SkillFoxx

AI Context Linker CLI

A CLI and skill that build a reviewed ai_context.md briefing from chosen projects so ChatGPT gets context without any code upload.

  • 100 ★ on the repository
  • Last commit
  • MIT
CLI

Extended access

Why this level

  • Reads local project metadata and publishes a briefing to a cloud folder.
All reasons and checks

xhonye/ai-context-linkerAuthor:xhonye

Install

Manual install

uv tool install --python 3.11 git+https://github.com/xhonye/AI-Context-Linker.git@v0.2.7

The first manual install command from the README. Git and uv are required.

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • Reads local project metadata and publishes a briefing to a cloud folder.

This is third-party code. Review the repository files before installing.

What it does

AI Context Linker prepares material for ChatGPT about your projects: goals, current status, blockers and next steps from a reviewed manifest. The result is an `ai_context.md` file that you upload to a regular chat or publish to a synced Google Drive folder. Scanning covers only allowlisted projects and by default reads neither source code nor chat transcripts. Each project gets visibility, sensitivity and a redaction profile, and a missing policy means deny. There is a demo on fictional projects, a relationship graph and an optional index of installed skills without their text.

Who it is for. People who run several projects with Codex and want to discuss plans in ChatGPT without retelling context every time.

Good fit when

  • You need to compare projects and pick what to push today.
  • A discussion moves from Codex to ChatGPT and context must carry over.
  • After new work the briefing is refreshed by asking the agent to update ai_context.
  • An agent validates the workspace config and manifest.

Not a fit when

  • You want ChatGPT to read or change source code.
  • Projects cannot leave the machine even as a briefing.
  • You need an MCP server with live file access.

Example request

Install AI Context Linker following INSTALL.md, run the demo and show ai_context.md without scanning my real projects.

Limitations

Git and uv are required, and uv prepares Python 3.11 in isolation. Connecting real projects the first time needs your review of scope and visibility. Data without progress records stays unknown: the briefing does not guess. Versions are 0.2.x, so the project is young. ChatGPT updates by file upload or a synced folder, and the briefing does not change on its own. A cloud folder leaves your computer, so publish only reviewed content to it.

How to disable. Remove the tool with `uv tool uninstall`, and delete the private configuration and published briefings separately, including the synced folder.

FAQ

What goes into ai_context.md?

Descriptions of chosen projects and reviewed progress. Source code and chat transcripts are not read unless you enable that per project.

How do I run the demo?

`ai-context-linker demo --output-dir ./linker-demo` from a directory outside the repository, with a new output folder. The demo uses fictional projects.

How does the briefing reach ChatGPT?

Upload the file to a regular chat or set up a synced Google Drive folder.

What about redaction?

Every project needs explicit visibility, sensitivity and a redaction profile. Without them the project is not published.

Is MCP required?

No. Neither an MCP server nor a repository upload is needed.

Discussion

No questions or reviews yet.

CLI tools
Needs a VPN

A skill and the ai-collab tool for Codex CLI, Claude Code and API models to work on a project, plus file reading in ChatGPT

CLIBroad access212

Indexes project files and composes a short task context into a file so the agent is not buried in noise

CLIExtended access62
Needs a VPN

A desktop app with a local MCP server that lets ChatGPT work with files, commands, skills and other MCP servers

MCP serverBroad access394

A Codex skill that hands tasks to web ChatGPT with project terminal access, saving Codex quota; modes from Medium to Pro.

SkillBroad access138
Needs a VPN

A Go command-line client for working with OpenAI, Azure, Perplexity and LLaMA language models right from the terminal

CLIBroad access966

README in short

Installation can be delegated to an agent via INSTALL.md, and manual commands are given separately. The boundaries section lists what is not exported by default.

README badge

Report a problem