Skip to content
Back to search

open-agent-hub

MarketplaceWorks with Claude CodeGitHub

A lightweight, zero-dependency CLI tool to manage and activate capabilities for AI coding assistants (such as Claude Code, Cursor, Trae, etc.).

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026. Its scripts were only partly scanned.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/guanyang/open-agent-hub with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/guanyang/open-agent-hub'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/guanyang--open-agent-hub/badge.svg)](/listings/guanyang--open-agent-hub)

HTML

<a href="/listings/guanyang--open-agent-hub"><img src="/api/listings/guanyang--open-agent-hub/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

You can install and manage skills either directly using Vercel's standard `skills` CLI, or via our built-in zero-dependency manager (`oah`) which also supports managing Agents and Slash Commands.

Option 1: Quick Install via Vercel's `skills` CLI (Easiest)

If you only need to use the modular **Skills** and are using a compatible agent (like Claude Code, Cursor, etc.), you can use Vercel's official `skills` CLI to install them directly from this repository without cloning:

# Add all skills from this repository
npx skills@latest add guanyang/open-agent-hub

# Add a specific skill (e.g., remotion)
npx skills@latest add guanyang/open-agent-hub --skill remotion

Option 2: Clone and use the built-in CLI (`oah`)

If you want to manage **Skills, Agents, and Slash Commands** dynamically via local symlinks, or if you want to sync upstream sources, you can clone the repository and use our CLI tool:

1. Clone the Hub

Clone this repository locally (it is recommended to place it in a fixed location for global reference):

git clone https://github.com/guanyang/open-agent-hub.git ~/open-agent-hub

2. Global Link via CLI

In the root directory, run the link command to register the CLI manager `open-agent` (with aliases `open-agent-hub`, `oah`, `ahub`):

cd ~/open-agent-hub
npm link

3. Manage Capabilities

After linking, you can manage your local agent environments from anywhere:

# List all dynamically scanned Skills, Agents, and Commands
oah list

# Check link status in your current project workspace (default behavior)
oah status

# Check link status in global system configurations (e.g. ~/.claude/)
oah status --global

# Enable a specific component inside the current project workspace
oah enable canvas-design

# Enable all components (Skills, Agents, Commands) in current project workspace (defaults to all)
oah enable

# Enable all components in project workspace for Cursor (links to .cursor/)
oah enable --target=cursor

# Enable all components in project workspace for ALL supported targets
oah enable --target=all

# Enable all components globally for ALL supported targets
oah enable --global --target=all

# Enable all components globally (system-level)
oah enable --global

# Enable all components in a custom target directory (auto-creates subdirectories dynamically)
oah enable --path=/path/to/my_agent_dir

# Disable all components inside the current project workspace
oah disable

CLI Filters & Options:

* **Filters (Passed as the name argument, mutually exclusive):** * `<name>`: Enable/disable a single component by its name/ID. * `--skills`: Enable/disable only all Skills components. * `--agents`: Enable/disable only all Agents components. * `--commands`: Enable/disable only all Commands components. * `--all`, `-a`: Enable/disable all Skills, Agents, and Commands (default behavior when no arguments are provided). * **Options:** * `-p, --project` (default): Project-level activation (links config directories inside your current working directory, e.g. `.claude/`). * `-g, --global`: System global level activation (e.g., links into user home config folder, like `~/.claude/`). * `-t, --target <name>`: Target environment to link to (supported: `claude`, `antigravity`, `gemini`, `codex`, `cursor`, `trae`, `opencode`, `kiro` and `all` to configure all of them, default: `claude`). * `--path <dir_path>`: Custom base directory to link components into (creates and links within `skills/`, `agents/`, and `commands/` subdirectories automatically).

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 18 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. {
  2. "name": "open-agent-hub",
  3. "owner": {
  4. "name": "guanyang",
  5. "email": "guanyangsunlight@gmail.com"
  6. },
  7. "metadata": {
  8. "description": "Open Agent Hub plugin marketplace",
  9. "version": "3.0.0"
  10. },
  11. "plugins": [
  12. {
  13. "name": "open-agent-hub",
  14. "description": "Unified capability management center for Skills, Agents, and Commands.",
  15. "source": "./"
  16. }
  17. ]
  18. }
README.md · README · 176 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # open-agent-hub
  2. **English** | [简体中文](README.zh-CN.md)
  3. A lightweight, zero-dependency CLI tool to manage and activate capabilities for AI coding assistants (such as Claude Code, Cursor, Trae, etc.). With a single command, you can link **Skills** (modular prompting), **Agents** (expert workflow roles), and **Commands** (slash commands) to your project workspaces or global system configurations.
  4. ---
  5. ## 📂 Directory Structure
  6. ```
  7. .
  8. ├── agents/ # System prompts for expert Agents (agent-*.md)
  9. ├── commands/ # Agent runtime Slash Commands (*.md)
  10. ├── docs/ # Technical specs and user guidelines
  11. ├── scripts/ # CLI manager source code (hub.js)
  12. ├── skills/ # Modular capability skills (83+ skills)
  13. ├── spec/ # Technical specification definitions for capabilities
  14. ├── template/ # Development templates for Skills, Agents, and Commands
  15. ├── AGENTS.md # Project-level LLM coding guidelines
  16. ├── CLAUDE.md # Claude-specific coding guidelines
  17. ├── GEMINI.md # Gemini-specific coding guidelines
  18. ├── CHANGELOG.md # Changelog of project versions
  19. ├── CONTRIBUTING.md # Community guidelines for contributions
  20. ├── LICENSE # MIT license file
  21. ├── SECURITY.md # Vulnerability reporting policies
  22. ├── package.json # CLI configuration and npm registration
  23. ├── skills_index.json # Scanned and generated global metadata index for skills
  24. ├── skills_sources.json # Data sources configuration for `oah sync` command
  25. ├── README.md # English documentation (this file)
  26. └── README.zh-CN.md # Chinese translation documentation
  27. ```
  28. *(Note: `AGENTS.md`, `CLAUDE.md`, and `GEMINI.md` contain project-level LLM coding behavioral guidelines, derived from [andrej-karpathy-skills](https://github.com/multica-ai/andrej-karpathy-skills))*
  29. ---
  30. ## 📖 Technical Guidelines & Documentation
  31. To maintain clean and focused documentation, deep-dive specifications have been moved under the `docs/` directory. Please refer to:
  32. * 🧩 **[Skill Guidelines](docs/Skill_Guidelines.md)**: Design standards, trigger rules, and a complete catalog of the 83+ modular skills.
  33. * 🤖 **[Agent Guidelines](docs/Agent_Guidelines.md)**: Specifications for Orchestrator, Evaluator, and Optimizer agent roles, detailing handoff contracts and Evaluator-Optimizer loops.
  34. * 🛠 **[Command Guidelines](docs/Command_Guidelines.md)**: Guidelines for agent-facing slash commands (such as `/commit`, `/review`, and `/test-tdd`).
  35. ---
  36. ## 🔌 Compatibility
  37. `open-agent-hub` follows standardized Markdown prompts with YAML frontmatter metadata. The CLI dynamically links components (Skills, Agents, Commands) to their respective subdirectories (`/skills/`, `/agents/`, `/commands/`) within the project or global configuration directories of the AI assistant:
  38. | Tool Name (Agent) | Type | Compatibility | Project Path (Workspace) | Global Path (System) |
  39. | :--- | :--- | :--- | :--- | :--- |
  40. | **Claude Code** | CLI | ✅ Full | `.claude/` | `~/.claude/` |
  41. | **Antigravity** | IDE | ✅ Full | `.agents/` | `~/.gemini/antigravity/` |
  42. | **Gemini CLI** | CLI | ✅ Full | `.gemini/` | `~/.gemini/` |
  43. | **Codex** | CLI | ✅ Full | `.codex/` | `~/.codex/` |
  44. | **Cursor** | IDE | ✅ Full | `.cursor/` | `~/.cursor/` |
  45. | **Trae** | IDE | ✅ Full | `.trae/` | `~/.trae/` |
  46. | **OpenCode** | CLI | ✅ Full | `.opencode/` | `~/.config/opencode/` |
  47. | **Kiro** | CLI/Agent | ✅ Full | `.kiro/` | `~/.kiro/` |
  48. > [!TIP]
  49. > The CLI tool (`oah`) links files into subdirectories under these paths, e.g., `<Path>/skills/` for skills, `<Path>/agents/` for agents, and `<Path>/commands/` for slash commands. In addition to directory linking, native plugin configurations are provided for Claude Code (`.claude-plugin/`), Codex (`.codex-plugin/`), and Cursor (`.cursor-plugin/`).
  50. ---
  51. ## 🚀 Quick Start
  52. You can install and manage skills either directly using Vercel's standard `skills` CLI, or via our built-in zero-dependency manager (`oah`) which also supports managing Agents and Slash Commands.
  53. ### Option 1: Quick Install via Vercel's `skills` CLI (Easiest)
  54. If you only need to use the modular **Skills** and are using a compatible agent (like Claude Code, Cursor, etc.), you can use Vercel's official `skills` CLI to install them directly from this repository without cloning:
  55. ```bash
  56. # Add all skills from this repository
  57. npx skills@latest add guanyang/open-agent-hub
  58. # Add a specific skill (e.g., remotion)
  59. npx skills@latest add guanyang/open-agent-hub --skill remotion
  60. ```
  61. ### Option 2: Clone and use the built-in CLI (`oah`)
  62. If you want to manage **Skills, Agents, and Slash Commands** dynamically via local symlinks, or if you want to sync upstream sources, you can clone the repository and use our CLI tool:
  63. #### 1. Clone the Hub
  64. Clone this repository locally (it is recommended to place it in a fixed location for global reference):
  65. ```bash
  66. git clone https://github.com/guanyang/open-agent-hub.git ~/open-agent-hub
  67. ```
  68. #### 2. Global Link via CLI
  69. In the root directory, run the link command to register the CLI manager `open-agent` (with aliases `open-agent-hub`, `oah`, `ahub`):
  70. ```bash
  71. cd ~/open-agent-hub
  72. npm link
  73. ```
  74. #### 3. Manage Capabilities
  75. After linking, you can manage your local agent environments from anywhere:
  76. ```bash
  77. # List all dynamically scanned Skills, Agents, and Commands
  78. oah list
  79. # Check link status in your current project workspace (default behavior)
  80. oah status
  81. # Check link status in global system configurations (e.g. ~/.claude/)
  82. oah status --global
  83. # Enable a specific component inside the current project workspace
  84. oah enable canvas-design
  85. # Enable all components (Skills, Agents, Commands) in current project workspace (defaults to all)
  86. oah enable
  87. # Enable all components in project workspace for Cursor (links to .cursor/)
  88. oah enable --target=cursor
  89. # Enable all components in project workspace for ALL supported targets
  90. oah enable --target=all
  91. # Enable all components globally for ALL supported targets
  92. oah enable --global --target=all
  93. # Enable all components globally (system-level)
  94. oah enable --global
  95. # Enable all components in a custom target directory (auto-creates subdirectories dynamically)
  96. oah enable --path=/path/to/my_agent_dir
  97. # Disable all components inside the current project workspace
  98. oah disable
  99. ```
  100. #### CLI Filters & Options:
  101. * **Filters (Passed as the name argument, mutually exclusive):**
  102. * `<name>`: Enable/disable a single component by its name/ID.
  103. * `--skills`: Enable/disable only all Skills components.
  104. * `--agents`: Enable/disable only all Agents components.
  105. * `--commands`: Enable/disable only all Commands components.
  106. * `--all`, `-a`: Enable/disable all Skills, Agents, and Commands (default behavior when no arguments are provided).
  107. * **Options:**
  108. * `-p, --project` (default): Project-level activation (links config directories inside your current working directory, e.g. `.claude/`).
  109. * `-g, --global`: System global level activation (e.g., links into user home config folder, like `~/.claude/`).
  110. * `-t, --target <name>`: Target environment to link to (supported: `claude`, `antigravity`, `gemini`, `codex`, `cursor`, `trae`, `opencode`, `kiro` and `all` to configure all of them, default: `claude`).
  111. * `--path <dir_path>`: Custom base directory to link components into (creates and links within `skills/`, `agents/`, and `commands/` subdirectories automatically).
  112. ## 🔄 Keeping Skills in Sync
  113. Many modular skills in the `skills/` directory originate from active open-source communities. You can sync them with upstream sources using the CLI or the underlying script:
  114. ```bash
  115. # Sync all configured sources
  116. oah sync
  117. # Sync only a specific source (e.g., anthropics-skills)
  118. oah sync anthropics-skills
  119. ```
  120. *Note: Configured upstream sources are stored in `skills_sources.json`. You can also execute this directly via `./scripts/sync_skills.sh`.*
  121. ---
  122. ## 🛡️ Security & Contributing
  123. * **Security Policy**: Please refer to [SECURITY.md](SECURITY.md) to report vulnerabilities.
  124. * **Contributing**: We welcome community contributions for new skills, agents, or commands. See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
  125. ---
  126. ## 📄 License
  127. This project is licensed under the [MIT License](LICENSE).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.