CodexGuide is a practical knowledge base and learning guide for using Codex across development, writing, research, automation, and team workflows. It serves beginners, developers, creators, researchers, and teams who want to learn how to use Codex and incorporate it into real tasks. The catalogue entries are Codex skills associated with this guide.
Borrowing it
Nothing to install: this file belongs to freestylefly/CodexGuide. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/freestylefly/CodexGuide/main/.agents/skills/image-publish/SKILL.mdgit clone --depth 1 https://github.com/freestylefly/CodexGuideWrote 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/freestylefly/codexguide/image-publish)<a href="https://agentmods.dev/skills/freestylefly/codexguide/image-publish"><img src="https://agentmods.dev/badge/skills/freestylefly/codexguide/image-publish/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/freestylefly/codexguide/image-publish"><img src="https://agentmods.dev/badge/skills/freestylefly/codexguide/image-publish.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 | $0.00043 | $0.01362 |
| Opus 5.5 | $0.00017 | $0.00545 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo ago First seen · 120 lines · 43 tokens per session scan A de1dd05b09c9
image-publish is a skill published in the GitHub repository freestylefly/CodexGuide (3,966 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 1,362 once invoked, about $0.0002 per session on Opus 5.5. 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.
image-publish compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| image-publishfreestylefly/CodexGuide | Skill | 4.0k | yesterday | MIT | A | 43 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |