Skip to content
Back to skills

Codexmate

ASecurity

**Source:** SakuraByteCore/codexmate (Apache 2.0) **Stack:** Node.js, local-first, zero cloud

  • 10 stars
  • 0 votes
  • 0 copies
  • 4 views
  • Added September 9, 2026
ai-agentsbashnodegitapi

Works with

  • claude code
  • cli
  • api
  • mcp

Security analysis

A92/100
  • mediumUses curl or wget to download content
  • mediumInstalls packages at runtime which could introduce malicious dependencies

Pro shows the line behind each finding and how to fix it

Scanned September 9, 2026

npx -y skills add yanacuti1121/Yana-AI --skill codexmate --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Codexmate?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Codexmate
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/yanacuti1121-codexmate/badge)](https://www.skillsdirectory.com/skills/yanacuti1121-codexmate)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
# codexmate

**Source:** SakuraByteCore/codexmate (Apache 2.0)
**Stack:** Node.js, local-first, zero cloud

## When to use

- Quản lý nhiều AI coding tools (Codex, Claude Code, OpenClaw) từ 1 dashboard
- Browse/export sessions cross-tool
- Import/export skills giữa các agent apps
- Cần OpenAI-compatible bridge cho Codex
- Orchestrate tasks với DAG dependency tracking
- Expose local tools qua MCP stdio

## Do NOT use for

- Cloud-based agent management
- Production deployment (early stage)

---

## Install

```bash
# Homebrew (macOS / Linux)
brew tap SakuraByteCore/codexmate
brew install codexmate

# npm
npm install -g codexmate

# curl
curl -fsSL https://raw.githubusercontent.com/SakuraByteCore/codexmate/main/scripts/install.sh -o /tmp/codexmate-install.sh
# Inspect first: head -40 /tmp/codexmate-install.sh — then run if safe:
bash /tmp/codexmate-install.sh
```

---

## Core commands

```bash
codexmate run          # start dashboard (CLI + Web UI)
codexmate status       # live agent sync — show Codex/Claude config & status
codexmate sessions     # list + filter sessions across all tools
codexmate sessions export --tool claude --format json
codexmate skills       # local skills marketplace
codexmate skills import ./my-skill.md
codexmate tasks        # DAG task queue
codexmate bridge start # OpenAI-compatible bridge (port 3100)
codexmate update       # self-update
```

---

## Skills Marketplace (YAMTAM integration)

Codexmate có skills marketplace tương thích với format YAMTAM:

```bash
# Export YAMTAM skills sang codexmate
codexmate skills import core/skills/moss-tts-nano/SKILL.md

# Import skill từ codexmate về YAMTAM
codexmate skills export my-skill > core/skills/my-skill/SKILL.md
```

---

## OpenAI Bridge

```bash
# Start bridge — Codex Responses API → OpenAI format
codexmate bridge start --port 3100

# Dùng với bất kỳ OpenAI-compatible client
curl http://localhost:3100/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model":"codex","messages":[{"role":"user","content":"hello"}]}'
```

---

## MCP Integration

```bash
# Expose local tools via MCP stdio
codexmate mcp start

# Add to Claude Code settings
# .claude/settings.json → mcpServers → codexmate
```

```json
{
  "mcpServers": {
    "codexmate": {
      "command": "codexmate",
      "args": ["mcp", "start"]
    }
  }
}
```

---

## Session Browser

```bash
# Search sessions across Codex / Claude / Gemini
codexmate sessions --search "authentication"
codexmate sessions --tool claude --since 7d
codexmate sessions export --output sessions.json
```

---

## Web UI

```bash
codexmate run --ui   # mở web dashboard tại http://localhost:4200
```

Dashboard có: provider switcher, session browser, usage analytics, task queue, prompt templates.

---

## References

- Repo: https://github.com/SakuraByteCore/codexmate
- Docs: https://sakurabytecore.github.io/codexmate/
- npm: https://www.npmjs.com/package/codexmate

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.