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 peteromallet/VibeComfy --skill debug-comfy-workflowgit clone --depth 1 https://github.com/peteromallet/VibeComfyWrote 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/peteromallet/vibecomfy/debug-comfy-workflow)<a href="https://agentmods.dev/skills/peteromallet/vibecomfy/debug-comfy-workflow"><img src="https://agentmods.dev/badge/skills/peteromallet/vibecomfy/debug-comfy-workflow/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/peteromallet/vibecomfy/debug-comfy-workflow"><img src="https://agentmods.dev/badge/skills/peteromallet/vibecomfy/debug-comfy-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00070 | $0.00540 |
| Opus 5.5 | $0.00028 | $0.00216 |
| Sonnet 5.5 | $0.00014 | $0.00108 |
| Haiku 4.5 | $0.00007 | $0.00054 |
Grade A, and why
debug-comfy-workflow 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 1mo 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug Comfy Workflow
Debug from cheap static evidence toward expensive runtime evidence. Decide first whether the failure is the graph, dependencies, or the runtime.
First Pass
vibecomfy inspect <workflow>
vibecomfy validate <workflow>
vibecomfy doctor <workflow> --json
vibecomfy analyze info <workflow>
For source JSON or conversion failures, keep the source as import evidence and do not execute its API export directly:
vibecomfy import <workflow.json>
vibecomfy validate workflows/<source-stem> --json
vibecomfy port doctor-all <workflow.json> --json
vibecomfy port widgets <workflow.json> --json
For runtime failures:
vibecomfy runtime doctor
vibecomfy logs tail
vibecomfy watchdog list
Missing Nodes Or Models
vibecomfy nodes install-plan <workflow>
vibecomfy nodes spec <ClassType>
vibecomfy fetch <workflow> --dry-run
vibecomfy models stage --select-phase core --dry-run
Install or download only after the evidence supports it and the user agrees.
For custom Python failures, separate these cases:
- malformed
io, unknown bindings, or an invalid result shape: fix the node declaration or explicit adapter; - missing declared distribution: prepare the selected worker with setup tools;
- missing snapshot member, archive/member digest mismatch, unsafe path, or absolute snapshot self-import: recapture with relative imports or use the installed-entrypoint mode;
- source traceback: inspect the reported source entrypoint and runtime line;
- changed bundle/source revision: reload and retry the canonical transaction.
Discipline
- Keep graph errors separate from environment errors.
- If embedded ComfyUI is not discoverable, use
vibecomfy-setup; that is not a workflow bug. - Do not recommend arbitrary node packs. Require
nodes install-plan, lockfile data, registry evidence, or a concrete precedent. - If class/schema evidence is missing, use
search-comfy-workflowsbefore patching. - Preserve report paths and cite the exact command output or file that supports the diagnosis.
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.
- 1mo ago Changed · +12 lines 2b0b8b9add0e
- 1mo ago Changed c0e28fa60a44
- 1mo ago First seen · 53 lines · 70 tokens per session scan A 0ac5bd4026bb
debug-comfy-workflow is a skill published in the GitHub repository peteromallet/VibeComfy (152 stars, last pushed today), licensed MIT. It adds 70 tokens to every session and 540 once invoked, about $0.0003 per session on Opus 5.5. 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.