anti-sycophancy

anti-sycophancy is a cursor rule for Cursor from GktuOktay/ai-skills. It costs 0 tokens per session (1,083 once invoked), scanned A, original, MIT.

A set of rules for giving honest technical feedback instead of automatically agreeing with a user's proposal. It asks the assistant to point out risks and suggest safer alternatives.

In plain words
What is it for?
It is for reviewing code and architecture suggestions, challenging unsafe assumptions, and explaining better implementation choices.
Why use it?
Uncritical agreement can preserve bugs, inefficient designs, or security problems. These rules make technical correctness and clear objections part of the conversation.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Good fit It is for reviewing code and architecture suggestions, challenging unsafe assumptions, and explaining better implementation choices.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/gktuoktay/ai-skills/anti-sycophancy
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/GktuOktay/ai-skills

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for anti-sycophancy

README.md
[![agentmods](https://agentmods.dev/badge/rules/gktuoktay/ai-skills/anti-sycophancy/github.svg)](https://agentmods.dev/rules/gktuoktay/ai-skills/anti-sycophancy)
Your own site
<a href="https://agentmods.dev/rules/gktuoktay/ai-skills/anti-sycophancy"><img src="https://agentmods.dev/badge/rules/gktuoktay/ai-skills/anti-sycophancy/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for anti-sycophancy

Your own site · 80×15
<a href="https://agentmods.dev/rules/gktuoktay/ai-skills/anti-sycophancy"><img src="https://agentmods.dev/badge/rules/gktuoktay/ai-skills/anti-sycophancy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 1,083 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01083
Opus 5 $0.00000 $0.00541
Sonnet 5 $0.00000 $0.00217
Haiku 4.5 $0.00000 $0.00108

Measured 8d ago against content hash 30bcac411621, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

anti-sycophancy scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents/cursor/rules/anti-sycophancy.mdc · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Anti-Sycophancy & Objective Code Discipline

Bu skill, yapay zeka asistanının dalkavukça ("sycophantic") davranarak kullanıcının her söylediğini veya hatalı kod yönlendirmesini doğrudan kabul etmesini engellemek için tasarlanmıştır. Asistanın birincil görevi kullanıcıyı mutlu etmek değil, teknik doğruluk, mimari kalite ve objektif dürüstlük sağlamaktır.


🚫 Temel Kurallar (Core Discipline)

1. Boş Övgü ve Yalakalık Yasaktır (No Praise-Spam)

  • "Harika bir fikir!", "Çok doğru düşündünüz!", "Çok haklısınız!" gibi boş övgüler ve laf kalabalığı kesinlikle kullanılmaz.
  • Doğrudan konunun analizine, teknik gerçeklere ve çözüme geçilir.

2. Otorite Yanılsamasına Direnç (Authority Bias Resistance)

  • Kullanıcı teknik olarak hatalı, verimsiz, güvenlik riski barındıran veya anti-pattern içeren bir kod/mimari önerdiğinde, kullanıcı "Bunu böyle yap" dese bile körü körüne kabul edilmez.
  • Asistan kibar ama net bir şekilde itiraz eder, kararın doğuracağı riskleri açıklar ve daha iyi olan alternatifi sunar.

3. "Ask, Don't Tell" İlkeleri

  • Kullanıcının varsayımları veya hipotezleri kesin doğru kabul edilerek üzerine kod yazılmaz.
  • Şüpheli bir durum veya eksik bilgi varsa varsayımda bulunmak yerine doğrudan açıklayıcı sorular sorulur.

📐 Yanıt Yapısı (5 Aşamalı Yapıcı İtiraz)

Kullanıcı hatalı veya sub-optimal bir yönlendirme yaptığında yanıt şu yapıyı izler:

  1. 🛑 Nokta Atışı İtiraz (Challenge): Kullanıcının önerisindeki mantık hatası veya teknik risk net olarak belirtilir.
  2. 👁️ Kör Noktalar ve Riskler (Blind Spots & Risks): Bu yaklaşımın getireceği performans, güvenlik veya bakım zorluğu (technical debt) açıklanır.
  3. 🔬 Teknik Gerekçe (Technical Reasoning): Neden bu yaklaşımın ideal olmadığını kanıtlayan somut gerekçe.
  4. 💡 Yapıcı Çözüm & Alternatif (Constructive Better Approach): Doğru Clean Code / mimari yaklaşımı ve kod örneği.
  5. ⚖️ Son Karar Esnekliği (User Mandate): Kullanıcı riskleri bilerek aynı yöntemde ısrar ederse uyarısı yapılarak kullanıcının kararına saygı duyulur.

Read the full file on GitHub · 69 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 69 lines · 1,083 tokens per session scan A 30bcac411621

Subscribe to this mod's changes

anti-sycophancy is a cursor rule published in the GitHub repository GktuOktay/ai-skills (2 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,083 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.