plugins CLAUDE.md

Repository guidance for a Claude Code plugin marketplace, a collection where reusable coding-agent extensions are published. It describes the folders for plugins, skills, commands, agents, and hooks, plus how skills can call one another.

In plain words
What is it for?
Use it when creating plugins or skills, editing marketplace metadata, organizing repository files, or changing skills that coordinate other skills.
Why use it?
It gives contributors a consistent structure for adding or changing marketplace components. It also highlights that parent skills must preserve the interfaces expected by child skills.

Instructions file

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/roboco-io/plugins/claude-md
Clone the repo
git clone --depth 1 https://github.com/roboco-io/plugins
Per session 1,746 This file is loaded in full into every session.
When invoked 1,746 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.

ModelPer sessionOnce invoked
Fable 5 $0.01746 $0.01746
Opus 5 $0.00873 $0.00873
Sonnet 5 $0.00349 $0.00349
Haiku 4.5 $0.00175 $0.00175

Measured 2d ago against content hash 2afbbaf58ce4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plugins CLAUDE.md 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 2d 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.

CLAUDE.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Repository Overview

Claude Code 플러그인 마켓플레이스 레포지토리. Skills, Commands, Agents, Hooks를 제공합니다.

  • GitHub: roboco-io/plugins
  • Marketplace 이름: roboco-plugins

Architecture

.claude-plugin/
└── marketplace.json              # Marketplace 정의 (필수)

plugins/
└── {category}/                   # development, security, workflow, documentation
    ├── .claude-plugin/
    │   └── plugin.json           # 플러그인 메타데이터
    ├── agents/                   # 에이전트 정의 (선택)
    ├── commands/                 # 커맨드 정의 (선택)
    └── skills/                   # 스킬 정의
        └── {skill-name}/
            ├── SKILL.md          # 스킬 지침 (YAML frontmatter + Markdown)
            └── references/       # Progressive disclosure용 참조 파일 (선택)

스킬 간 호출 관계

aws-well-architected 스킬은 오케스트레이터로서 6개 Pillar별 하위 스킬(aws-wa-*)을 호출하고 통합 리포트를 생성함. 이처럼 스킬이 다른 스킬을 호출하는 패턴이 존재하므로, 오케스트레이터 스킬 수정 시 하위 스킬의 인터페이스(입출력 형식)가 유지되는지 확인 필요.

Plugin Development

새 플러그인 추가 시 필수 작업

  1. plugins/{category}/.claude-plugin/plugin.json 생성
  2. plugins/{category}/skills/{name}/SKILL.md 생성 (YAML frontmatter 포함)
  3. .claude-plugin/marketplace.jsonplugins 배열에 추가
  4. README.md의 플러그인 목록 업데이트 (아래 규칙 참조)

marketplace.json 스키마

{
  "name": "roboco-plugins",
  "owner": { "name": "roboco-io" },
  "plugins": [
    {
      "name": "category-name",
      "source": "./plugins/category-name",
      "category": "category",
      "skills": ["./skills/skill-name/SKILL.md"]
    }
  ]
}

주의사항:

  • plugins 배열 항목은 문자열이 아닌 객체여야 함
  • 로컬 플러그인의 source는 문자열 경로, 외부 플러그인의 source{ "source": "npm"|"github", ... } 객체
  • skills 배열의 경로는 플러그인 source 디렉토리 기준 상대 경로 (예: ./skills/skill-name/SKILL.md)

외부 플러그인 추가

npm 또는 GitHub에서 외부 플러그인을 참조할 수 있음:

{
  "name": "external-plugin",
  "source": { "source": "npm", "package": "package-name" },
  "version": "1.0.0",
  "description": "설명",
  "category": "category"
}

Read the full file on GitHub · 208 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. 2d ago First seen · 208 lines · 1,746 tokens per session scan A 2afbbaf58ce4

Subscribe to this mod's changes

plugins CLAUDE.md is an instructions file published in the GitHub repository roboco-io/plugins (21 stars, last pushed 1mo ago), licensed MIT. It adds 1,746 tokens to every session, about $0.0087 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.