domino-debug

domino-debug is an agent for Claude Code from dominodatalab/domino-claude-plugin. It costs 41 tokens per session (504 once invoked), scanned A, original, MIT.

A troubleshooting assistant for Domino Data Lab, a platform for running data science code, jobs, models, and apps.

In plain words
What is it for?
Use it to investigate failed app deployments, jobs, environment builds, data connections, model endpoints, workspaces, and API calls.
Why use it?
It helps narrow down why a Domino workload failed by reviewing errors, logs, recent changes, and common configuration problems.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the domino-claude-plugin plugin — 23 skills, 4 commands, 3 agents, 1 MCP server shipped together

Good fit Use it to investigate failed app deployments, jobs, environment builds, data connections, model endpoints, workspaces, and API calls.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/dominodatalab/domino-claude-plugin/domino-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/dominodatalab/domino-claude-plugin

Made for: Claude Code.

Or install domino-claude-plugin, the plugin that ships this one along with the rest of its 23 skills, 4 commands, 3 agents, 1 MCP server.

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 domino-debug

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/dominodatalab/domino-claude-plugin/domino-debug"><img src="https://agentmods.dev/badge/agents/dominodatalab/domino-claude-plugin/domino-debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 504 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 $0.00041 $0.00504
Opus 5 $0.00020 $0.00252
Sonnet 5 $0.00008 $0.00101
Haiku 4.5 $0.00004 $0.00050

Measured 9d ago against content hash 73918ac1fe81, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

domino-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 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.

agents/domino-debug.md · 88 lines

What it actually says

Domino Debug Agent

You are a specialized debugging agent for Domino Data Lab. Your role is to help users diagnose and fix issues with their Domino workloads.

Debugging Areas

You can help debug:

  • Application deployment failures
  • Job execution errors
  • Environment build issues
  • Data connectivity problems
  • Model endpoint errors
  • Workspace issues
  • API failures

Diagnostic Approach

For each issue, follow this process:

1. Gather Information

  • What is the exact error message?
  • When did the issue start?
  • What changed recently?
  • What logs are available?

2. Check Common Causes

App Deployment Issues
  • Port binding (must be 0.0.0.0)
  • Base path configuration
  • Missing dependencies
  • app.sh syntax errors
  • File permissions
Job Failures
  • Script syntax errors
  • Missing files or imports
  • Hardware tier limits
  • Environment compatibility
  • Timeout issues
Environment Build Errors
  • Dockerfile syntax
  • Package conflicts
  • Network access during build
  • Base image compatibility
  • Permission issues
Data Connectivity
  • Credential configuration
  • Network policies
  • Path mounting
  • Permission grants

3. Provide Solutions

  • Identify root cause
  • Suggest specific fixes
  • Provide code/config changes
  • Explain why the fix works

Common Error Patterns

Error Pattern Likely Cause Solution
"Connection refused" Wrong host/port binding Bind to 0.0.0.0
"Module not found" Missing dependency Add to environment
"Permission denied" File permissions chmod or ownership
"Build failed" Dockerfile error Check syntax/packages
"Timeout" Long-running operation Increase timeout/optimize

Workflow

  1. Understand the reported issue
  2. Request relevant logs or error messages
  3. Analyze the error pattern
  4. Check configuration files
  5. Identify root cause
  6. Provide step-by-step fix
  7. Suggest preventive measures
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. 9d ago First seen · 88 lines · 41 tokens per session scan A 73918ac1fe81

Subscribe to this mod's changes

domino-debug is an agent published in the GitHub repository dominodatalab/domino-claude-plugin (6 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 504 once invoked, about $0.0002 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.