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 zztdandan/image-generate-mcp-remote --skill img-gengit clone --depth 1 https://github.com/zztdandan/image-generate-mcp-remoteWrote 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/zztdandan/image-generate-mcp-remote/img-gen)<a href="https://agentmods.dev/skills/zztdandan/image-generate-mcp-remote/img-gen"><img src="https://agentmods.dev/badge/skills/zztdandan/image-generate-mcp-remote/img-gen/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/zztdandan/image-generate-mcp-remote/img-gen"><img src="https://agentmods.dev/badge/skills/zztdandan/image-generate-mcp-remote/img-gen.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 | $0.00034 | $0.01171 |
| Opus 5 | $0.00017 | $0.00585 |
| Sonnet 5 | $0.00007 | $0.00234 |
| Haiku 4.5 | $0.00003 | $0.00117 |
Grade A, and why
img-gen 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 6d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
img-gen — 直接图像生成
通过 OS 环境变量读取 API key，直接发起 HTTP 请求生成/编辑图片。 不依赖 MCP 中间层，不依赖任何 .env 文件。
适用范围
- 用户要求生成图片（GPT Image 2 / Nano Banana 2）
- 用户要求编辑已有图片
- gpt-icon-generate 等依赖生图能力的技能的下层实现
技能文件
所有脚本为技能自包含：
scripts/
├── img_gen.py ← 统一 CLI（check / generate / edit）
├── check_env.py ← .env 配置检测
├── lib/
│ ├── presets.py ← 13 个 preset 配置 + 尺寸映射 + .env 加载
│ ├── openai_images.py ← OpenAI Images 协议
│ └── gemini_gen.py ← Gemini generateContent 协议
└── presets/
├── gpt/ (10 个) ← 每个 preset 一个 Python 封装
└── banana/ (3 个)
快速开始
Step 1 — 检测环境
python3 scripts/check_env.py
从 OS 环境变量读取配置，确认 API key 存在，报告各渠道可用状态。 不打印 token 值。如果失败，检查环境变量是否设置。
Step 2 — 生成图片
# 使用 GPT preset
python3 scripts/img_gen.py generate \
--preset laozhang_gpt_image_2_default \
--prompt "A futuristic steel plant" \
--save output.png --size 2K --ratio 16:9
# 使用 Banana preset
python3 scripts/img_gen.py generate \
--preset laozhang_nano_banana_pro \
--prompt "传统中式园林" \
--save garden.png --size 4K --ratio 16:9
Step 3 — 编辑图片
python3 scripts/img_gen.py edit \
--preset laozhang_gpt_image_2_default \
--image input.png --prompt "Add blue sky" \
--save edited.png
Preset 专属脚本
每个 preset 有独立 Python 封装：
python3 scripts/presets/gpt/laozhang_gpt_image_2_default.py generate --prompt "..." --save out.png
python3 scripts/presets/banana/laozhang_nano_banana_pro.py generate --prompt "..." --save out.png
环境配置
通过 OS 环境变量配置（无需 .env 文件）：
IMG_GEN_GPT_IMAGE_2_OFFICIAL_API_KEY=<token>
IMG_GEN_GPT_IMAGE_2_OFFICIAL_PRESET=laozhang_gpt_image_2_default
IMG_GEN_NANO_BANANA_2_OFFICIAL_API_KEY=<token>
IMG_GEN_NANO_BANANA_2_OFFICIAL_PRESET=laozhang_nano_banana_pro
IMAGE_OUTPUT_DIR=/home/base/images
安全说明：技能检测仅确认环境变量非空，不打印 token 值。
支持的 Preset
13 个 preset，详见 references/presets.md：
| 协议 | 数量 | Provider |
|---|---|---|
| OpenAI Images | 10 | laozhang, openai, apiyi, right_codes, copperai |
| Gemini | 3 | laozhang, apiyi, google |
What ships with it
23 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.
- .skillhub/metadata.json 178 B
- references/presets.md 2.8 KB
- references/protocols.md 2.5 KB
- references/size-mapping.md 1.8 KB
- scripts/check_env.py 2.5 KB runs code
- scripts/img_gen.py 5.8 KB runs code
- scripts/lib/__init__.py 117 B runs code
- scripts/lib/gemini_gen.py 4.2 KB runs code
- scripts/lib/openai_images.py 4.4 KB runs code
- scripts/lib/presets.py 8.5 KB runs code
- scripts/presets/banana/apiyi_nano_banana_2.py 530 B runs code
- scripts/presets/banana/google_nano_banana.py 526 B runs code
- scripts/presets/banana/laozhang_nano_banana_pro.py 550 B runs code
- scripts/presets/gpt/apiyi_gpt_image_2.py 519 B runs code
- scripts/presets/gpt/copperai_gpt_image_2.py 531 B runs code
- scripts/presets/gpt/laozhang_gpt_image_2_default.py 563 B runs code
- scripts/presets/gpt/laozhang_gpt_image_2_enterprise.py 575 B runs code
- scripts/presets/gpt/laozhang_gpt_image_2_sora_official.py 587 B runs code
- scripts/presets/gpt/laozhang_gpt_image_2_vip.py 547 B runs code
- scripts/presets/gpt/openai_gpt_image_2.py 523 B runs code
- scripts/presets/gpt/right_codes_gpt_image_2_vip.py 559 B runs code
- scripts/presets/gpt/right_codes_gpt_image_2.py 543 B runs code
- scripts/presets/gpt/right_codes_nano_with_image_api_images.py 603 B runs code
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.
- 6d ago First seen · 137 lines · 34 tokens per session scan A 9d1bbab62031
img-gen is a skill published in the GitHub repository zztdandan/image-generate-mcp-remote (0 stars, last pushed 6d ago), licensed MIT. It adds 34 tokens to every session and 1,171 once invoked, about $0.0002 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 2026-09-05.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.