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 agentmods add skills/fuyuxiang/echo-agent/image-gennpx skills add fuyuxiang/echo-agent --skill image-gengit clone --depth 1 https://github.com/fuyuxiang/echo-agentWrote 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/fuyuxiang/echo-agent/image-gen)<a href="https://agentmods.dev/skills/fuyuxiang/echo-agent/image-gen"><img src="https://agentmods.dev/badge/skills/fuyuxiang/echo-agent/image-gen.svg" alt="Measured on agentmods" 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 | $0.00023 | $0.00579 |
| Opus 5 | $0.00012 | $0.00290 |
| Sonnet 5 | $0.00005 | $0.00116 |
| Haiku 4.5 | $0.00002 | $0.00058 |
Grade A, and why
image-gen scanned grade A 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl "https://image.pollinations.ai/prompt/A%20cat%20wearing%20sunglasses" -o output.png What it actually says
Image Generation
Generate images from text prompts. Multiple provider options.
Option A: OpenAI DALL-E 3 (Best quality)
Requires OPENAI_API_KEY.
from openai import OpenAI
client = OpenAI()
response = client.images.generate(
model="dall-e-3",
prompt="A serene mountain lake at sunset, photorealistic",
size="1024x1024",
quality="standard", # or "hd"
n=1,
)
image_url = response.data[0].url
Sizes: 1024x1024, 1792x1024, 1024x1792
Option B: Pollinations.ai (Free, no key)
# Simple GET request - returns PNG
curl "https://image.pollinations.ai/prompt/A%20cat%20wearing%20sunglasses" -o output.png
# With parameters
curl "https://image.pollinations.ai/prompt/YOUR_PROMPT?width=1024&height=1024&seed=42" -o output.png
Option C: Stability AI
Requires STABILITY_API_KEY.
curl -X POST "https://api.stability.ai/v2beta/stable-image/generate/sd3" \
-H "authorization: Bearer $STABILITY_API_KEY" \
-H "accept: image/*" \
-F "prompt=lighthouse on a cliff" \
-F "output_format=png" \
-o output.png
Script
python3 scripts/generate_image.py "A cat in space" --provider dalle --output /tmp/gen.png
python3 scripts/generate_image.py "Logo design" --provider dalle --size 1024x1024
python3 scripts/generate_image.py "Mountains" --provider stability --output landscape.png
Requires API key environment variable:
- DALL-E:
export OPENAI_API_KEY=sk-xxx - Stability AI:
export STABILITY_API_KEY=sk-xxx
Prompt Tips
- Be specific: "a red fox sitting in snow, photorealistic, 4K" > "fox"
- Style keywords: photorealistic, watercolor, oil painting, pixel art, anime
- Negative: avoid ambiguous words, be descriptive
What ships with it
1 file 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.
- 4d ago First seen · 75 lines · 23 tokens per session scan A dff22ddbeccf
image-gen is a skill published in the GitHub repository fuyuxiang/echo-agent (988 stars, last pushed 4d ago), licensed MIT. It adds 23 tokens to every session and 579 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pptx
从论文、大纲或结构化文本生成 PowerPoint (.pptx) 演示文稿。Use when 用户需要把一篇论文/文章/大纲做成幻灯片、slides、演示文稿、PPT、deck。Don't use when 只需纯文本总结、生成 Word/PDF、或修改已有 pptx 的单个像素级样式。.
ppt-generation
Generate PPTX presentations from slide plan + content.
chart-visualization
Generate charts: select type, extract data, render image.
oc-dossier
OC / 角色档案 / 人物档案的全生命周期技能（对应 HMA「原创角色」命名空间）。覆盖两个互补入口： （A）存角色——用户丢来文字 / 文件说"把这个角色存下来""从书里摘个人物"时，先跑 occlassify.py 拿确定性 verdict，再分流：structured→dossierbuild.py 自动切片落库；ambiguous→AI 按三层铁律理解抽取落库；两路落库后都刷 ocregistry 快照。 （B）唤醒角色——对话里叫到已落库 OC 的名字 / 代号并像对其说话时，用 ocregistry.py find 确定性解析到基础包，进入角色扮演，按需惰性召回故事 / 拓展包。 三层铁律：① 基础包必有且仅 1…
aimh-worldbook
AIMH 的「世界书拆解器」可选技能。当 AI 在会话中阅读/处理一篇超长文本（书籍 / 长篇资料，字数达几万级， 超过阈值导致 token 消耗过大）时，主动回问用户是否需要把该文本拆解为一套结构化「世界书」 （world bible）——即作家创作前脑中那本固定的作品世界设定集：人物卡、地点卡、时间线、概念/主题卡、 故事线、章节索引。拆解产物是一组互相关联的 AIMH 包（概览包 + 分章包 + 人物/概念聚合包）， 全部遵循 FM-V2 契约、确定性落盘、不幻觉。 何时用（命中即加载）： - 触发条件：AI 正要读/已读入一篇超长文本（书籍 / 长篇资料，字数达几万级）（默认阈值见下「触发与回问」），…
podcast-generation
Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.