleration or dynamic scaling. Part of the AlterLab Academic Skills suite.

AlterLab-IEU/AlterLab-Academic-Skills · 61 tokens

r-parallel-distributed

R distributed computing with sparklyr, future.batchtools. Use for cluster and cloud computing.

LeoLin990405/r-analytics-skill · 25 tokens

cloud-infra-data

AWS/GCP/Azure data infrastructure — S3/GCS/ADLS partitioning, BigQuery slot management, Redshift spectrum, Snowflake warehouses, IAM roles for data access, cost optimization, and managed service selection. Use this skill whenever the user is deploying a pipeline to cloud, choosing between managed data services…

Methasit-Pun/data_engineer_claude_skills · 157 tokens