AWorld is an agent harness, meaning a framework that coordinates an AI agent’s tools, memory, context, and execution so expert knowledge can be turned into reusable skills and autonomous agents. It is for building domain-specific agent applications and workflows, with the catalogue entries representing skills, agents, and commands that operate within the AWorld ecosystem.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/inclusionAI/AWorldnpx agentmods add skills/inclusionai/aworld/html-to-imageWrote 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/inclusionai/aworld/html-to-image)<a href="https://agentmods.dev/skills/inclusionai/aworld/html-to-image"><img src="https://agentmods.dev/badge/skills/inclusionai/aworld/html-to-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.
<a href="https://agentmods.dev/skills/inclusionai/aworld/html-to-image"><img src="https://agentmods.dev/badge/skills/inclusionai/aworld/html-to-image.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00046 | $0.00631 |
| Opus 5 | $0.00023 | $0.00316 |
| Sonnet 5 | $0.00009 | $0.00126 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
html-to-image 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.
What it actually says
HTML 转图片 (html-to-image)
概述
将 HTML 文件或内容通过 agent-browser 渲染为图片。典型用法：Claude 生成精美 HTML → 本 skill 截图 → 得到可直接发布的图片。
工具路径
- 脚本：
.claude/skills/html-to-image/html_to_image.sh - 依赖：
agent-browser（CDP 已连接）、python3
用法
./html_to_image.sh -o <output> [-f <html_file> | -c <html_content>] [-w <width>] [-p <cdp_port>] [--full]
参数
| 参数 | 说明 | 必填 | 默认 |
|---|---|---|---|
-o |
输出图片路径（.png） | 是 | - |
-f |
HTML 文件路径（与 -c 二选一） |
二选一 | - |
-c |
HTML 内容字符串（与 -f 二选一） |
二选一 | - |
-w |
视口宽度 | 否 | 1080 |
-e |
视口高度（不指定则全页截图） | 否 | - |
-p |
CDP 端口 | 否 | 9222 |
--full |
全页截图（忽略视口高度限制） | 否 | 默认开启 |
示例
# 从 HTML 文件截图
./html_to_image.sh \
-f card.html -o card.png
# 直接传入 HTML 内容
./html_to_image.sh \
-c '<html><body><h1>Hello</h1></body></html>' \
-o hello.png
# 指定宽度（适配手机尺寸）
./html_to_image.sh \
-f infographic.html -o output.png -w 750
# 固定视口截图（非全页）
./html_to_image.sh \
-f page.html -o output.png -w 1080 -e 1920 --no-full
典型工作流
- Claude 根据内容生成精美 HTML（信息图、卡片等）
- 使用本 skill 截图为 PNG
- 将截图传给
xhs-publisher发布到小红书
# 生成图片
./html_to_image.sh -f card.html -o card.png
# 发布到小红书
./.claude/skills/xhs-publisher/publish_xhs.sh -t "标题" -c "正文" -i card.png
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.
- 10d ago First seen · 69 lines · 46 tokens per session scan A c70e9093b72c
html-to-image is a skill published in the GitHub repository inclusionAI/AWorld (1,230 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 631 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 2026-08-30.
Other skills, from other repositories
record-browser-gif
Record browser or Web UI interaction demos as optimized GIFs using the available built-in browser, state-based frame capture, and deterministic encoding, then publish to a dedicated assets branch when the task includes attaching the GIF to a pull request. Use when asked to make, record, or generate a GIF that…
record-browser-gif
Record browser or Web UI interaction demos as optimized GIFs using the available built-in browser, state-based frame capture, and deterministic encoding, then attach the GIF to a pull request with gh --attach, falling back to a dedicated assets branch where attach cannot apply. Use when asked to make, record, or…
hive.browser-automation
Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…
hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
hive.image-generation
Required before calling imagegenerate. Create and edit images from a prompt — generate an image, make a picture / logo / illustration / icon / banner / poster / thumbnail / hero image / mockup / product shot / social graphic, or edit / restyle / combine existing images from reference images. Uses OpenAI gpt-image-2…