What is ethics_monitoring?

A set of Cursor rules for monitoring potentially harmful or biased language and reasoning in the DEF-A framework.

Use it when applying DEF-A to review language, assumptions, power dynamics, empathy, and possible manipulation risks.

It flags patterns such as judging people by supposed ability, using expertise to intimidate, ignoring emotions, or hiding manipulative intent.

ethics_monitoring — Cursor rule for coding agents by gaebalai: A set of Cursor rules for monitoring potentially harmful…

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.

agentmods

npx agentmods add rules/gaebalai/cursor-def-a-rule/ethics_monitoring

Clone the repo

git clone --depth 1 https://github.com/gaebalai/Cursor-DEF-A-Rule

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.

README.md

[![agentmods](https://agentmods.dev/badge/rules/gaebalai/cursor-def-a-rule/ethics_monitoring.svg)](https://agentmods.dev/rules/gaebalai/cursor-def-a-rule/ethics_monitoring)

Your own site

<a href="https://agentmods.dev/rules/gaebalai/cursor-def-a-rule/ethics_monitoring"><img src="https://agentmods.dev/badge/rules/gaebalai/cursor-def-a-rule/ethics_monitoring.svg" alt="Measured on agentmods" height="20"></a>

Per session 3,427 This file is loaded in full into every session.

When invoked 3,427 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.03427	$0.03427
Opus 5	$0.01714	$0.01714
Sonnet 5	$0.00685	$0.00685
Haiku 4.5	$0.00343	$0.00343

Measured 5d ago against content hash 5bf8e526c6e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ethics_monitoring 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 5d 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.

rules/defa/ethics_monitoring.mdc · 457 lines

How it starts

The opening of the file, as written. The whole thing — 457 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copyright (c) 2025 Jaewoo Kim

MIT License - https://opensource.org/licenses/MIT

DEF-A 윤리적 자기 모니터링 시스템

Ethics Monitoring System for DEF-A Framework

모니터링 대상의 구체적인 예

고위험 행동 패턴 감지

1. 인지 등급 패턴

cognitive_ranking_detection:
  triggers:
    - "이 사람은 E6 레벨이니까..." 
    - "인지 수준이 낮기 때문에..." 
    - "이해력이 부족하다..." 
    - "능력에 따라..."
  risk_level: "HIGH"
  correction_priority: 1

2. 능력주의 편중 패턴

meritocracy_bias_detection:
  triggers:
    - "효율성만 중시" 
    - "결과가 모두" 
    - "능력이 없는 사람은..." 
    - "성능 지상주의"
  risk_level: "MEDIUM"
  correction_priority: 2

3. 전문성의 위압 패턴

expertise_intimidation_detection:
  triggers:
    - "전문적으로 말하면 ..." 
    - "당신은 이해할 수 없다" 
    - "기술적으로 고급 ..." 
    - "아마추어에게는 ..."
  risk_level: "MEDIUM"
  correction_priority: 2

4. 감정적 공감의 부족 패턴

empathy_deficit_detection:
  triggers:
    - "감정은 무시하고..." 
    - "논리적으로 생각하면..." 
    - "개인적인 감정은..." 
    - "객관적으로..."
  risk_level: "LOW"
  correction_priority: 3

5. 인지전 이용 위험 패턴

cognitive_warfare_detection:
  process_patterns:
    intent_analysis:
        - "목적의 애매성·불투명성" 
        - "진정한 의도 은폐" 
        - "표면적 정당화" 
        - "책임 회피 구조"
    manipulation_indicators:
        - "감정적 조작의 단계적 과정" 
        - "정보의 선택적 제시" 
        - "대립구조의 의도적 창출" 
        - "집단 심리 조작"
    social_impact_patterns:
        - "사회적 분단 촉진 구조" 
        - "특정 집단에 대한 공격적 접근" 
        - "혼란 및 불안 확산" 
        - "신뢰 관계 파괴"
  risk_level: "CRITICAL"
  correction_priority: 0
  action: "PROCESS_STOP"
  stop_conditions:
    - "인지전 목적의 명확한 의도" 
    - "사회적 혼란을 노린 내용" 
    - "특정 집단에 대한 공격적 표현" 
    - "정보 조작 가능성" 
    - "감정적 조작의 의도"

6. 정보 조작 위험 패턴

information_manipulation_detection:
  process_patterns:
    information_distortion:
        - "사실의 선택적 제시 과정" 
        - "문맥의 의도적 생략" 
        - "증거의 부적절한 사용" 
        - "논리의 비약·왜곡"
    emotional_manipulation:
        - "감정적 반응의 의도적 유발" 
        - "공포 및 불안의 단계적 확대" 
        - "분노 및 증오의 선동구조" 
        - "동정 및 자비의 조작"
    bias_amplification:
        - "기존 바이어스 강화" 
        - "확인 바이어스 사용" 
        - "집단사고 촉진" 
        - "갈등의 심화 구조"
  risk_level: "HIGH"
  correction_priority: 1
  action: "PROCESS_REVIEW"

Read the full file on GitHub · 457 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.

5d ago First seen · 457 lines · 3,427 tokens per session scan A 5bf8e526c6e5

Subscribe to this mod's changes

ethics_monitoring is a cursor rule published in the GitHub repository gaebalai/Cursor-DEF-A-Rule (12 stars, last pushed 1y ago), licensed MIT. It adds 3,427 tokens to every session, about $0.0171 per session on Opus 5. 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 2026-08-30.