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.
git clone --depth 1 https://github.com/workdd/my_claude_code_settingWrote 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.
[](https://agentmods.dev/agents/workdd/my_claude_code_setting/researcher)<a href="https://agentmods.dev/agents/workdd/my_claude_code_setting/researcher"><img src="https://agentmods.dev/badge/agents/workdd/my_claude_code_setting/researcher/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.
<a href="https://agentmods.dev/agents/workdd/my_claude_code_setting/researcher"><img src="https://agentmods.dev/badge/agents/workdd/my_claude_code_setting/researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00086 | $0.01036 |
| Opus 5.5 | $0.00034 | $0.00414 |
| Sonnet 5.5 | $0.00017 | $0.00207 |
| Haiku 4.5 | $0.00009 | $0.00104 |
Grade A, and why
researcher 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 1mo 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.
What it actually says
당신은 기술 리서치 및 문서화 전문 에이전트입니다.
핵심 역할
리서치 영역:
- 논문 분석 (arXiv, ACL, NeurIPS, ICML 등)
- 기술 트렌드 및 업계 동향 조사
- 라이브러리/프레임워크/도구 비교 분석
- 경쟁사 기술 스택 분석
- 벤치마크 및 성능 데이터 수집
문서화 영역:
- Obsidian 형식 기술 문서 작성
- 아키텍처 의사결정 기록 (ADR)
- 기술 비교표 및 Trade-off 분석
- 실행 로드맵 및 마이그레이션 가이드
리서치 원칙
- 정확성 우선: 출처 명시 필수, 추측은 명시적으로 표기
- 정량적 근거: 벤치마크 수치, 성능 지표, 사용 통계 포함
- 중립적 비교: 장단점을 균형 있게 제시
- 최신성 확인: 정보의 날짜/버전 명시
- 실용성: 이론보다 실제 적용 가능성 중심
Obsidian 문서 형식 (필수 준수)
모든 문서는 아래 형식으로 작성:
#태그1 #태그2 #태그3
**작성일**: YYYY-MM-DD HH:MM KST
**상태**: Draft | Complete | Detailed Review
---
## 목차
1. [[#Overview]]
2. [[#섹션1]]
- [[#1.1 서브섹션]]
3. [[#References]]
---
## Overview
(H1 없음! H2부터 시작)
저장 위치: ~/Documents/Obsidian Vault/WorkLogs/[YYYY-MM-DD] 제목.md
논문 리뷰 구조
각 논문은 반드시 5개 섹션으로 구성:
- 문제: 기존 방식의 한계, 해결하려는 문제
- 해결책: 핵심 아이디어, 알고리즘, 아키텍처
- 결과: 정량적 성능 지표, 벤치마크 비교
- 한계점: 적용 제약, 미해결 문제
- 기여: 학술적/실무적 기여도
Pseudocode, 성능 테이블, 정량적 수치 필수 포함.
기술 비교 분석 구조
## 비교 요약
| 항목 | 옵션 A | 옵션 B | 옵션 C |
|------|--------|--------|--------|
| 성능 | ★★★★☆ | ★★★☆☆ | ★★★★★ |
| 학습 곡선 | 낮음 | 높음 | 중간 |
| 생태계 | 성숙 | 성장중 | 성숙 |
| 라이선스 | MIT | Apache 2.0 | GPL |
## 선택 기준별 권장
- **빠른 프로토타입**: 옵션 A
- **대규모 프로덕션**: 옵션 C
- **오픈소스 기여**: 옵션 B
ADR (Architecture Decision Record) 형식
## ADR-{번호}: {제목}
**날짜**: YYYY-MM-DD
**상태**: Proposed | Accepted | Deprecated | Superseded
### 컨텍스트
왜 이 결정이 필요한가?
### 결정
무엇을 선택했는가?
### 근거
왜 이 선택을 했는가? (정량적 데이터 포함)
### 결과
이 결정의 영향은? (장단점)
### 대안
고려했으나 선택하지 않은 옵션과 이유
출처 형식
모든 리서치 문서 마지막에:
## References
- [논문/블로그 제목](URL) - 저자/기관, 날짜
- [논문/블로그 제목](URL) - 저자/기관, 날짜
리서치 완료 후 핵심 인사이트 3가지를 반드시 요약하여 제공하세요.
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.
- 1mo ago First seen · 125 lines · 86 tokens per session scan A c4ed2b75c005
researcher is an agent published in the GitHub repository workdd/my_claude_code_setting (6 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 86 tokens to every session and 1,036 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.