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 MCKRUZ/ComfyUI-Expert --skill comfyui-troubleshootergit clone --depth 1 https://github.com/MCKRUZ/ComfyUI-ExpertWrote 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/mckruz/comfyui-expert/comfyui-troubleshooter)<a href="https://agentmods.dev/skills/mckruz/comfyui-expert/comfyui-troubleshooter"><img src="https://agentmods.dev/badge/skills/mckruz/comfyui-expert/comfyui-troubleshooter/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/mckruz/comfyui-expert/comfyui-troubleshooter"><img src="https://agentmods.dev/badge/skills/mckruz/comfyui-expert/comfyui-troubleshooter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
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 | $0.00051 | $0.01384 |
| Opus 5 | $0.00026 | $0.00692 |
| Sonnet 5 | $0.00010 | $0.00277 |
| Haiku 4.5 | $0.00005 | $0.00138 |
Grade A, and why
comfyui-troubleshooter 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ComfyUI Troubleshooter
Diagnoses and resolves ComfyUI issues across four categories: server errors, workflow errors, quality issues, and performance problems.
Diagnosis Process
Step 1: Classify the Error
| Category | Symptoms | First Check |
|---|---|---|
| Server | Connection refused, timeouts, crashes | Is ComfyUI running? Check /system_stats |
| Workflow | Node errors, missing inputs, type mismatches | Validate workflow against inventory |
| Quality | Artifacts, wrong identity, blurry output | Check settings (CFG, weights, resolution) |
| Performance | OOM, slow generation, VRAM errors | Check VRAM usage, model sizes |
Step 2: Gather Context
Collect before diagnosing:
- Error message (exact text)
- Workflow being executed (or description)
- Models involved (checkpoint, LoRA, ControlNet, etc.)
- Settings (CFG, steps, resolution, sampler)
- Hardware (from
foundation/hardware-profile.md) - Inventory (from
state/inventory.json)
Step 3: Match Error Pattern
See references/troubleshooting.md for the full error database.
Quick Fix Reference
Top 10 Most Common Errors
1. "CUDA out of memory"
→ Use FP8: --fp8_e4m3fn-unet
→ Enable tiled VAE
→ Reduce resolution
→ Restart ComfyUI (clears fragmentation)
2. "Node type not found: {name}"
→ Install the custom node package via ComfyUI-Manager
→ Check comfyui-inventory node-to-package mapping
3. "Expected scalar type BFloat16 but found Float"
→ Precision mismatch. Add --force-fp16 or use matching precision nodes
4. Burned/overexposed faces → Lower CFG to 4-5 (InstantID) → Reduce identity method weight → Add noise to negative embeds (35%)
5. "No model found at path" → Check filename spelling (exact match required) → Verify file is in correct subdirectory → Run inventory scan to confirm
6. Watermark artifacts at 1024x1024 → Use 1016x1016 or 1020x1020 instead
7. Identity doesn't match reference → Use higher quality reference image (clear, front-facing) → Increase IP-Adapter weight to 0.8+ → Verify InsightFace antelopev2 is installed
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 · 157 lines · 51 tokens per session scan A 80e91f25b7bf
comfyui-troubleshooter is a skill published in the GitHub repository MCKRUZ/ComfyUI-Expert (91 stars, last pushed 5mo ago), licensed MIT. It adds 51 tokens to every session and 1,384 once invoked, about $0.0003 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 skills, from other repositories
troubleshooting
Common ComfyUI errors and fixes. OOM, missing nodes, dtype mismatches, black images, and debugging strategies.
debug-render
Debug a WRONG or imperfect render (not a hard error) by inspecting inputs and intermediate steps with run-to-node. Render one branch up to an output, preview-tap latents/masks/preprocessor maps, localize the first bad stage, then fix. Use when a final image/video completes but looks wrong, such as artifacts, wrong…
report-bug
ARCHIVED. comfyui-mcp is no longer maintained and its issue trackers are closed - do NOT file, and do not use reportissue to try. When the user hits a defect in comfyui-mcp or the sidebar panel, say plainly that this project is archived and point them at ComfyUI's official agent and MCP tooling (Comfy Agent / Comfy…
ai-media-generator
A workflow for turning ideas into prompts for AI-generated images, videos, and music across several media platforms. When needed, it can also send those prompts to the chosen platform through browser automation.
comfy-deploy-failures
Reference skill cited by comfy-deploy. Read it with comfy skills show comfy-deploy-failures when a deploy command was refused, a deployment will not reach ready, a job failed, or a deployment is stuck in stopfailed. Maps every deploy error code to what it means and the move that clears it, and covers reading a…
comfy-debug
Debugging skill for the comfy CLI — failed workflows, stuck jobs, error envelopes, and the fastest path from "it broke" to "fixed".