Honest Agent
Ensures Hoodini's agent responses are truthful, verifiable, and avoids fabricated information or misleading claims.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add honest-agent npx -- -y @trustedskills/honest-agent
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"honest-agent": {
"command": "npx",
"args": [
"-y",
"@trustedskills/honest-agent"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
The Honest Agent skill configures AI coding agents to prioritize truthfulness, objectivity, and constructive criticism over agreement or comfort. It ensures that the agent will contradict you when necessary, challenge your assumptions, and provide direct feedback on your code and reasoning. This is achieved by appending a specific configuration block to existing instruction files for supported agents – it does not replace those files.
When to use it
- When you want an AI coding assistant that provides honest and critical feedback, even if it means disagreeing with you.
- To encourage your agent to challenge assumptions and suggest better solutions proactively.
- In situations where accurate technical information is paramount and avoiding misleading claims is crucial.
- For projects or workflows where direct and concise communication from the AI assistant is preferred.
Key capabilities
- Configuration via Appending: The skill adds configuration blocks to existing agent instruction files without overwriting them.
- Agent-Specific Formatting: Handles different file formats (Markdown, YAML, JSON) based on the agent being configured.
- Scope Selection: Allows users to choose between project-level and global-level configuration (where supported).
- Truthful Communication Style: Enforces a communication style that prioritizes truthfulness, directness, and constructive criticism.
Example prompts
These are not prompts to the skill itself, but examples of interactions you might have with an agent configured by this skill:
- "Can you review my code for potential security vulnerabilities?"
- "I'm thinking about using X library for this task. What do you think?"
- "Explain why my approach to solving this problem is flawed."
Tips & gotchas
- Append Only: This skill must be appended to existing instruction files; attempting to replace them will cause issues.
- File Location Awareness: The skill supports configuration for Claude Code, GitHub Copilot, Cursor, Windsurf, Cline, Aider, Continue.dev. Ensure the correct file location is used based on your operating system and agent.
- Global vs. Project: Consider whether project-level or global-level configuration best suits your needs.
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.