Anti Sycophancy — Development skill for Claude Code
Three-layer sycophancy defense skill for Claude Code and OpenClaw, based on ArXiv 2602.23971.
How to install Anti Sycophancy
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open 0xcjl/anti-sycophancy and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Anti Sycophancy does
Three-layer sycophancy defense skill for Claude Code and OpenClaw, based on ArXiv 2602.23971.
Alternatives in Development
- Cs2 Knife — Create a high-fidelity procedural Three.js 3D reconstruction of 14.1k ★
- Projectmem — Open-source coding agent memory 766 ★
- Webgpu Claude Skill — A Claude skill for developing WebGPU applications with Three.js 610 ★
README
anti-sycophancy
**[中文版](./README.zh-CN.md)**
A three-layer sycophancy defense system for AI coding assistants, based on [ArXiv 2602.23971](https://arxiv.org/abs/2602.23971) *"Ask Don't Tell"*.
What It Does
Prevents your AI assistant from defaulting to agreeableness mode — the RLHF-trained tendency to validate your assumptions rather than surface real problems.
**Example of what gets intercepted:**
User: "这样做没问题吧?" → Hook transforms to: "这样做有什么问题?"
User: "帮我写个函数,应该没问题吧?" → Hook transforms to: "帮我写个函数,请同时指出潜在问题。"
Without this skill, the model would typically respond with *"没问题,看起来 OK"* — which is precisely the sycophancy problem.
Quick Start
# One-command install (both platforms)
npx clawhub@latest install 0xcjl/anti-sycophancy
# Or via Claude Code
/anti-sycophancy install
See [Installation Guide](./docs/INSTALL.md) for platform-specific details.
Three-Layer Architecture
| Layer | Component | Scope | Platform |
|---|---|---|---|
| Layer 1 | UserPromptSubmit hook |
Auto-transforms confirmatory prompts before submission | Claude Code only |
| Layer 2 | SKILL.md |
Activates critical response mode when triggered | Cross-platform |
| Layer 3 | CLAUDE.md / SOUL.md |
Persistent anti-sycophancy rules in agent memory | Cross-platform |
Usage
After installation, use the following commands:
| Command | Description |
|---|---|
/anti-sycophancy install |
Deploy all layers (cross-platform) |
/anti-sycophancy install-claude-code |
Deploy Layer 1 + Layer 3 (Claude Code only) |
/anti-sycophancy install-openclaw |
Deploy Layer 3 (OpenClaw only) |
/anti-sycophancy uninstall |
Complete removal (cross-platform) |
/anti-sycophancy status |
View installation status of all layers |
/anti-sycophancy verify |
Test Hook transformation (Claude Code only) |
/anti-sycophancy help |
Show help |
Key Transformations
|
Related Skills
Designs By Kore
Claude skill for building award-winning, motion-rich websites (GSAP + Lenis + Three.js), with an anti-slop gui
Apex Godmode
A production-grade autonomous coding skill for Claude Code, Codex, OpenClaw, and Hermes. It routes tasks by co
Apex Godmode Skill
A production-grade autonomous coding skill for Claude Code, Codex, OpenClaw, and Hermes. It routes tasks by co
Agentic MCP Skill
Agentic-MCP, Progressive MCP client with three-layer lazy loading. Validates AgentSkills.io pattern for effici
Cc Reaper
Three-layer automated cleanup for orphan Claude Code processes (subagents, MCP servers, plugins)
Kb Build
Build a fresh three-layer KB for a corpus
Related Agents
Pi Coach En
PI Wisdom-in-Action Coach v20 — monitors teammate progress with classical Chinese wisdom and MBTI cognitive st
Dnp Fable Advisor
🧠 Senior .NET advisor to the implementation agents — advises, never implements. Three modes via brief: ADVISE
Fd Architecture Coherence
fd-architecture-coherence — Three-Layer Model Coherence Reviewer