A command for diagnosing why a ComfyUI image-generation workflow failed. It examines the failed run, error details, logs, and the node where execution stopped.

Use it with a prompt ID or the latest run to identify the failing node, inspect its expected inputs, review the traceback, and suggest a fix.

It gathers the relevant technical evidence in one investigation instead of making you search through execution history and logs manually.

debug — Command by sandyup

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.

agentmods

npx agentmods add commands/sandyup/comfyui-mcp/debug

Clone the repo

git clone --depth 1 https://github.com/sandyup/comfyui-mcp

Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 863 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin 86% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5	$0.00009	$0.00863
Opus 5	$0.00005	$0.00432
Sonnet 5	$0.00002	$0.00173
Haiku 4.5	$0.00001	$0.00086

Measured yesterday against content hash 78cdb28ccb2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

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.

Origin

This is a copy

86% identical to debug — 32 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugin/commands/debug.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/comfy-debug — Diagnose a Failed Workflow

The user wants to find out why a ComfyUI workflow execution failed and get a suggested fix.

Instructions

Get the execution history. The argument is: $ARGUMENTS
- If a prompt_id is provided, call get_history with that prompt_id
- If "last" is provided or no argument given, call get_history with no prompt_id to get the most recent execution
Extract the error. From the history response, identify:
- node_id: the node where execution failed
- node_type / class_type: what kind of node it was
- exception_message: the error message
- traceback: the full Python traceback
If the execution succeeded (no error), tell the user it completed normally and show the output summary.
Get relevant logs. Call get_logs with a keyword filter matching the error — use the exception class name (e.g., "RuntimeError", "ValueError") or a distinctive phrase from the error message. Request up to 200 lines.
Inspect the failing node. Call get_node_info with the node_type of the failing node. Check:
- What inputs does the node expect?
- Are there required inputs that might be missing or mistyped?
- What data types are expected for each input?
Check for missing models. If the error mentions a missing file, model, or checkpoint:
- Call list_local_models to see what's installed
- Compare against what the workflow references
- If a model is missing, suggest using download_model or provide a search query for search_models
Check for missing nodes. If the error is a KeyError or mentions an unknown node type:
- The node pack may not be installed
- Call search_custom_nodes with the node class name to find which pack provides it
- Suggest installing the pack
Present the diagnosis. Provide a clear summary:
- What failed: node type, node ID, and a one-line description
- Why it failed: root cause explanation in plain language
- Suggested fix: concrete steps the user can take to resolve the issue
- Traceback excerpt: the most relevant lines from the traceback (not the full dump)

Read the full file on GitHub · 73 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.

yesterday First seen · 73 lines · 9 tokens per session scan A 78cdb28ccb2c

Subscribe to this mod's changes

debug is a command published in the GitHub repository sandyup/comfyui-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 9 tokens to every session and 863 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to debug, differing in 32 lines, and is treated as a copy.

Code review Data and AI Debugging

debug

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

This is a copy

How it starts

/comfy-debug — Diagnose a Failed Workflow

Instructions

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement