A readiness checker and router for Qwen Image, an image-generation model, running on a remote GPU machine. It directs requests to image generation, editing, or inpainting workflows.

Use it when a ComfyUI-based Qwen image workflow is needed, especially for generating, editing, or filling parts of images.

It helps determine whether the required GPU service is available and selects the appropriate Qwen workflow.

qwen-image — Skill for Claude Code and Codex by Elumenotion/GuideAnts

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.

Any agent

npx skills add Elumenotion/GuideAnts --skill qwen-image

Clone the repo

git clone --depth 1 https://github.com/Elumenotion/GuideAnts

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/elumenotion/guideants/qwen-image/github.svg)](https://agentmods.dev/skills/elumenotion/guideants/qwen-image)

Your own site

<a href="https://agentmods.dev/skills/elumenotion/guideants/qwen-image"><img src="https://agentmods.dev/badge/skills/elumenotion/guideants/qwen-image/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/elumenotion/guideants/qwen-image"><img src="https://agentmods.dev/badge/skills/elumenotion/guideants/qwen-image.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 842 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found 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 5.1	$0.00050	$0.00842
Opus 5.5	$0.00020	$0.00337
Sonnet 5.5	$0.00010	$0.00168
Haiku 4.5	$0.00005	$0.00084

Measured 1mo ago against content hash 8b074b3a3da6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

qwen-image scanned grade C 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 1mo ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/preflight.py, scripts/probe.py, scripts/skill_gateway_client.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Harvests environment variableshighData exfiltration

Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.

printenv QWEN_IMAGE_SKILL_BASE_URL >/dev/null && printenv QWEN_IMAGE_SKILL_TOKEN >/dev/null && echo "env ok" || echo "env missing"

samples/skills/qwen-image skills/qwen-image/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Qwen Image (umbrella)

Paths — fixed layout, do not probe or re-derive. The sandbox CWD is the notebook's output directory. This skill's scripts live under Skills/qwen-image/scripts/ relative to it, so run the commands in this file exactly as written. Write every deliverable to the CWD with a bare filename (e.g. -o gen.png): never prefix an output path with Output/ — the CWD is the output directory, so Output/… would create a nested Output/ folder.

Product notebook SD tools cover plain txt2img/img2img without Qwen/Comfy. Use this family when the user needs Qwen Image 2512 BF16 generate, edit, or inpaint via the ComfyUI-video adapter on the GPU host.

PC sandbox → GPU host gateway. Skills run on the workstation; the comfyui-video container runs on the GPU host (guideants-video-stack); the gateway endpoint and token come from the guide Environment (QWEN_IMAGE_SKILL_BASE_URL, QWEN_IMAGE_SKILL_TOKEN). Do not use 127.0.0.1 — that is the PC, not the GPU host.

When to use product SD tools instead

If the request is a simple notebook image with no Qwen-specific need, use GuideAnts' built-in SD image tools — not these skills.

GPU host gateway (env-configured)

The scripts read QWEN_IMAGE_SKILL_BASE_URL and QWEN_IMAGE_SKILL_TOKEN from the guide Environment automatically — do not hardcode or export them inline.

Verify before running:

printenv QWEN_IMAGE_SKILL_BASE_URL >/dev/null && printenv QWEN_IMAGE_SKILL_TOKEN >/dev/null && echo "env ok" || echo "env missing"

If either is missing, stop and ask the user to set it in the guide's Environment variables. Never scan the LAN or guess the GPU host's IP.

GPU host stack: GA_COMFYUI_VIDEO_PORT=8189, GA_QWEN_IMAGE_SKILL_TOKEN in guideants-video-stack/.env. Header: X-Qwen-Image-Skill-Token.

Probe first

python3 Skills/qwen-image/scripts/probe.py
python3 Skills/qwen-image/scripts/preflight.py --for probe

Route to a task skill

User wants…	Skill
New image from text	`qwen-image-generate`
Restyle / edit existing image	`qwen-image-edit`
Masked fill / whiteboard completion	`qwen-image-inpaint`
Unclear / “is the GPU host ready?”	stay here; run probe

Read the full file on GitHub · 80 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

1mo ago First seen · 80 lines · 50 tokens per session scan C 8b074b3a3da6

Subscribe to this mod's changes

qwen-image is a skill published in the GitHub repository Elumenotion/GuideAnts (61 stars, last pushed 2d ago), licensed Apache-2.0. It adds 50 tokens to every session and 842 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Creative and media ai ai-agents ai-tools anthropic docker hugging-face

example-feature-generator

Generate boilerplate for new features following project conventions. Use when user says "create feature", "add feature", or "new feature scaffolding".

qf-studio/navigator · 33 tokens

thinking-theory-of-constraints

When throughput or latency is pipeline-limited, identify the single binding constraint and exploit, subordinate, elevate, then recheck—ignore non-constraints.

tjboudreaux/cc-thinking-skills · 37 tokens

agent-flutter-developer

Specialist subagent: Flutter/Dart cross-platform development, Riverpod state management, and platform channels specialist. Use when building Flutter apps, implementing state management, or working with native platform features. Trigger phrases: Flutter, Dart, Riverpod, Bloc, widget, MaterialApp, GoRouter, platform…

travisjneuman/.claude · 74 tokens

qwen-image