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 Elumenotion/GuideAnts --skill qwen-image-generategit clone --depth 1 https://github.com/Elumenotion/GuideAntsWrote 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/elumenotion/guideants/qwen-image-generate)<a href="https://agentmods.dev/skills/elumenotion/guideants/qwen-image-generate"><img src="https://agentmods.dev/badge/skills/elumenotion/guideants/qwen-image-generate/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/elumenotion/guideants/qwen-image-generate"><img src="https://agentmods.dev/badge/skills/elumenotion/guideants/qwen-image-generate.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 | $0.00052 | $0.01188 |
| Opus 5.5 | $0.00021 | $0.00475 |
| Sonnet 5.5 | $0.00010 | $0.00238 |
| Haiku 4.5 | $0.00005 | $0.00119 |
Grade C, and why
qwen-image-generate 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.
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" How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Qwen Image generate (BF16)
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-generate/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/.
Text → PNG on the GPU host. Draft uses qwen-image-v1 (image_generate_ready); high uses
qwen-image-generate-20-v1 (image_generate_20_ready).
When to use product SD tools instead
Plain notebook txt2img without Qwen/Comfy → use built-in SD tools.
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.
Canvas and quality (named choices only)
Do not pass pixel dimensions or sampler numbers (--width, --height, --steps,
--cfg, --lora-strength). The CLI maps tested profiles internally.
| Flag | Choices | When to use |
|---|---|---|
--canvas |
square (default), landscape, portrait |
Match user aspect intent |
--quality |
draft (default), high |
draft = Lightning 4-step (qwen-image-v1); high = 20-step non-LoRA (qwen-image-generate-20-v1, cfg 2.5) |
Use --quality high only when the user explicitly asks for higher quality or a
non-Lightning render. Default to draft.
Run the CLI directly — do not wrap it in subprocess or os.chdir.
Preflight
Draft (default):
python3 Skills/qwen-image-generate/scripts/preflight.py --for generate
High quality (when user asked for non-Lightning / quality job):
What ships with it
3 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.
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 · 137 lines · 52 tokens per session scan C 614d54cd6e7a
qwen-image-generate is a skill published in the GitHub repository Elumenotion/GuideAnts (61 stars, last pushed 2d ago), licensed Apache-2.0. It adds 52 tokens to every session and 1,188 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.
Other skills, from other repositories
example-feature-generator
Generate boilerplate for new features following project conventions. Use when user says "create feature", "add feature", or "new feature scaffolding".
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.
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…
content-repurposer
Adapt content across platforms with tone/format shifting — blog to social, long to short, text to visual outline. Use when repurposing content for different channels, audiences, or formats.
electron-desktop
Desktop application development with Electron for Windows, macOS, and Linux. Use when building cross-platform desktop apps, implementing native OS features, or packaging web apps for desktop.
investment-memo-generator
Investment memo creation combining financial analysis, document generation, and structured templates. Use when creating investment memos, pitch decks, deal summaries, or investment committee materials.