Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/zztdandan/image-generate-mcp-remote/gpt-icon-generate)<a href="https://agentmods.dev/skills/zztdandan/image-generate-mcp-remote/gpt-icon-generate"><img src="https://agentmods.dev/badge/skills/zztdandan/image-generate-mcp-remote/gpt-icon-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/zztdandan/image-generate-mcp-remote/gpt-icon-generate"><img src="https://agentmods.dev/badge/skills/zztdandan/image-generate-mcp-remote/gpt-icon-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 | $0.00181 | $0.03563 |
| Opus 5 | $0.00090 | $0.01782 |
| Sonnet 5 | $0.00036 | $0.00713 |
| Haiku 4.5 | $0.00018 | $0.00356 |
Grade A, and why
gpt-icon-generate 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 10d 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GPT Icon Generation Skill
用途
- 生成图标、图标包、应用图标、UI 图标、产品功能图标。
- 生成规则网格图标板,并拆分成透明 PNG 单图。
- 默认走
2K、1:1、4x4 / 16 icons、白底、贴合图标轮廓描边/外发光/柔和阴影。 - 用户可以指定行数、列数、尺寸、比例、MCP 工具、
pad、border、fuzz、postprocess等参数。 - 不支持自由散排;如果生成结果不是规则网格,应重新生成,不要强行切图。
MCP 与路径
- 本项目 MCP 配置文件:
.opencode/opencode.json - 默认图片 MCP 工具:
image-generate-mcp-remote_gpt_image_2_official - 临时探索工具:
image-generate-mcp-remote_gpt_image_2_temporary - 生成前优先调用
image-generate-mcp-remote_list_image_tools_catalog_tool检查当前工具支持的 size preset。 - 推荐输出路径:当前工作目录下的明确绝对路径,例如
/home/base/repo/document/app-icons-sheet.png
默认流程
如果用户没有特别指定,使用以下默认流程:
- 使用
image-generate-mcp-remote_gpt_image_2_official。 - 生成
2048x2048、1:1、纯白背景图标板。 - 图标布局为
4x4,共16个图标;expected_count = rows * cols。 - 提示词要求每个图标都有贴合自身轮廓的外描边、外发光或柔和阴影。
- 不要要求远离图标的方形卡片框、圆角矩形底板、大面积 backplate 或 tile。
- 生成后运行
verify_image_output.py校验实际宽高、比例、通道。 - 用实际宽高和行列运行
plan_icon_sheet_params.py计算切图参数。 - 用
split_icon_sheet_connected_bbox.py做整图连通域切图。 - 如需 UI 图标库,把每张图等比缩放后居中放入计算得到的透明画布,不固定写死
512x512。
可配置参数
rows:图标板行数,默认4cols:图标板列数,默认4size:生成尺寸,默认2048x2048aspect_ratio:图片比例,默认1:1tool:图片生成工具,默认gpt_image_2_official;陌生兼容站点试跑时才使用gpt_image_2_temporaryfuzz:背景 floodfill 容差,默认1.5%pad:组件 bbox 外扩像素,默认由实际图片尺寸计算border:透明图标边缘留白,默认由实际图片尺寸计算min_area:主组件最小面积阈值,默认由实际图片尺寸计算postprocess:透明边缘后处理模式,默认baseline,可选alpha_open_blur
expected_count 不需要用户指定,始终等于 rows * cols。
工具选择规则
- 默认使用
image-generate-mcp-remote_gpt_image_2_official。 - 如果用户明确要求 right.codes draw 兼容链路,优先要求服务启动时将
IMG_GEN_GPT_IMAGE_2_OFFICIAL_PRESET配置为right_codes_gpt_image_2,仍使用image-generate-mcp-remote_gpt_image_2_official。 - 只有在探索陌生 OpenAI Images 兼容站点、且还没有正式 preset 时,才使用
image-generate-mcp-remote_gpt_image_2_temporary。 - 如果目标尺寸不被当前工具支持,选择同宽高比下最接近的可用尺寸,并告知用户。
- 如果请求
2K但实际返回1K,不直接失败;必须以实际输出尺寸重新计算切图参数。
生成建议
- 明确要求
exactly {expected_count} icons in a {rows}x{cols} regular grid。 - 明确要求
canvas size {width}x{height}。 - 明确要求
pure white page background。 - 明确要求
ample padding between icons。 - 明确要求
each icon centered in its own cell。 - 优先要求每个图标外面有贴合图标轮廓的细、柔和、可见但不过厚的阴影轮廓,便于后续稳定切图。
- 不要生成远离图标的正方形卡片框、圆角矩形底板、大面积 backplate 或 tile;外框应像贴纸描边一样沿图标外轮廓包裹。
- 若需要透明底,提示词里写
transparent background with real alpha channel,并在生成后验证。 - 若模型经常生成伪透明图,不要继续强依赖 alpha,改为生成纯白背景 + 每个图标外贴合轮廓的描边/外发光/柔和阴影。
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.
- 10d ago First seen · 245 lines · 181 tokens per session scan A 823d7c4e2977
gpt-icon-generate is a skill published in the GitHub repository zztdandan/image-generate-mcp-remote (0 stars, last pushed 6d ago), licensed MIT. It adds 181 tokens to every session and 3,563 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
html-ppt-zhangzara-retro-zine
A neighborhood zine on the disappearing corner shops — portraits, voices, and what a block loses when they close. Built as a decision-grade story deck for community, local readers.
html-ppt-zhangzara-studio
A photography studio's portfolio-and-rate deck — the signature work, the process, and the packages that win the brief. Built as a decision-grade design craft deck for prospective clients.
motion-frames
A single-frame motion-design composition with looping CSS animations — rotating type ring, animated globe, ticking timer, parallax labels. Renders as a hero video poster you can hand straight to HyperFrames or any keyframe-based exporter. Use when the brief asks for "motion design", "animated hero", "loop", "video…
webgl-halftone-drift
A self-contained WebGL2 hero: a flowing field screened through a rotated halftone dot grid into a duotone print aesthetic; move the cursor to bend the drift.
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.
motion-graphics
A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI…