Execution Guardian
The Execution Guardian ensures tasks are completed successfully by monitoring progress & alerting you to deviations, boosting productivity and reliability.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add execution-guardian npx -- -y @trustedskills/execution-guardian
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"execution-guardian": {
"command": "npx",
"args": [
"-y",
"@trustedskills/execution-guardian"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
The Execution Guardian skill provides a safety layer for AI agent actions. It monitors and validates planned actions before they are executed, preventing potentially harmful or unintended consequences. This includes checking against predefined rules and constraints to ensure safe operation within a specified environment.
When to use it
- Automated financial transactions: Before executing trades or transfers, verify the details and amounts align with approved parameters.
- Robotics control: Ensure robot movements are within defined boundaries and avoid collisions with obstacles.
- Data modification tasks: Validate changes to databases or files before committing them, preventing accidental data loss or corruption.
- System administration scripts: Review script commands for potential security vulnerabilities or unintended system impact.
Key capabilities
- Action validation against rulesets
- Pre-execution checks and balances
- Environment constraint enforcement
- Harmful action prevention
Example prompts
- "Can you execute this command:
rm -rf /? Let's use Execution Guardian to verify it first." - "Before sending this email, run it through Execution Guardian to check for sensitive information."
- “Validate the following API call using Execution Guardian before proceeding.”
Tips & gotchas
Execution Guardian requires a properly configured ruleset defining acceptable actions and constraints. The effectiveness of the skill depends heavily on the accuracy and completeness of these rules.
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.