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.
git clone --depth 1 https://github.com/JosiahSiegel/claude-plugin-marketplaceWrote 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/plugins/josiahsiegel/claude-plugin-marketplace/adf-master)<a href="https://agentmods.dev/plugins/josiahsiegel/claude-plugin-marketplace/adf-master"><img src="https://agentmods.dev/badge/plugins/josiahsiegel/claude-plugin-marketplace/adf-master/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.
<a href="https://agentmods.dev/plugins/josiahsiegel/claude-plugin-marketplace/adf-master"><img src="https://agentmods.dev/badge/plugins/josiahsiegel/claude-plugin-marketplace/adf-master.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
adf-master 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 9d 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.
What it actually says
{
"name": "adf-master",
"version": "4.3.4",
"description": "Complete Azure Data Factory expertise for pipeline JSON development, validation, and optimization (2025-2026). This plugin should be used for ADF pipeline creation, activity configuration, linked services, datasets, triggers, expressions, CI/CD, Microsoft Fabric integration, Databricks orchestration, ML pipeline patterns, and debugging.",
"author": {
"name": "Josiah Siegel",
"email": "[email protected]"
},
"homepage": "https://github.com/JosiahSiegel/claude-plugin-marketplace/tree/main/plugins/adf-master",
"repository": "https://github.com/JosiahSiegel/claude-plugin-marketplace",
"keywords": [
"adf",
"azure-data-factory",
"datafactory",
"azure",
"pipeline-json",
"activity-types",
"copy-activity",
"foreach-activity",
"lookup-activity",
"execute-pipeline",
"web-activity",
"databricks-job",
"linked-services",
"managed-identity",
"service-principal",
"expression-functions",
"triggers",
"tumbling-window",
"schedule-trigger",
"event-trigger",
"datasets",
"parquet",
"delimited-text",
"validation",
"nesting-rules",
"resource-limits",
"cicd",
"arm-templates",
"github-actions",
"azure-devops",
"fabric",
"fabric-lakehouse",
"fabric-warehouse",
"onelake",
"invoke-pipeline",
"variable-libraries",
"synapse",
"adls-gen2",
"blob-storage",
"sql-database",
"snowflake",
"rest-api",
"sftp",
"machine-learning",
"azure-ml",
"batch-endpoints",
"azure-ai-services",
"mlflow",
"feature-engineering",
"data-archival",
"anomaly-detection",
"sentiment-analysis",
"ml-scoring",
"training-pipeline",
"2025",
"2026"
],
"license": "MIT"
}
What it installs
The manifest is a name and a version. 6 skills, 5 commands, 1 agent travel with it, and installing the plugin installs all of them — 1,203 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill adf-validation-rules A 149 tokens
- Skill windows-git-bash-compatibility A 146 tokens
- Skill fabric-onelake-2025 A 148 tokens
- Skill adf-ml-analytics A 150 tokens
- Skill databricks-2025 A 167 tokens
- Skill adf-master A 178 tokens
- Command adf-expression A 18 tokens
- Command adf-create-pipeline A 20 tokens
- Command adf-debug A 17 tokens
- Command adf-linked-service A 17 tokens
- Command adf-validate A 21 tokens
- Agent adf-expert A 172 tokens
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.
- 9d ago First seen · 71 lines scan A 18f97fa533ee
adf-master is a plugin published in the GitHub repository JosiahSiegel/claude-plugin-marketplace (54 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
devops-tools
DevOps automation: ClickHouse, Doppler, MLflow, Cloudflare Workers, pueue orchestration, notifications, session recovery, MiniMax consensus analysis.
local-ai
From nothing to a working AI setup you own. Scans the machine for models that fit, installs and wires up the right app with consent at every download, shares it over a private URL, and rents a cloud GPU when a model is too big. Needs shell access.
ml-training
Machine-learning training and benchmarking on rented cloud GPUs: prebaked RunPod images that boot in seconds instead of minutes, pod lifecycle scripts, GPU selection and pricing ladders, and the provisioning pitfall catalog.
azure-agent-skills
193+ production-ready Azure skills covering compute, data, AI/ML, networking, security, and management. Built from Microsoft Learn and following the Agent Skills open standard.
orchestra
Skills for working with Orchestra data pipelines — diagnose and fix failed runs, triage with a merge gate, author pipeline YAML, set up dbt Slim CI, configure dbt state-aware orchestration (source freshness and buildafter), run Snowflake data-quality tests, review a workspace against best practices, and merge duplicat.
databricks
Databricks skills for the CLI, Apps, Lakebase, Model Serving, Lakeflow Jobs, Spark Declarative Pipelines, Declarative Automation Bundles (DABs), and classic-to-serverless migration.