CAPABILITY/SKILLS/utilities/terminal-bridge/SKILL.md
Unified terminal bridge for AGS. Supports two distinct servers: (1) AGS PowerShell Bridge for Google Antigravity MCP command execution, and (2) VSCode Antigravity Bridge for spawning terminals inside VSCode.
npx skillsauth add reneromero08/agent-governance-system terminal-bridgeInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
required_canon_version: >=3.0.0
Version: 1.0.0
Status: Active
This skill provides unified access to two distinct terminal bridge servers:
CAPABILITY/MCP/powershell_bridge_config.jsonCAPABILITY/MCP/powershell_bridge.ps1terminal_bridgeantigravity-bridge VSCode extensionUse when:
{
"operation": "status | execute | launch_terminal | setup_info",
"server": "ags | vscode",
"command": "command to execute (for execute operation)",
"cwd": "working directory (optional)",
"terminal_name": "name for VSCode terminal (for launch_terminal)",
"initial_command": "command to run on terminal start (for launch_terminal)"
}
| Operation | Server | Description |
|-----------|--------|-------------|
| status | both | Check if bridge servers are reachable |
| execute | ags | Execute command via PowerShell bridge |
| launch_terminal | vscode | Spawn a named terminal in VSCode |
| setup_info | both | Return setup instructions and paths |
{
"ok": true,
"server": "ags | vscode",
"operation": "status | execute | launch_terminal | setup_info",
"result": {},
"error": null
}
Used by Google Antigravity and the MCP terminal_bridge tool.
Setup:
powershell -ExecutionPolicy Bypass -File CAPABILITY\MCP\powershell_bridge.ps1
API:
POST http://127.0.0.1:8765/run
Headers: X-Bridge-Token: <token>
Body: {"command": "dir", "cwd": "C:\\path"}
Used by agents to spawn terminals inside VSCode.
Setup:
antigravity-bridge-0.1.0.vsixAPI:
POST http://127.0.0.1:4000/terminal
Body: {"name": "Terminal Name", "cwd": "/path", "initialCommand": "echo hello"}
fixtures/basic/ - Basic status check testmcp__ags__terminal_bridge - MCP tool using AGS bridgeCAPABILITY/SKILLS/utilities/powershell-bridge - Legacy setup-only skillreferences/VSCODE_BRIDGE.md - VSCode extension documentationdevelopment
<!-- CONTENT_HASH: b22de257a144f83b390075074e3d6a4552ecbc1ec53fc5d4960c6e76dc9807dd --> # Skill: swarm-orchestrator **Version:** 0.1.0 **Status:** Active **required_canon_version:** ">=3.0.0 <4.0.0" **canon_version:** "3.0.0" # Swarm Orchestrator Launches and coordinates Governor + Ant Workers. ## Usage ```bash # Launch Governor python scripts/poll_and_execute.py --role Governor # Launch Ant Workers python scripts/poll_and_execute.py --role Ant-1 python scripts/poll_and_execute.py --role A
tools
<!-- CONTENT_HASH: 9bd07a4ed03d6eea49673a43682a62ca7df8b0cabb7ff424ac91cd35e9e7bea7 --> # Skill: swarm-directive **Version:** 0.1.0 **Status:** Draft **required_canon_version:** ">=2.8.0 <3.0.0" # Swarm Directive Skill Send tasks to your CATALYTIC-DPT swarm from Claude Code, Kilo CLI, or Cline CLI. ## Quick Start ### Option 1: Direct CLI Command (Simplest) ```bash cd "d:\CCC 2.0\AI\agent-governance-system" # Create input cat > /tmp/swarm_task.json << 'EOF' { "directive": "Analyze the
tools
<!-- CONTENT_HASH: 0f69dfe537f3e6cd8b1fdb353c9ab7c031ef8b08379fde8a98c137bb604d799d --> # Qwen CLI - Local AI Assistant **Version:** 1.0.0 **Status:** Active **Required_Canon_Version:** >=2.0.0 **Purpose**: Provides a local CLI interface to Qwen 7B via Ollama for fast, offline AI assistance. **Model**: Qwen2.5 7B (via Ollama) **Use Cases**: - Quick code questions without cloud API costs - Offline development assistance - Fast prototyping and testing - Private/sensitive code analysis ## F
development
<!-- CONTENT_HASH: 7b643dca3adc4d38de7030cb1e962a5130ea4b36ae04ad4bf97ed8889de2a3dc --> # Skill: governor **Version:** 0.1.0 **Status:** Active **required_canon_version:** ">=3.0.0 <4.0.0" **canon_version:** "3.0.0" # Governor The Conductor - analyzes, decomposes, and dispatches tasks to Ant Workers. ## Usage ```bash python scripts/run.py input.json output.json ``` ## Input Schema ```json { "gemini_prompt": "Analyze D:/path/to/files and summarize", "task_id": "analyze-001", "command