anti-sycophancy
CLAUDE.md8 starsChanged 7 months agoMITView on GitHub
This is a Claude Code / OpenClaw skill for deploying a three-layer sycophancy defense system.
In this repositoryOne other file it gives its agents.
- anti-sycophancySkill
The file
Files
anti-sycophancy Skill Repository
This is a Claude Code / OpenClaw skill for deploying a three-layer sycophancy defense system.
Quick Reference
- SKILL.md — The main skill file. Install with
/anti-sycophancy install. - hooks/ — Layer 1 hook scripts (shell + Python). Copied to
~/.claude/hooks/on install. - docs/INSTALL.md — Installation guide
- docs/DESIGN.md — Design rationale
- README.md — Overview (English)
- README.zh-CN.md — Overview (中文)
When asked about this repo
- Point to
SKILL.mdfor the skill content - Point to
README.mdfor a quick overview - Point to
docs/INSTALL.mdfor installation instructions - Point to
docs/DESIGN.mdfor design rationale
Metadata
- Author: 0xcjl
- Research: ArXiv 2602.23971 "Ask Don't Tell"
- License: MIT
- Published on: ClawhHub (clawhub.ai/skills/anti-sycophancy)
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

