codex-command-center

Name: codex-command-center
Author: sevensir888

Pending

A local desktop control center for organizing Codex projects, engineering tasks, sessions, Git changes, Skills, and MCP configuration.

50stars

1forks

TypeScript

Installation

# Add to your Claude Code skills
git clone https://github.com/sevensir888/codex-command-center

Getting Started

Guides for using ai agents skills like codex-command-center.

Caveman: Cut Claude Token Use by 65%
How agent-side prompt compression works, when to use it, and when not to.
What is an AI Skills Marketplace?
Definitions, how marketplaces work, and how to choose between them in 2026.
Getting Started with AI Skills

README.md

Frequently Asked Questions

What is codex-command-center?

codex-command-center is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by sevensir888. A local desktop control center for organizing Codex projects, engineering tasks, sessions, Git changes, Skills, and MCP configuration. It has 50 GitHub stars.

Is codex-command-center safe to use?

codex-command-center's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.

How do I install codex-command-center?

Clone the repository with "git clone https://github.com/sevensir888/codex-command-center" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is codex-command-center written in?

codex-command-center is primarily written in TypeScript. It is open-source under sevensir888 on GitHub, so you can review or fork the full source.

Are there alternatives to codex-command-center?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh codex-command-center against similar tools.

Agentic AI for Beginners

Build your first AI agent from scratch - tool use, ReAct pattern, memory, deployment

41 minBeginner

Comments (0)

to leave a comment.

No comments yet. Be the first to share your thoughts!

Related Skills

ECC

by affaan-m

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,219

claude-skills conduit

Codex Command Center

Turn Codex sessions into organized engineering work.

Codex Command Center is a Windows-first, local-first desktop workspace for organizing Codex-based engineering work across projects, tasks, sessions, Git changes, Skills, and MCP configuration.

Codex does the reasoning, editing, commands, and tests. Codex Command Center keeps the surrounding engineering workflow understandable and resumable.

Overview

Heavy Codex usage can leave useful context spread across:

local repositories;
engineering objectives;
Codex session history;
staged and unstaged Git changes;
local Skills;
MCP configuration.

Codex Command Center connects those pieces into one focused workflow:

Project -> Task -> Codex Session -> File Changes -> Result

The app is intentionally smaller than an IDE, terminal emulator, chat client, or advanced Git GUI. It is an organizing layer for local Codex work.

Screenshots

Dashboard	Projects and tasks

Sessions	Git changes

Codex environment

Core features

Project organization: register local development folders and see branch, Git state, task counts, and recent activity.
Task tracking: organize engineering objectives with Planned, Active, Completed, and Blocked statuses.
Codex session discovery: index local Codex session metadata without mutating Codex session files.
Session workflows: link sessions to tasks, launch Codex for a task, and resume selected sessions through the local Codex CLI.
Git review: inspect branch, staged files, unstaged files, working-tree state, and per-file diffs; stage, unstage, and commit focused changes.
Codex environment visibility: show detected Codex CLI path/version, redacted local configuration previews, discoverable Skills, and MCP server summaries.
Local-first storage: keep projects, tasks, session links, and settings on the local machine.

Typical workflow

Add a repository
-> create or select an engineering task
-> launch or resume Codex work
-> review indexed sessions
-> inspect Git changes
-> continue, complete, or block the task

Local-first behavior

The app stores its own state as local JSON under the user's local application data directory. Registered projects are path references; Codex Command Center does not copy project source code into application storage.

The native layer reads local Codex session metadata, local Codex configuration files, local Skills folders, local MCP configuration, and Git status for registered projects. Configuration previews redact lines that appear to contain keys, tokens, secrets, or passwords.

The project does not add telemetry, analytics, accounts, cloud synchronization, source-code upload, Codex-session upload, or Git-diff upload. The app can still invoke external local tools such as codex and git; those tools have their own behavior and configuration.

Requirements

Windows 11 is the primary supported platform.
Git on PATH for Git review.
Codex CLI on PATH for launch and resume actions.
Node.js 24 is the validated source-development and production-build version; Rust and Cargo are also required for native builds.

Installation

Windows binaries are available from GitHub Releases.

NSIS setup executable: recommended for most Windows users. This is the normal interactive installer.
MSI installer: useful for users or environments that prefer MSI-based installation or deployment.
Standalone executable: can run directly without a normal installer.

The v0.1.0 Windows binaries are currently unsigned. Source-build instructions remain in the Development and Build sections below.

Development

Install dependencies:

npm ci

Run the browser development surface:

npm run dev

Run the desktop app:

npm run tauri:dev

Run the frontend production build:

npm run build

Run the lightweight tracked-file secret scan:

npm run check:secrets

Build

Build the desktop application:

npm run tauri:build

For native checks when Cargo is available:

cargo fmt --manifest-path src-tauri/Cargo.toml -- --check
cargo check --manifest-path src-tauri/Cargo.toml
cargo test --manifest-path src-tauri/Cargo.toml
cargo clippy --manifest-path src-tauri/Cargo.toml --all-targets --all-features -- -D warnings

Architecture

Frontend: React and TypeScript under src/.
Desktop shell: Tauri 2 configuration under src-tauri/.
Native commands: Rust commands for local filesystem, process launch, Git, Codex session indexing, Skills discovery, and MCP configuration summaries.
Storage: local JSON state under the user's local application data directory.
Codex integration: local Codex CLI detection plus launch/resume commands.
Git integration: local Git CLI calls for branch, status, diff, stage, unstage, and commit operations.

Relationship to CodMate

Codex Command Center evolved from the open-source CodMate project by Loocor. Upstream work is acknowledged, and applicable Apache-2.0 licensing and attribution are preserved in LICENSE, NOTICE, and THIRD-PARTY-NOTICES.md.

This project has been substantially refocused and reworked around a Windows-first, Codex-centric workflow for projects, tasks, sessions, and Git changes. It should not be described as built entirely from scratch.

Contributing

See CONTRIBUTING.md.

Use Issues for bugs and focused feature requests, Discussions for questions, workflow ideas, and general feedback, and Security for private vulnerability reports.

Security

See SECURITY.md.

Roadmap

See ROADMAP.md.

Release notes

Release notes for v0.1.0 are available under docs/releases/v0.1.0.md and on the GitHub Releases page.

License

Codex Command Center is distributed under the Apache License 2.0.

Disclaimer

Codex Command Center is an independent open-source project and is not an official OpenAI product. OpenAI, Codex, and related marks belong to their respective owners.