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/arize-ai/arize-claude-code-plugin/arize-datasetsnpx skills add Arize-ai/arize-claude-code-plugin --skill arize-datasetsgit clone --depth 1 https://github.com/Arize-ai/arize-claude-code-pluginWhat 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 | $0.00079 | $0.02528 |
| Opus 5 | $0.00039 | $0.01264 |
| Sonnet 5 | $0.00016 | $0.00506 |
| Haiku 4.5 | $0.00008 | $0.00253 |
Grade A, and why
arize-datasets 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 3d 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 — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arize AX Datasets
Manage datasets in the Arize AI platform using the ax CLI.
Prerequisites
The user must have:
- Arize AX CLI installed (
pip install arize-ax-cli) - CLI configured with valid credentials (
ax config init)
Core Dataset Commands
List All Datasets
ax datasets list
Options:
--output <format>- Output format:table(default),json,csv,parquet--profile <name>- Use specific configuration profile--limit <n>- Limit number of results--offset <n>- Skip first n results (pagination)
Examples:
# List as table (default)
ax datasets list
# List as JSON
ax datasets list --output json
# List with pagination
ax datasets list --limit 10 --offset 0
# Use production profile
ax datasets list --profile production
Extracting Dataset IDs:
To find a specific dataset ID for use in other operations:
# Get all dataset IDs and names as JSON
ax datasets list --output json | jq '.[] | {id: .id, name: .name}'
# Find a dataset ID by name
ax datasets list --output json | jq -r '.[] | select(.name == "Training Data") | .id'
# Save dataset ID to a variable
DATASET_ID=$(ax datasets list --output json | jq -r '.[] | select(.name == "Training Data") | .id')
echo "Found dataset: $DATASET_ID"
# Use the ID in subsequent commands
ax datasets get "$DATASET_ID"
ax datasets delete "$DATASET_ID"
Without jq (using grep):
# List with grep to find dataset
ax datasets list --output json | grep -A 2 "Training Data" | grep "id"
# More reliable pattern
ax datasets list --output json | grep -B 1 '"name": "Training Data"' | grep "id" | cut -d'"' -f4
Get Dataset Details
Retrieve information about a specific dataset:
ax datasets get <dataset-id>
Options:
--output <format>- Output format--profile <name>- Configuration profile to use
Examples:
# Get dataset details
ax datasets get ds_abc123xyz
# Get as JSON
ax datasets get ds_abc123xyz --output json
# Get from production environment
ax datasets get ds_abc123xyz --profile production
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.
- 3d ago First seen · 384 lines · 79 tokens per session scan A f023444fc7e6
arize-datasets is a skill published in the GitHub repository Arize-ai/arize-claude-code-plugin (21 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 2,528 once invoked, about $0.0004 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 skills, from other repositories
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
bigquery-ai-ml
Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform time-series forecasting, predict values, detect outliers or anomalies, find key drivers, perform semantic search or vector search, classify text, calculate similarity…
ondb
A logical analysis and reasoning tool for AI. Use when decomposing documents into structured knowledge, querying entities and relations, validating consistency, or indexing files. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", "analyze this document", entity CRUD, or cross-skill…
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
mixed-precision
Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.
sparse-autoencoder-training
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.