Borrowing it
Nothing to install: this file belongs to YoungjaeDev/my-claude-plugins. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/YoungjaeDev/my-claude-plugins/main/AGENTS.mdgit clone --depth 1 https://github.com/YoungjaeDev/my-claude-pluginsWrote 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/instructions/youngjaedev/my-claude-plugins/agents-md)<a href="https://agentmods.dev/instructions/youngjaedev/my-claude-plugins/agents-md"><img src="https://agentmods.dev/badge/instructions/youngjaedev/my-claude-plugins/agents-md/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/instructions/youngjaedev/my-claude-plugins/agents-md"><img src="https://agentmods.dev/badge/instructions/youngjaedev/my-claude-plugins/agents-md.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 | $0.08144 | $0.08144 |
| Opus 5.5 | $0.03258 | $0.03258 |
| Sonnet 5.5 | $0.01629 | $0.01629 |
| Haiku 4.5 | $0.00814 | $0.00814 |
Grade C, and why
my-claude-plugins AGENTS.md scanned grade C with 1 finding 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 today.
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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- 사용자 문서와 릴리스 안내에는 `rm -rf ~/.claude/plugins/cache/my-claude-plugins/` 후 marketplace update + Claude Code 재시작 절차를 유지한다 (플러그인 캐시 버그). How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
이 파일이 정본이다. 루트
CLAUDE.md는@AGENTS.md한 줄로 이 파일을 import 하는 포인터일 뿐이므로 편집은 항상 여기에 한다. Claude Code 는CLAUDE.md를 통해, Codex 는AGENTS.md를 직접 읽는다.
기본 원칙
- 이 저장소는 Claude Code 플러그인 marketplace 다. 변경 전에 이 문서,
README.md, 해당 플러그인의plugins/<name>/CLAUDE.md를 먼저 읽는다. - 사용자가 한국어로 요청하면 한국어로 응답한다.
- 변경은 요청 범위에만 한정하고, 관련 없는 파일이나 기존 사용자 변경을 되돌리지 않는다.
- 파일 탐색과 검색은
rg,rg --files를 우선 쓴다. - 라이브러리·런타임·플랫폼 사실은 기억이나 사본이 아니라 실행 시점에 확인한다: 벤더 공식 문서(
https://code.claude.com/docs/llms.txt,https://developers.openai.com/codex/llms.txt등)와 설치된 도구의--help. 조회 순서와 실패 시 동작은plugins/docs/skills/skill-forge/references/live-lookup.md. - 설계 결정을 묻는 질문에는
docs/adr/를, 용어는GLOSSARY.md를 먼저 읽는다. 이 저장소에는.llmwiki/가 없다 (바깥 지식이 없다). - 문서와 매니페스트가 함께 움직이는 저장소이므로 코드 변경 시
README.md, 이 문서, marketplace manifest 의 동기화 필요성을 항상 확인한다.
플러그인 트리 하나를 Claude Code 와 Codex CLI 가 함께 읽는다 (one source, two runtimes). Codex 는 .claude-plugin/marketplace.json 과 plugins/*/.claude-plugin/plugin.json 을 네이티브 폴백으로 직접 읽으므로 생성 계층이 없다.
Plugins (8)
각 플러그인의 설명은 jq -r '.plugins[] | "\(.name): \(.description)"' .claude-plugin/marketplace.json 으로 읽는다. 아래 표는 이름과 분류만 유지하고, check-doc-consistency.mjs 가 이 이름 집합을 marketplace.json 과 대조한다.
| Plugin | Category | 흡수한 옛 플러그인 |
|---|---|---|
dev |
Development | github-dev, project-init, e2e-harness |
docs |
Documentation | docs-forge, publish |
scout |
Research & Search | code-scout, deepwiki, paper-search-tools |
ml |
Development | ml-toolkit |
wiki |
Outside Knowledge | llm-wiki, mem0-ops |
deck |
Documentation | (신규, 덱 저장소 3곳에 손으로 복사되던 규칙·도구) |
council |
AI Models | (단독 유지, Claude 전용) |
codex-image |
AI Models | (단독 유지, Claude 전용) |
플러그인명을 짧게 둔 이유는 호출 길이와 가독성이다. 플러그인 스킬은 항상 /plugin:skill 로 노출된다. 슬래시 메뉴는 :·-·_ 를 무시하고 이름 안의 단어 시작에서도 매칭하므로 (/rev 가 /dev:review-loop 를 하이라이트, Claude Code 2.1.236 이상) 접두사 길이가 매칭을 막지는 않는다. 플러그인은 .claude/settings.json 에서 auto-load 된다. 사용법은 README.md.
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.
- today Changed · +5 lines · +1,287 tokens per session 4dcf45b79676
- 11d ago Changed · +7 lines · +1,224 tokens per session 736e7f494841
- 12d ago Changed · +13 lines · +103 tokens per session e3285b717ad8
- 13d ago Changed · +1 lines · +34 tokens per session ae780052852c
- 27d ago Changed · +1 lines · +148 tokens per session 24edd3990be1
- 1mo ago Changed · +1 lines · +77 tokens per session 153c46c218b9
- 1mo ago Changed · +154 tokens per session 9182084f8d79
- 1mo ago Changed · +17 lines · +703 tokens per session 4ad429760229
- 1mo ago Changed · -77 lines · -2,402 tokens per session 8e309e46e3a2
- 1mo ago First seen · 197 lines · 6,816 tokens per session scan C b235f02847fd
my-claude-plugins AGENTS.md is an instructions file published in the GitHub repository YoungjaeDev/my-claude-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 8,144 tokens to every session, about $0.0326 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.