Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Opengui Plugin Install

ASecurity

Install or upgrade the standalone OpenGUI Codex or WorkBuddy plugin on macOS from verified prebuilt GitHub releases. Use for plugin installation, not phone actions or DSH installation.

1,800 stars
0 votes
0 copies
0 views
Added 9/20/2026
ai-agentsrustbashnodetestinggitapi

Works with

cliapimcp

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add Core-Mate/OpenGUI --skill opengui-plugin-install --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Opengui Plugin Install?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Opengui Plugin Install
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/core-mate-opengui-plugin-install/badge)](https://www.skillsdirectory.com/skills/core-mate-opengui-plugin-install)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: opengui-plugin-install
description: Install or upgrade the standalone OpenGUI Codex or WorkBuddy plugin on macOS from verified prebuilt GitHub releases. Use for plugin installation, not phone actions or DSH installation.
---

# OpenGUI plugin installation

Infer Codex or WorkBuddy from the request; ask only if the target is missing. The two plugins have independent versions and installation directories. Do not install both unless requested.

1. Read the public GitHub releases API for `Core-Mate/OpenGUI`, following pagination. Select the newest non-draft, non-prerelease semantic version with tag `opengui-codex-vX.Y.Z` or `opengui-workbuddy-vX.Y.Z` and all matching assets below. If the user explicitly asks for the public testing/prerelease version, include non-draft prereleases for that host and explain their uncompleted device acceptance. An explicit requested version takes precedence; never silently substitute a different version. Do not use the repository-wide latest release, which may be DSH or an APK.
2. Download `opengui-HOST-X.Y.Z-install.command` and its `.sha256` asset from that release into a fresh temporary directory. Use HTTPS with redirect-to-HTTPS only. Require exact filenames and verify SHA-256 before executing the installer. The checksum establishes integrity relative to the selected public release, not an independent publisher signature.
3. Finish existing OpenGUI phone tasks before an upgrade. WorkBuddy 5.5.6 or newer may stay open; never kill it or its phone/mirror processes. Older compatible WorkBuddy versions require a normal Command-Q restart when the installer reports `HOST_RESTART_REQUIRED`. Codex requires the native CLI with `codex plugin` support. Never remove a conflicting plugin source without the user's authorization.
4. For WorkBuddy, run the selected installer with `--check` first. Read its exact error code; do not inspect the entire application or rewrite configuration manually. Multiple applications require an explicit `--app` selection. When invoked inside WorkBuddy 5.5.6+, run `bash /absolute/path/opengui-HOST-X.Y.Z-install.command` directly in the current task after the preflight passes. It downloads and verifies the matching package, prepares private Node 22.23.2, installs into a fresh version directory, and atomically configures only the selected host. If an upgrade reports `upgrade_blocked`, finish and close the old OpenGUI task/viewer/mirror, disable OpenGUI in MCP service management, wait for its broker to exit, then retry once. No Git clone, pnpm, source compilation, agent-written JSON, or user-run test suite is required.
5. Read the result. After `LIVE_CONFIG_WRITTEN`, keep WorkBuddy open: trust/enable the OpenGUI MCP if prompted, open `/hooks` to review and apply the external Hook change, and open `/skills` to confirm `opengui`. Start a new task only if the current task does not refresh. After a stopped-host installation, open WorkBuddy and perform the same checks. Verify read-only device discovery before phone actions. USB and system permissions remain user actions. Installation success does not prove phone control, desktop visibility, or two-device acceptance.

Required release assets:
- Codex: `opengui-codex-X.Y.Z.tar.gz`, its `.sha256`, and the installer plus its `.sha256`.
- WorkBuddy: `opengui-mcp-X.Y.Z.tgz`, its `.sha256`, and the installer plus its `.sha256`.

If no complete release exists or downloads fail, report that precise state. Do not replace the installer with source builds or invent a working download link. For explicitly requested candidate testing, use a maintainer-provided archive with its adjacent checksum and the matching source installer: `bash install-macos.command --archive /absolute/package.tar.gz` (WorkBuddy uses `.tgz`). Keep candidate and published status separate.

Rollback uses the previous version's verified installer after tasks end. WorkBuddy also records scoped configuration backups in `~/.workbuddy/opengui/local-install-<configuration-id>.json`; Codex retains previous inventories and a configuration backup beside each immutable package. Preserve subsequent unrelated edits when recovering; do not reset an entire host or touch DSH.

Attribution

Core-MateCore-Mate
View sourceMore from Core-Mate →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

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 (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →