agentmods.dev

my-claude-plugins AGENTS.md

my-claude-plugins AGENTS.md is an instructions file for Codex, OpenCode from YoungjaeDev/my-claude-plugins. It costs 6,816 tokens per session, scanned C, original, MIT.

Repository instructions for a Claude Code plugin marketplace that is also read by Codex. They explain where the shared instructions live, how plugin files are organized, and which documentation and manifests must stay consistent.

In plain words
What is it for?
Use them when changing AGENTS.md, plugin files, marketplace manifests, or documentation in the YoungjaeDev/my-claude-plugins repository. Requests written in Korean should receive Korean responses.
Why use it?
They give coding agents one source of project rules across two agent tools and reduce duplicated instructions or mismatched plugin metadata.

Instructions file for CodexOpenCode

Installs and runs on its own, but its text points at files inside the plugin that ships it — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed.

not rated 2 9d ago C scan 6,816 tokens original MIT
View the source file YoungjaeDev/my-claude-plugins
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 instructions/youngjaedev/my-claude-plugins/agents-md
Clone the repo
git clone --depth 1 https://github.com/YoungjaeDev/my-claude-plugins

Made for: Codex, OpenCode.

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 my-claude-plugins AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/youngjaedev/my-claude-plugins/agents-md.svg)](https://agentmods.dev/instructions/youngjaedev/my-claude-plugins/agents-md)
Your own site
<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="Measured on agentmods" height="20"></a>
Per session 6,816 This file is loaded in full into every session.
When invoked 6,816 The same file — it is already loaded in full.
Security scan C 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5 $0.06816 $0.06816
Opus 5 $0.03408 $0.03408
Sonnet 5 $0.01363 $0.01363
Haiku 4.5 $0.00682 $0.00682

Measured 4d ago against content hash b235f02847fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 4d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- Claude Code 플러그인 캐시 이슈 때문에 사용자 문서나 릴리스 안내에는 필요 시 `rm -rf ~/.claude/plugins/cache/my-claude-plugins/` 후 marketplace update 및 Claude Code 재시작 절차를 유지하세요.
AGENTS.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

이 파일이 정본이고, 루트 CLAUDE.md 는 이 파일을 @AGENTS.md 로 import 하는 한 줄짜리 포인터다. 두 런타임이 서로 다른 파일명을 찾기 때문이다 — Claude Code 는 CLAUDE.md 만 읽고 그 안의 @AGENTS.md import 로 이 파일을 끌어오며, Codex 는 AGENTS.md 를 그대로 읽는다. 내용을 이 파일 한 곳에만 두어 미러 유지 부담을 없앴다.

CLAUDE.md 를 따로 편집하지 마라 — @AGENTS.md 한 줄 import 일 뿐이다. 편집은 항상 AGENTS.md 에 한다.

기본 원칙

  • 이 저장소는 Claude Code 플러그인 marketplace 저장소입니다. 변경 전에는 이 문서, README.md, 관련 플러그인의 plugins/<name>/CLAUDE.md를 먼저 확인하세요.
  • 사용자가 한국어로 요청하면 한국어로 응답하세요.
  • 변경은 요청 범위에만 한정하고, 관련 없는 파일이나 기존 사용자 변경 사항은 되돌리지 마세요.
  • 파일 탐색과 검색은 우선 rg, rg --files를 사용하세요.
  • 플러그인 개발 중 라이브러리·런타임·플랫폼 사실을 확인할 때는 docs/llm-doc-sources.md 에 정리된 LLM 문서 소스(mcpdocs 등록 + deepwiki 타깃)를 먼저 사용하세요.
  • 문서와 매니페스트가 함께 움직이는 저장소이므로 코드 변경뿐 아니라 README.md, 이 문서, marketplace manifest의 동기화 필요성을 항상 확인하세요.

플러그인 트리 하나를 Claude Code 와 Codex CLI 가 함께 읽습니다 — one source, two runtimes. Codex 는 .claude-plugin/marketplace.json 과 plugins/*/.claude-plugin/plugin.json 을 네이티브 매니페스트 폴백으로 직접 읽으므로 생성 계층이 없습니다.

Plugins (14)

각 플러그인이 무엇을 하는지는 jq -r '.plugins[] | "\(.name): \(.description)"' .claude-plugin/marketplace.json 으로 읽는다 — 설명을 여기에 다시 적으면 매니페스트와 표 두 곳을 손으로 맞춰야 하고, check-doc-consistency.mjs 는 이름 집합만 검사하므로 설명 drift 는 조용히 남는다. 아래 표는 이름·분류만 유지한다 (가드가 이 이름 집합을 marketplace.json 과 대조한다).

Plugin Category
core-config Core
github-dev GitHub
e2e-harness Testing
code-scout Research & Search
deepwiki Research & Search
paper-search-tools Research & Search
codex-image AI Models
council AI Models
ml-toolkit Development Tools
publish Content & Translation
project-init Planning
docs-forge Documentation
mem0-ops Memory & Lore
llm-wiki Memory & Lore

플러그인은 .claude/settings.json 에서 auto-load 됩니다. 사용법 상세는 README.md.

저장소 구조

디렉터리 배치 자체는 ls plugins/ 로 확인한다. 아래는 그 배치만 봐서는 알 수 없는 각 경로의 역할과 편집 금지 여부다.

  • AGENTS.md: 이 문서. 두 런타임 공통 최상위 지침 + 플러그인 목록 + 구조 요약.
  • CLAUDE.md: @AGENTS.md 를 import 하는 한 줄 파일. Claude Code 진입점일 뿐, 별도 내용이 없습니다.
  • CLAUDE.md.global / CLAUDE.md.global.ko: 사용자 전역 지침(~/.claude/CLAUDE.md)의 정본과 손으로 유지하는 한국어 번역. 영어 파일이 SoT — 영어를 먼저 고치고 .ko 를 미러한 뒤 cp CLAUDE.md.global ~/.claude/CLAUDE.md 로 사본을 갱신한다. .ko 는 어떤 에이전트도 로드하지 않는다. 사본을 이 워킹트리로의 심볼릭 링크로 걸지 않는다 — 그러면 브랜치 전환과 커밋 안 된 편집이 그 순간 전역 지침으로 발효된다.
  • README.md: 사용자용 설치 및 플러그인 문서.
  • .claude/settings.json: 로컬 플러그인 로드 설정.
  • .claude-plugin/marketplace.json: marketplace 레지스트리와 플러그인 버전 목록. Codex 도 이 카탈로그를 네이티브로 읽는다.
  • .claude/rules/: 특정 경로에 적용되는 상세 규칙 (Claude 전용 — Codex 는 읽지 못함).
  • plugins/<name>/: 각 플러그인의 원본 디렉터리. plugins/<name>/.claude-plugin/plugin.json 이 플러그인별 매니페스트와 버전이며, Claude 와 Codex 가 같은 파일을 읽는다.

Read the full file on GitHub · 197 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. 4d ago First seen · 197 lines · 6,816 tokens per session scan C b235f02847fd

Subscribe to this mod's changes

my-claude-plugins AGENTS.md is an instructions file published in the GitHub repository YoungjaeDev/my-claude-plugins (2 stars, last pushed 9d ago), licensed MIT. It adds 6,816 tokens to every session, about $0.0341 per session on Opus 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.

Related

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).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens