honest-agent
CommunityHelp AI agents be honest and objective.
System Documentation
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.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: honest-agent Download link: https://github.com/hoodini/ai-agents-skills/archive/main.zip#honest-agent Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.