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 aAAaqwq/AGI-Super-Team --skill code-material-gengit clone --depth 1 https://github.com/aAAaqwq/AGI-Super-TeamWrote 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/aaaaqwq/agi-super-team/code-material-gen)<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/code-material-gen"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/code-material-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 5.1 | $0.00075 | $0.01091 |
| Opus 5 | $0.00037 | $0.00545 |
| Sonnet 5 | $0.00015 | $0.00218 |
| Haiku 4.5 | $0.00007 | $0.00109 |
Grade A, and why
code-material-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 2d 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
code-material-gen — 代码生成配图素材
HTML/CSS + Playwright 渲染，全中文手写字体，像素精确，零成本
定位
当素材需要全中文、手写字体、字迹清晰、可复现时使用。替代API生图方案（longform-visual-notes），不消耗任何API额度。
与其他skill的关系
| Skill | 关系 |
|---|---|
| longform-visual-notes | 互补：API生图 vs 代码生成 |
| content-cover-gen | 互补：封面场景可用code-material-gen |
| daily-gzh-content | 素材生成阶段调用 |
| daily-xhs-content | 小红书素材（比例改3:4） |
快速使用
python3 ~/clawd/skills/code-material-gen/scripts/generate.py \
--type list \
--title "三个核心建议" \
--items "建议一:先用Excel写规则" "建议二:手动执行30天" "建议三:追求稳定性" \
--font MaShanZheng \
--palette ink \
--size 1536x1024 \
--output /path/to/output.png
素材类型
| type | 用途 | items格式 |
|---|---|---|
timeline |
时间线/阶段图 | "阶段一:描述" "阶段二:描述" |
compare |
对比表格（表头第一项） | "指标|A|B" "胜率|59%|61%" |
list |
要点列表/编号卡片 | "标题:描述" |
quote |
金句/引用卡片 | "金句文字" "作者" |
cover |
文章封面 | "副标题" "标签1,标签2" |
chart |
数据展示（同list） | 同list |
手写字体
| 字体 | 风格 | 推荐场景 |
|---|---|---|
MaShanZheng |
马善政楷体 | ✅ 推荐，清晰有力，正文首选 |
ZCOOLKuaiLe |
站酷快乐体 | 圆润活泼，适合轻松内容 |
LiuJianMaoCao |
刘建毛草 | 草书风格，仅适合大标题 |
ZhiMangXing |
芝麻行书 | 行书风格，适合金句卡片 |
配色方案
| palette | 风格 | 适用 |
|---|---|---|
tech |
深色科技（深蓝底+亮蓝） | AI/科技/数据主题 |
warm |
暖色纸张（米色底+橙红） | 经验分享/生活类 |
ink |
水墨风（白底+红黑） | ✅ 推荐，文化感强 |
minimal |
极简白（白底+蓝） | 通用/商务 |
尺寸建议
| 平台 | 推荐 | 参数 |
|---|---|---|
| 公众号/抖音 | 16:9 | 1536x1024 |
| 小红书 | 3:4 | 1024x1365 |
| 封面 | 16:9 | 1920x1080 |
输出规范
- ✅ 全中文，无任何英文
- ✅ 手写字体，清晰可读
- ✅ 零成本，不消耗API
- ✅ 可复现，同样参数永远输出一样
- ✅ <1秒/张，批量生成极快
依赖
- Python 3 + Playwright（
pip install playwright） - 中文字体文件在
~/.fonts/chinese-handwriting/ - 无需网络，无需API key
更新日志
- v1.0.0 (2026-04-18): 初始版本
- 5种素材类型（timeline/compare/list/quote/cover）
- 4种手写字体（马善政/站酷快乐/刘建毛草/芝麻行书）
- 4种配色方案（tech/warm/ink/minimal）
What ships with it
7 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.
- scripts/~/clawd/projects/MediaClaw/output/articles/2026-04-18/ai-quant-real-review/素材/01-三阶段时间线.png 51 KB
- scripts/~/clawd/projects/MediaClaw/output/articles/2026-04-18/ai-quant-real-review/素材/02-阶段数据对比.png 51 KB
- scripts/~/clawd/projects/MediaClaw/output/articles/2026-04-18/ai-quant-real-review/素材/03-三个真实认知.png 60 KB
- scripts/~/clawd/projects/MediaClaw/output/articles/2026-04-18/ai-quant-real-review/素材/04-五个实用建议.png 99 KB
- scripts/~/clawd/projects/MediaClaw/output/articles/2026-04-18/ai-quant-real-review/素材/05-风控规则.png 73 KB
- scripts/~/clawd/projects/MediaClaw/output/articles/2026-04-18/ai-quant-real-review/素材/06-金句.png 22 KB
- scripts/generate.py 12 KB 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.
- 2d ago First seen · 101 lines · 75 tokens per session scan A 3c0903f17746
code-material-gen is a skill published in the GitHub repository aAAaqwq/AGI-Super-Team (91 stars, last pushed 3d ago), licensed MIT. It adds 75 tokens to every session and 1,091 once invoked, about $0.0004 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
frontend-design
Use this as the design-lead layer for VideoStudio COMPOSE work. It shapes project/composition/composition-manifest.json::artdirection and the model-authored HTML/SVG motion graphics in index.html.
image-design-review
Read this skill only after a passing COMPOSE or HYBRID imagestudio project.snapshot returns visualevidence.attached:true. Never load it at task start, during routing, or in the same parallel batch as image-router. Never use it for a GENERATE or EDIT raster, including strict reproduction, semantic editing, explicit…
composition-design-review
Apply this checklist yourself after a successful composition.snapshot, before the preview is shown. It is advisory: nothing is submitted to the host, no operation records a verdict, and no gate waits on it — the host publishes the contact sheet with the passing snapshot. It is a design QA layer for your own authoring…
image-canvas
Read this private ImageStudio skill only after route lock when the result has multiple meaningful visual regions, an explicit reading order, exact layout constraints, or references bound to regions. Skip it for a simple single-region image. If art direction is also needed, read image-craft first. This adapts the…
image-craft
Read this skill only after route lock when the task needs original art direction, restyling, or clarification of an underspecified look. Skip it for crop, resize, format conversion, background removal, deterministic placement, or a narrow edit whose visual system is already defined.
slides
A slide generator that creates PNG images for presentation decks, including simple backgrounds for spoken-video scripts and fuller layouts for standalone presentations.