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.
npx skills add hybridindie/comfyui_mcp --skill troubleshootinggit clone --depth 1 https://github.com/hybridindie/comfyui_mcpWrote 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/skills/hybridindie/comfyui_mcp/troubleshooting)<a href="https://agentmods.dev/skills/hybridindie/comfyui_mcp/troubleshooting"><img src="https://agentmods.dev/badge/skills/hybridindie/comfyui_mcp/troubleshooting/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/skills/hybridindie/comfyui_mcp/troubleshooting"><img src="https://agentmods.dev/badge/skills/hybridindie/comfyui_mcp/troubleshooting.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 | $0.00035 | $0.01061 |
| Opus 5 | $0.00017 | $0.00531 |
| Sonnet 5 | $0.00007 | $0.00212 |
| Haiku 4.5 | $0.00003 | $0.00106 |
Grade A, and why
troubleshooting scanned grade A with 1 finding 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.
Unrestricted tool accesslowExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
- The MCP server inspects workflows for nodes known to execute arbitrary code, access the network, or read/write files. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ComfyUI Troubleshooting Guide
Each section below is independent. Find the section whose symptom matches the error you are seeing and work through only those checks.
Connection Failures
Symptoms: Tools return connection errors, timeouts, or "ComfyUI not reachable" messages.
Checks:
- Is ComfyUI running? Check the ComfyUI terminal/logs for errors.
- Is the URL correct? Verify
COMFYUI_URLenvironment variable orcomfyui.urlin~/.comfyui-mcp/config.yaml. Default ishttp://localhost:8188. - Firewall/network: If ComfyUI runs on a remote machine, ensure port 8188 is accessible.
- Use
comfyui_get_system_infoto test basic connectivity.
Model Not Found
Symptoms: comfyui_generate_image or workflows fail with "model not found" errors.
Checks:
- Run
comfyui_list_modelswith the correct folder type (e.g., "checkpoints", "loras") to see what's available. - Model filenames are case-sensitive and must include the extension (e.g.,
v1-5-pruned-emaonly.safetensors). - If the model isn't listed, it needs to be placed in the correct ComfyUI models directory.
- If ComfyUI Model Manager is installed, use
comfyui_search_modelsandcomfyui_download_modelto fetch models directly. - Run
comfyui_list_model_foldersto see all valid folder types.
Workflow Execution Failures
Symptoms: comfyui_run_workflow or comfyui_generate_image fails after submission.
Checks:
- Run
comfyui_validate_workflowfirst to catch structural issues. - Check for missing custom nodes —
comfyui_list_nodesshows what's installed. If a workflow uses nodes that aren't installed, it will fail. - Check connections — a node output index must match what the node actually produces. Use
comfyui_get_node_infoto verify. - Check
comfyui_get_queueto see if the job is stuck or if there's a queue backlog. - Check
comfyui_get_progresswith the prompt_id to see which node failed.
Queue Stuck / Job Not Completing
Symptoms: Jobs stay in "running" state indefinitely, or the queue doesn't process.
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.
- 10d ago First seen · 86 lines · 35 tokens per session scan A 772d188f18f9
troubleshooting is a skill published in the GitHub repository hybridindie/comfyui_mcp (2 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 1,061 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
mlflow-traces
Use when working with MLflow traces: debugging via MCP tools, analyzing performance, logging feedback, writing custom scorers/evaluations, or cleaning up trace data.
hmem-new-error
Create a new E-entry (bug/error) in hmem with the strict 5-level scaffold. Use when the user wants to log a bug, file a report, or document an error ('Bug loggen', 'log this error', 'Fehler eintragen'), or before any writememory with prefix='E'.
Safe Android Reverser
Safely fingerprint, route, decompile, inspect Flutter AOT, query program evidence, and reconstruct Android network/auth/crypto behavior through one capability-aware MCP control plane.
local-gpu-imagegen
Use when a user asks to create, generate, draw, render, transform, restyle, or revise a visual asset on the local GPU.
spotify-mcp-doctor
Diagnose and repair NovaLux12/spotify-mcp-server failures — auth, permissions, devices, rate limits, OpenClaw wiring. Use when Spotify tool calls fail or setup stalls.
feedback-nudge
Use when the user wants to report a bug, request a feature, or send feedback to the Zooza engineering team. Also offer proactively after a successful commit operation (max once per week).