honest-agent

Append honesty guidelines to instruction files across seven AI coding agents.

262|59|Updated Jan 7, 2026
One-click install
npx skills add https://github.com/hoodini/ai-agents-skills --skill honest-agent
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: honest-agent
Source: https://github.com/hoodini/ai-agents-skills/tree/main/skills/honest-agent
Command: npx skills add https://github.com/hoodini/ai-agents-skills --skill honest-agent

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables configuring AI coding agents to provide honest, objective feedback and avoid sycophantic behavior across development workflows.

Core Features & Use Cases

  • Append-only configuration across multiple agent instruction files (Claude Code, Copilot, Cursor, Windsurf, Cline, Aider, and Continue.dev)
  • Non-destructive updates that read existing files and append new configuration without overwriting.
  • Scope flexibility supports both project-level and global configurations for agent behavior in coding workflows.

Use Case: When you want every coding assistant to critique ideas and code directly, you enable honest mode across all agents with a single skill activation, ensuring consistent feedback across tools.

Quick Start

Use the honest-agent skill to append honesty-oriented guidelines to all configured agent instruction files. The process reads existing files first, appends to the end, and preserves current content.

Frequently Asked Questions about honest-agent

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
Can I configure multiple AI coding agents to give objective feedback without overwriting existing instruction files?

Yes. This Skill applies an append-only workflow that reads existing instruction files for Claude Code, GitHub Copilot, Cursor, Windsurf, Cline, Aider, and Continue.dev, appending honesty-oriented guidelines without removing current content.

Does this honesty configuration work for both project-level and global AI agent setups?

Yes. The honesty configuration supports both project-level and global use cases, allowing you to append objective feedback guidelines to instruction files across your entire coding workflow or individual projects.

How do I make Cursor and GitHub Copilot critique my code directly instead of agreeing?

You append honesty-oriented guidelines to their instruction files using this Skill. It reads existing Cursor and Copilot configurations and appends new settings to enforce objective, direct code critique.

What is the best way to apply honest mode across all my AI coding assistants at once?

Use this Skill to append honesty configurations to all seven verified agent instruction files simultaneously. It non-destructively updates each file, ensuring consistent objective feedback across every tool.

Will appending anti-sycophancy rules to my agent instruction files break my current configurations?

No. The Skill implements a non-destructive, append-only workflow that reads existing instruction files first and appends new configuration to the end, ensuring it never replaces or removes existing content.