---
title: "masthead-agent-tools"
description: "Masthead Agent Tools for BigQuery Data Observability and FinOps"
canonical: https://agentpluginsdirectory.com/plugins/masthead-agent-tools
last-updated: 2026-09-11
---

# masthead-agent-tools
Masthead Agent Tools for BigQuery Data Observability and FinOps
- Slug: masthead-agent-tools
- Publisher: masthead-data
- Repository: https://github.com/masthead-data/for-agents
- Manifest: plugin.json
- Version: 1.2.0
- Category (editorial): other
- Skills: 8 (masthead-asset-prioritization, masthead-compute-savings-with-pipelines, masthead-compute-savings-with-workload-assignments, masthead-incident-triaging, masthead-savings, masthead-storage-savings-with-datasets, masthead-storage-savings-with-tables, masthead-triage)
- MCP servers: 1 (masthead)
- Stars: 0
- Repository created: 2026-03-19
- Repository last pushed: 2026-09-10
- Publisher type: Organization
- Listing: https://agentpluginsdirectory.com/plugins/masthead-agent-tools
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What masthead-agent-tools does, in the publisher's words

A unified, multiplatform agent toolkit for Masthead Data, BigQuery data observability and FinOps cost optimization for Google Cloud.

This repository provides single-source-of-truth plugins and skills for:

- Claude Code
- OpenAI Codex
- Antigravity / Gemini CLI
- Universal Skills CLI
- FinOps (Cost Savings): Optimize BigQuery compute, storage, data models, and pipelines based on historical dataset insights.
- Real-Time Observability: Connect via Model Context Protocol (MCP) to investigate, trace lineage, and resolve live pipeline failures and data anomalies.

All FinOps skills adhere to strict non-action principles:

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/masthead-data/for-agents/HEAD/README.md

## Skills

- masthead-asset-prioritization: Review monitoring tiers for BigQuery tables and BI assets against Masthead asset scores, propose PRIORITY or CRITICAL for assets that matter and REGULAR for prioritized assets that no longer do, explain each suggestion from the score metrics, and apply changes through the Masthead MCP server only o…
- masthead-compute-savings-with-pipelines: Optimize BigQuery compute costs by identifying and pausing/disabling unused, dead-end, or inefficient pipelines that consume compute resources.
- masthead-compute-savings-with-workload-assignments: Optimize BigQuery compute costs by reassigning data models (Dataform, dbt, Airflow) or principals (service accounts, users) to slot reservations or on-demand compute based on Masthead recommendations without impacting performance.
- masthead-incident-triaging: Triage, analyze downstream impact, and mitigate data quality and pipeline incidents using the Masthead MCP server.
- masthead-savings: Run the full Masthead FinOps audit across tables, datasets, pipelines, and data models. Same workflow as the Claude Code `/savings` command, invocable as `$masthead-savings` in Codex.
- masthead-storage-savings-with-datasets: Optimize BigQuery storage costs at the dataset level by switching storage billing models and setting expiration policies.
- masthead-storage-savings-with-tables: Optimize BigQuery storage costs by identifying and removing dead-end and unused tables.
- masthead-triage: Triage active Masthead incidents with lineage and blast-radius analysis. Same workflow as the Claude Code `/triage` command, invocable as `$masthead-triage` in Codex.

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.

## MCP servers

- masthead: transport: streamable-http; url: https://mcp.mastheadata.com/mcp

Read from the plugin's own mcp.json. Environment variable names only, never values.