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.