Codex Image To Eagle logo

Codex Image To Eagle

Organization
vibeshotclub
codex-image-to-eagle

Archive Codex-generated images from the current user's Codex generated_images directory into Eagle with the prompt saved as annotation. Use when the user asks to save, archive, import, or sync Codex generated images to Eagle with prompts, tags, and folders.

Overview

Publishervibeshotclub
Repositoryvsc-skills
Skill namecodex-image-to-eagle
Stars
876
Forks
139
Bundled files
1
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by vibeshotclub on GitHub. Read the source before you install it.

Installation

Install the Codex Image To Eagle AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/vibeshotclub/vsc-skills/tree/main/codex-image-to-eagle
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/vibeshotclub/vsc-skills.git /tmp/vsc-skills
mkdir -p .claude/skills
cp -r /tmp/vsc-skills/codex-image-to-eagle .claude/skills/codex-image-to-eagle
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Codex Image To Eagle in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Codex Image To Eagle on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Codex Image To Eagle is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Codex Image to Eagle

Archive images generated by Codex into Eagle and preserve the prompt as searchable metadata.

Default behavior

  • Image source: CODEX_GENERATED_IMAGES_DIR if set, otherwise <current user home>/.codex/generated_images
  • Eagle connection: local Eagle MCP server on http://127.0.0.1:41596 by default. Prefer the IPv4 loopback address over localhost to avoid IPv6/hostname resolution issues.
  • Stdio mode: the script reads the current user's ~/.codex/config.toml, prefers [mcp_servers.eagle], and can auto-detect other Eagle-like stdio MCP entries. Use --transport http to force the legacy HTTP path.
  • Import method: Eagle MCP item_add
  • Prompt storage: Eagle item annotation
  • Default tags: Codex, AI生成, Prompt
  • Default folder: use the folder requested by the user as the root; if none is specified, create or reuse Codex 生成图
  • Default organization: put each image into a local-date subfolder under the root, e.g. Codex 生成图/2026-4-26
  • Folder safety: resolve folders by exact parent-child path, not by name alone. Folder creation is guarded by a local lock to avoid duplicate date folders when several automation jobs run at the same time.

Script

Use the bundled script:

bash
node scripts/archive-codex-image-to-eagle.js --latest --prompt "PROMPT_TEXT"

The bundled script defaults to http://127.0.0.1:41596. If needed, override it explicitly:

bash
EAGLE_SERVER_URL=http://127.0.0.1:41596 node scripts/archive-codex-image-to-eagle.js --latest --prompt "PROMPT_TEXT"

Stdio MCP mode:

bash
node scripts/archive-codex-image-to-eagle.js --transport stdio --latest --prompt "PROMPT_TEXT"
node scripts/archive-codex-image-to-eagle.js --transport stdio --check-connection

Example Codex config:

toml
[mcp_servers.eagle]
command = "node"
args = ["/your/Eagle/Plugins/mcp-server/modules/mcp-proxy.js"]
env = { EAGLE_SERVER_URL = "http://127.0.0.1:41596" }

Important: the script can read ~/.codex/config.toml, but it cannot automatically reuse MCP tools already connected to Codex. If the script is launched inside a network-restricted automation shell, a child stdio proxy may still inherit that sandbox. The strongest automation path is to call the configured Eagle MCP tool directly from Codex instead of shelling out to this script.

When using Eagle MCP tools directly, folder handling must follow this exact rule:

  1. Resolve the root folder first.
    • Prefer EAGLE_CODEX_ROOT_FOLDER_ID or a user-provided root folder ID.
    • Otherwise call folder_get with getAllHierarchy: true, fullDetails: true and find the root folder whose name is exactly Codex 生成图 or the requested root name and whose parent/parentId is empty.
  2. Resolve the date folder only under that root folder.
    • Search children by exact name and exact parent ID.
    • Never search by date name globally.
    • Never create a date folder at Eagle root level unless the requested root itself is intentionally the Eagle root.
  3. Create a missing date folder with parentId set to the resolved root folder ID.
  4. If more than one matching date folder already exists under the same root, reuse the oldest existing folder ID and report the duplicate instead of creating another one.
  5. For automation concurrency, prefer the bundled script because it has a local lock around folder creation.

Common options:

bash
# Import the newest Codex-generated image.
node scripts/archive-codex-image-to-eagle.js --latest --prompt "PROMPT_TEXT"

# Override the Codex generated image directory when needed.
node scripts/archive-codex-image-to-eagle.js --latest --image-dir "~/.codex/generated_images" --prompt "PROMPT_TEXT"

# Import all image files in the newest generated_images session folder.
node scripts/archive-codex-image-to-eagle.js --latest-session --prompt "PROMPT_TEXT"

# Import a specific file.
node scripts/archive-codex-image-to-eagle.js --path "/absolute/path/image.png" --prompt "PROMPT_TEXT"

# Read a long prompt from a file.
node scripts/archive-codex-image-to-eagle.js --latest --prompt-file "/absolute/path/prompt.txt"

# Choose a target Eagle folder by name or ID.
node scripts/archive-codex-image-to-eagle.js --latest --folder-name "Codex 生成图" --prompt "PROMPT_TEXT"
node scripts/archive-codex-image-to-eagle.js --latest --folder-id "FOLDER_ID" --prompt "PROMPT_TEXT"
node scripts/archive-codex-image-to-eagle.js --latest --root-folder-id "ROOT_FOLDER_ID" --prompt "PROMPT_TEXT"

# Automation: fixed folder ID skips folder_get/folder_create permission prompts.
EAGLE_CODEX_FOLDER_ID="FOLDER_ID" node scripts/archive-codex-image-to-eagle.js --latest --prompt "PROMPT_TEXT"

# Automation: fixed root folder ID still creates/reuses date subfolders under that root.
EAGLE_CODEX_ROOT_FOLDER_ID="ROOT_FOLDER_ID" node scripts/archive-codex-image-to-eagle.js --latest --prompt "PROMPT_TEXT"

# Disable date subfolders and import into the root folder directly.
node scripts/archive-codex-image-to-eagle.js --latest --no-date-subfolders --prompt "PROMPT_TEXT"

# Preview without modifying Eagle.
node scripts/archive-codex-image-to-eagle.js --latest --prompt "PROMPT_TEXT" --dry-run

# Test MCP connectivity without importing images.
node scripts/archive-codex-image-to-eagle.js --transport stdio --check-connection

Workflow

  1. Identify the image path.
    • If the user refers to the latest generated image, use --latest.
    • If a generation produced multiple images, use --latest-session.
    • If the user provides a path, use --path.
  2. Capture the final prompt exactly as used to generate the image.
  3. Run the script with the prompt.
  4. Return the imported Eagle item ID(s) and the folder used.

Prompt annotation format

The script writes this structure into Eagle annotation:

text
Prompt:
...

Archive:
- source: Codex
- original_path: ...
- archived_at: ...

Safety

  • Do not delete or move source files in the Codex generated images directory.
  • Use --dry-run first when the prompt, folder, or image selection is uncertain.
  • If Eagle is not running or the MCP plugin is disabled, ask the user to start Eagle and enable Eagle MCP.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Codex Image To Eagle AI skill do?

Archive Codex-generated images from the current user's Codex generated_images directory into Eagle with the prompt saved as annotation. Use when the user asks to save, archive, import, or sync Codex generated images to Eagle with prompts, tags, and folders.

Why use Codex Image To Eagle on TypingMind?

Because you install it once and use it with any model. Codex Image To Eagle is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Codex Image To Eagle in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/vibeshotclub/vsc-skills/tree/main/codex-image-to-eagle. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Codex Image To Eagle?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Codex Image To Eagle?

As many as you like. As long as a model supports skills, you can use Codex Image To Eagle with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Codex Image To Eagle AI skill free?

It is published on GitHub by vibeshotclub. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇