debug-render

A troubleshooting workflow for an image or video render that looks wrong even though it completed. It checks intermediate results one stage at a time to find where the problem first appears.

In plain words
What is it for?
Use it to investigate artifacts, wrong subjects or poses, color problems, blur, melted details, or conditioning issues in image and video pipelines.
Why use it?
It avoids rerunning an entire multi-stage render without knowing what caused the defect. By narrowing the check to one branch or stage, it helps distinguish bad inputs from a faulty processing step.

Skill for Claude CodeCodex

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 skills/sandyup/comfyui-mcp/debug-render
Any agent
npx skills add sandyup/comfyui-mcp --skill debug-render
Clone the repo
git clone --depth 1 https://github.com/sandyup/comfyui-mcp

Made for: Claude Code, Codex.

Per session 122 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,646 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 89% 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.

ModelPer sessionOnce invoked
Fable 5 $0.00122 $0.01646
Opus 5 $0.00061 $0.00823
Sonnet 5 $0.00024 $0.00329
Haiku 4.5 $0.00012 $0.00165

Measured yesterday against content hash 3a70b2e78078, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debug-render 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

89% identical to debug-render — 95 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/skills/debug-render/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debugging renders with run-to-node

When a final asset looks wrong (not when it errors), don't re-roll the whole graph and hope. Localize the fault: render only as far as one stage and LOOK at what that stage actually produces. The wrong-looking output is downstream of a first bad step — find that step, fix it there, and everything after it follows.

The tool for this is panel_run with to_node_id ("run to node"), which uses ComfyUI's native partial execution: only the target output node plus everything upstream of it renders; every other branch is skipped. That makes each probe fast and cheap, and the output is delivered to you automatically (same as any run — don't poll).

When to reach for this

  • A final image/video is wrong: artifacts, wrong subject/pose/composition, off color, soft/blurry, melted hands, wrong style.
  • A conditioner isn't "taking": ControlNet, IPAdapter, a mask, an inpaint, a LoRA — and you can't tell if the input to it is wrong or the node is wrong.
  • A multi-stage pipeline (base → refiner, txt2img → upscale, decode → post) degrades: you need to see which stage introduces the problem.
  • You only want to test one branch of a multi-output graph without paying for the others.

If instead the run fails (red error, OOM, missing node, black image from a crash) → use the troubleshooting skill; this skill is for outputs that complete but look wrong.

The one hard rule: to_node_id must be an OUTPUT node

ComfyUI can only run to an output node — SaveImage, PreviewImage, SaveVideo, SaveAudio, etc. (these show is_output: true in panel_get_graph). A bare KSampler / VAEDecode / preprocessor is not an output node, so you can't target it directly. To inspect a point that isn't already an output, add a preview tap there:

You want to see… Wire type Tap to add Wiring
An intermediate image (post-process, refiner stage, composite) IMAGE PreviewImage image → PreviewImage.images
A latent (after a sampler, before/after upscale) LATENT VAEDecodePreviewImage latent → VAEDecode.samples; reuse the graph's VAE → VAEDecode.vae; then → PreviewImage
A mask (inpaint, segmentation, attention) MASK MaskToImagePreviewImage mask → MaskToImage.maskPreviewImage
A ControlNet/preprocessor map (depth/pose/canny) usually IMAGE already PreviewImage the preprocessor's IMAGE output → PreviewImage.images
The actual prompt/conditioning CONDITIONING (can't preview as an image) inspect widget values / the text node feeding it instead

Read the full file on GitHub · 106 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.

  1. yesterday First seen · 106 lines · 122 tokens per session scan A 3a70b2e78078

Subscribe to this mod's changes

debug-render is a skill published in the GitHub repository sandyup/comfyui-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 122 tokens to every session and 1,646 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to debug-render, differing in 95 lines, and is treated as a copy.

Related

Other skills, from other repositories

planning-with-files-ar

تخطيط مستمر قائم على الملفات لعمل وكلاء الذكاء الاصطناعي متعدد الخطوات. يحتفظ بملفات taskplan.md و findings.md و progress.md على القرص، وتحقن خطافات دورة الحياة سياق التخطيط المحدد للمشروع. تقرأ الاستعادة التلقائية ملفات تخطيط المشروع فقط. يمكن للأمر الصريح session-catchup.py --metadata فحص بيانات وصفية لجلسات الوكيل…

OthmanAdi/planning-with-files · 189 tokens

kl-consistency-test

Write, calibrate, and debug the prefill-vs-decode logprob (KL) consistency tests in sglang -- the two independent conditions a zero requires (every operator batch-invariant, and the two paths computing the same function), which helper separates them, how to pick a threshold once they hold, and how to localize a…

sgl-project/sglang · 108 tokens

i18n-localization

Internationalization and localization patterns. Detecting hardcoded strings, managing translations, locale files, RTL support.

vudovn/ag-kit · 27 tokens

dsh-web-documentation

Use when adding or editing dsh-web README files, docs, AGENTS.md instructions, user-facing configuration text, or bilingual documentation pairs.

zhu1090093659/dsh-web · 34 tokens

baoyu-youtube-transcript

Downloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面"…

JimLiu/baoyu-skills · 107 tokens

indication-dossier

Build a source-backed biomedical indication dossier. Use when a research task asks for disease biology, target rationale, patient segmentation, biomarkers, trials, drugs, competitive landscape, or translational evidence.

companion-inc/feynman · 43 tokens