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/freestylefly/codexguide/image-publishnpx skills add freestylefly/CodexGuide --skill image-publishgit clone --depth 1 https://github.com/freestylefly/CodexGuideWhat 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 | $0.00043 | $0.01362 |
| Opus 5 | $0.00022 | $0.00681 |
| Sonnet 5 | $0.00009 | $0.00272 |
| Haiku 4.5 | $0.00004 | $0.00136 |
Grade A, and why
image-publish 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 3d 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.
完成标准：`curl -I` 返回 `HTTP/1.1 200 OK`，并且 `Content-Type` 是图片类型。 How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
图片发布
本 Skill 仅供 CodexGuide 仓库使用。目标是把插入文档的图片处理成可发布状态：本地规范命名，按需加水印，上传到阿里 OSS，通过 CDN 验证，最后在 Markdown 中引用公开 URL。
步骤
-
首次在本会话使用本 Skill 时，询问用户是否把新图片默认处理为“加水印 + 图床化 + 替换到实际文档/网页”。
- 如果用户同意，本会话后续新图片默认自动执行：规范命名、添加
苍何水印、上传 OSS、验证 CDN、把文档或网页中的引用替换为水印版 CDN URL。 - 如果用户不同意，仅按用户每次明确要求处理。
- 如果用户已经在本会话明确同意过，不要重复询问。 完成标准：本会话的新图片默认处理偏好已明确。
- 如果用户同意，本会话后续新图片默认自动执行：规范命名、添加
-
确认源图片和目标 Markdown。 完成标准：明确源文件、插入位置和图片 alt 文本。
-
规范本地图片文件。
- 指南正文图片默认放在
docs/images/。 - 文件名使用小写 kebab-case，描述图片内容，不使用截图编号。
- 除非用户明确要求转换格式，否则保留原扩展名。 完成标准：最终本地路径稳定，且没有覆盖无关文件。
- 指南正文图片默认放在
-
按偏好或用户要求添加水印。
- Windows 使用
scripts/add-watermark.ps1。 - Linux/macOS 使用
scripts/add-watermark.sh。 - 默认水印文字是
苍何。 - 先生成预览图；用户确认效果前，不替换原图。
- 如果用户已同意默认水印，后续新图片不需要每次重新确认水印。 完成标准：预览图已生成，并完成视觉检查。
- Windows 使用
-
上传到阿里 OSS。
- Windows 使用
scripts/upload-oss-image.ps1。 - Linux/macOS 使用
scripts/upload-oss-image.sh。 - 从
.env.oss.local读取凭据。 - 如果
.env.oss.local缺失，先新建带占位符的.env.oss.local模板，让用户补充后停止本次上传。 - 不打印密钥。
- 优先使用文档中已有的 CDN 形态：
https://cdn.canghecode.com/codexguide/docs/images/<name>。 完成标准：脚本输出对象路径和公开 URL。
- Windows 使用
-
验证 CDN URL。 完成标准：
curl -I返回HTTP/1.1 200 OK，并且Content-Type是图片类型。 -
仅在图片 URL 验证通过后更新 Markdown 或网页。
- 如果用户已同意默认图床化和水印，文档和网页里应引用水印版 CDN URL，而不是本地图片或无水印 URL。 完成标准：目标文件在指定位置包含最终 CDN URL，本地行号检查能看到插入或替换后的内容。
命令
Windows 水印预览：
.\.agents\skills\image-publish\scripts\add-watermark.ps1 `
-InputPath .\docs\images\example.png `
-OutputPath .\docs\images\example-watermarked.png `
-Text "苍何"
Windows OSS 上传：
.\.agents\skills\image-publish\scripts\upload-oss-image.ps1 `
-InputPath .\docs\images\example-watermarked.png `
-PublicName example-watermarked.png
Linux/macOS 水印预览：
.agents/skills/image-publish/scripts/add-watermark.sh \
docs/images/example.png \
docs/images/example-watermarked.png \
"苍何"
Linux/macOS OSS 上传：
.agents/skills/image-publish/scripts/upload-oss-image.sh \
docs/images/example-watermarked.png \
example-watermarked.png
What ships with it
4 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.
- 3d ago First seen · 120 lines · 43 tokens per session scan A de1dd05b09c9
image-publish is a skill published in the GitHub repository freestylefly/CodexGuide (3,368 stars, last pushed 5d ago), licensed MIT. It adds 43 tokens to every session and 1,362 once invoked, about $0.0002 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
embedded-captions
Add captions or subtitles to an existing single-subject talking-head video without editing the footage. Use for plain verbatim captions, cinematic captions embedded behind the subject, VFX captions, “炸/特效/酷炫字幕,” or a named identity from the 35-style catalog. Route by visual identity, not by backend engine. The quiet…
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.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
剪辑环境的唯一管理者：就绪检查（skills 是否最新 → Runtime 是否配套）、Skills 更新激活、Runtime 安装与体检。用户说检查更新、安装剪辑环境、装播放器、检查剪辑环境、剪辑环境就绪了吗、配置转录凭证时使用；业务 Skill（剪口播/字幕/画面/导出）第 0 步也引用本 Skill 的就绪检查。不用于剪辑、字幕、画面、导出本身或项目数据迁移。.
cap_llm_inspect_image
How to inspect a local image with inspectimage.