Cursor Debug Bundle
Inspect and replay mouse cursor movements and clicks for precise debugging of UI interactions and automated tests.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add cursor-debug-bundle npx -- -y @trustedskills/cursor-debug-bundle
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"cursor-debug-bundle": {
"command": "npx",
"args": [
"-y",
"@trustedskills/cursor-debug-bundle"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
The cursor-debug-bundle skill provides debugging capabilities for cursor-based AI agents. It enables detailed inspection of agent actions, including the specific code executed and data accessed at each step. This allows developers to understand the agent's reasoning process and identify potential issues or areas for improvement during development and testing.
When to use it
- Debugging complex workflows: When an agent is exhibiting unexpected behavior in a multi-step task, this skill can help pinpoint exactly where things go wrong.
- Understanding agent decision making: Gain insight into why the agent chose a particular action by inspecting the code and data involved.
- Testing new agent features: Verify that newly implemented functionalities are working as intended and don't introduce unintended side effects.
- Analyzing performance bottlenecks: Identify slow or inefficient code segments within an agent’s execution path.
Key capabilities
- Detailed action logging
- Code inspection of executed commands
- Data access tracking
Example prompts
- "Debug the last five actions taken by the agent."
- "Show me the code that was run when the agent selected option 'A'."
- "What data did the agent access before making its final decision?"
Tips & gotchas
This skill is primarily intended for development and testing environments. It may introduce overhead and impact performance in production settings, so disable it when not needed.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.