adf-debug

adf-debug is a command for Claude Code from JosiahSiegel/claude-plugin-marketplace. It costs 17 tokens per session (1,093 once invoked), scanned A, original, MIT.

A guide for investigating failures in Azure Data Factory, Microsoft’s cloud service for moving and transforming data. It reads an error, pipeline name, or failure description and suggests specific fixes.

In plain words
What is it for?
Use it to diagnose failed data-copy and transformation pipelines, identify likely causes, and get remediation steps for common Azure Data Factory errors.
Why use it?
It helps turn unclear pipeline errors into a focused list of checks, such as connections, permissions, files, queries, and destination schemas.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the adf-master plugin — 6 skills, 5 commands, 1 agent shipped together

Good fit Use it to diagnose failed data-copy and transformation pipelines, identify likely causes, and get remediation steps for common Azure Data Factory errors.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/josiahsiegel/claude-plugin-marketplace/adf-debug
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.

Clone the repo
git clone --depth 1 https://github.com/JosiahSiegel/claude-plugin-marketplace

Made for: Claude Code.

Or install adf-master, the plugin that ships this one along with the rest of its 6 skills, 5 commands, 1 agent.

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 adf-debug

README.md
[![agentmods](https://agentmods.dev/badge/commands/josiahsiegel/claude-plugin-marketplace/adf-debug/github.svg)](https://agentmods.dev/commands/josiahsiegel/claude-plugin-marketplace/adf-debug)
Your own site
<a href="https://agentmods.dev/commands/josiahsiegel/claude-plugin-marketplace/adf-debug"><img src="https://agentmods.dev/badge/commands/josiahsiegel/claude-plugin-marketplace/adf-debug/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 adf-debug

Your own site · 80×15
<a href="https://agentmods.dev/commands/josiahsiegel/claude-plugin-marketplace/adf-debug"><img src="https://agentmods.dev/badge/commands/josiahsiegel/claude-plugin-marketplace/adf-debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,093 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original 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 $0.00017 $0.01093
Opus 5 $0.00009 $0.00547
Sonnet 5 $0.00003 $0.00219
Haiku 4.5 $0.00002 $0.00109

Measured 10d ago against content hash 842b5c83148e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

adf-debug 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 10d 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.

plugins/adf-master/commands/adf-debug.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADF Pipeline Debugger

Analyze Azure Data Factory pipeline errors and provide targeted solutions.

Task

Debug the provided ADF error or pipeline issue and provide specific remediation steps.

Arguments

  • $ARGUMENTS: Either:
    • An error message or error code from ADF
    • A pipeline name to analyze for potential issues
    • A description of the failure behavior

Common Error Patterns and Solutions

Activity Errors

ErrorCode: UserErrorActivityRunFailed

  • Check activity-specific error in error.message
  • Common causes: connection timeout, invalid query, permission denied
  • Solution: Validate linked service connectivity, check firewall rules

ErrorCode: UserErrorFailedToReadSourceData

  • Source data unavailable or inaccessible
  • Check: file exists, permissions granted, network accessible
  • For Blob: verify container/path, SAS token not expired

ErrorCode: UserErrorFailedToWriteSinkData

  • Cannot write to destination
  • Check: sink permissions, disk space, schema compatibility
  • For SQL: verify table exists, columns match, constraints satisfied

Copy Activity Errors

ErrorCode: SqlServerCannotConnect

Solutions:
1. Verify server name and database name
2. Check firewall allows Azure services or specific IPs
3. Verify credentials (SQL auth) or role assignments (MI/SP)
4. For serverless: implement retry for auto-pause wake-up

ErrorCode: CosmosDbPartitionKeyRangeTooLarge

Solutions:
1. Increase Data Integration Units (DIUs)
2. Add WHERE clause to limit data per copy
3. Partition the copy by date or other key

Data Flow Errors

ErrorCode: DF-EXECUTOR-InvalidDataType

Solutions:
1. Check source column types vs expected types
2. Add explicit cast/convert in transformation
3. Verify date format matches expected pattern

ErrorCode: DF-EXECUTOR-OutOfMemory

Solutions:
1. Increase cluster size (Core Count)
2. Add partitioning before memory-intensive operations
3. Use broadcast join for small dimension tables
4. Optimize transformations to reduce intermediate data

Read the full file on GitHub · 179 lines

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. 10d ago First seen · 179 lines · 17 tokens per session scan A 842b5c83148e

Subscribe to this mod's changes

adf-debug is a command published in the GitHub repository JosiahSiegel/claude-plugin-marketplace (54 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 1,093 once invoked, about $0.0001 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.