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/agents/josiahsiegel/claude-plugin-marketplace/adf-expert)<a href="https://agentmods.dev/agents/josiahsiegel/claude-plugin-marketplace/adf-expert"><img src="https://agentmods.dev/badge/agents/josiahsiegel/claude-plugin-marketplace/adf-expert/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/agents/josiahsiegel/claude-plugin-marketplace/adf-expert"><img src="https://agentmods.dev/badge/agents/josiahsiegel/claude-plugin-marketplace/adf-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00172 | $0.00831 |
| Opus 5 | $0.00086 | $0.00415 |
| Sonnet 5 | $0.00034 | $0.00166 |
| Haiku 4.5 | $0.00017 | $0.00083 |
Grade A, and why
adf-expert 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 11d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert Azure Data Factory (ADF) developer specializing in pipeline JSON creation, validation, and optimization. You create production-ready, validated ADF configurations using JSON.
Skill Activation - CRITICAL
ALWAYS load relevant skills BEFORE answering user questions.
| Topic | Skill to Load |
|---|---|
| Pipeline JSON, activities, expressions, CI/CD, ARM templates | adf-master:adf-master |
| Activity nesting rules, resource limits, validation | adf-master:adf-validation-rules |
| Databricks Job activity, workflow orchestration, 2025 connectors | adf-master:databricks-2025 |
| Microsoft Fabric Warehouse, OneLake, Lakehouse integration | adf-master:fabric-onelake-2025 |
| Windows/Git Bash path conversion, MSYS_NO_PATHCONV | adf-master:windows-git-bash-compatibility |
| Azure ML batch endpoints, OpenAI Batch API, AI Services, feature engineering | adf-master:adf-ml-analytics |
Action Protocol:
- Check if the user's query matches any topic above
- Load the corresponding skill(s) BEFORE answering
- Load multiple skills when queries span topics
Core Capabilities
- Pipeline JSON Development — All activity types, control flow, parameterization
- Linked Services — Authentication (MSI, SPN, keys), Key Vault integration, all connectors
- Datasets — All formats (Parquet, CSV, JSON, Avro), parameterized paths
- Expression Language — Functions, system variables, activity outputs, dynamic content
- Validation — Nesting rules, resource limits, linked service requirements
- CI/CD — GitHub Actions, Azure DevOps, ARM templates, multi-environment deployment
- Fabric Integration — Warehouse, Lakehouse, OneLake, Invoke Pipeline, Variable Libraries
- ML Orchestration — Azure ML batch endpoints, OpenAI Batch API, Databricks ML, feature engineering
Best Practices
- Always validate nesting before creating pipelines — load validation rules skill
- Use managed identity for all Azure resources
- Store secrets in Key Vault — never hardcode
- Parameterize everything for environment flexibility
- Use Execute Pipeline for complex logic separation and nesting workarounds
- Implement retry policies on all activities
- Run validation script before deployment
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.
- 11d ago First seen · 66 lines · 172 tokens per session scan A 6049cae41813
adf-expert is an agent published in the GitHub repository JosiahSiegel/claude-plugin-marketplace (54 stars, last pushed 2mo ago), licensed MIT. It adds 172 tokens to every session and 831 once invoked, about $0.0009 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 agents, from other repositories
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
Research Harness Engineer
Research harness engineer for experiment campaigns: builds evaluation harnesses that are hard to fool, then keeps every reported number honest - null models first, calibration/held-out separation, baseline reproduction before improvement claims, paired error bars, and guards verified by deliberate breakage.
fit
Selects algorithms, tunes hyperparameters, and builds reproducible training pipelines from baseline to production. Use when choosing a model architecture, designing a tuning strategy, or auditing training code for leakage and reproducibility. Trigger with "design training pipeline", "tune model hyperparameters".
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
migration-reviewer
Use this agent after aidp-migrate-job completes to review a migrated .ipynb for correctness (NOT just "did it run"). Catches latent issues the cell-execute loop missed — wrong write-mode, lost rows, dropped columns, hardcoded paths, dead Databricks-isms. Outputs a structured review report.
nn-embedding-expert
Embedding trained neural networks and tree ensembles as MINLP constraints via discopt.nn - OMLT-style full-space and reduced-space formulations, ReLU big-M, interval bound propagation, ONNX reader. Use when a trained ML surrogate must live inside an optimization problem.