plugin-dev

A guide for creating Claude Code plugins, which bundle related agents, skills, commands, hooks, and connections into one installable package. It covers plugin structure, configuration, sharing, versioning, and marketplaces.

In plain words
What is it for?
Use it to design plugin folders, write their configuration, group related capabilities, prepare marketplace entries, and follow Claude Code's plugin format.
Why use it?
It helps turn scattered custom tools into a package that can be reused, distributed, and updated across projects or teams.

Skill for Claude CodeCodex

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 skills/andisab/swe-marketplace/plugin-dev
Any agent
npx skills add andisab/swe-marketplace --skill plugin-dev
Clone the repo
git clone --depth 1 https://github.com/andisab/swe-marketplace

Made for: Claude Code, Codex.

Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,090 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00076 $0.04090
Opus 5 $0.00038 $0.02045
Sonnet 5 $0.00015 $0.00818
Haiku 4.5 $0.00008 $0.00409

Measured 2d ago against content hash a0562cd2b119, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plugin-dev 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.

plugins/context-engineering/skills/plugin-dev/SKILL.md · 691 lines

How it starts

The opening of the file, as written. The whole thing — 691 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plugin Dev Skill

This skill helps create production-ready Claude Code plugins following Anthropic's official plugin specifications.

What is a Plugin?

A plugin is a bundled collection of Claude Code components that work together to provide cohesive functionality. Plugins enable:

  • Modular distribution: Package related capabilities together
  • Team sharing: Install once across multiple projects
  • Version management: Track plugin versions independently
  • Marketplace discovery: Publish for community use
  • Automatic updates: Keep components synchronized

Plugin vs Individual Components

Approach When to Use
Individual Components Single capability, personal use, experimental
Plugin Multiple related components, team distribution, reusable across projects

Example - Individual approach:

  • .claude/agents/postgres-expert.md (one file)
  • .claude/commands/test.md (one file)

Example - Plugin approach:

  • database-toolkit/ plugin containing:
    • Agents: postgres-expert, mongodb-expert, sql-expert
    • Skills: migration-management, query-optimization
    • Commands: /migrate, /db-status
    • Templates: schema templates

Design consideration: Claude supports 20-50 skills simultaneously. When designing plugins with multiple skills, keep each skill focused and avoid overlap. Beyond 50 simultaneous skills, activation accuracy may decrease. Consider bundling related capabilities into fewer, more comprehensive skills rather than many narrow ones.

Plugin Structure

plugin-name/
├── .claude-plugin/
│   └── plugin.json              # Required: Plugin metadata
├── agents/                      # Optional: Sub-agent definitions
│   ├── agent-one.md
│   └── agent-two.md
├── skills/                      # Optional: Skill definitions
│   ├── skill-one/
│   │   ├── SKILL.md             # Do NOT add README.md inside skill dirs
│   │   ├── examples/
│   │   └── assets/              # Optional: Static resources
│   └── skill-two/
│       └── SKILL.md
├── commands/                    # Optional: Slash commands
│   ├── command-one.md
│   └── subfolder/
│       └── command-two.md
├── hooks/                       # Optional: Hook configurations
│   └── hooks.json
├── .mcp.json                    # Optional: MCP server integrations
├── .lsp.json                    # Optional: LSP server integrations
├── templates/                   # Optional: Code templates
│   └── template-files/
├── patterns/                    # Optional: Design patterns
│   └── pattern-docs/
├── README.md                    # Recommended: Plugin documentation
└── LICENSE                      # Recommended: License file

Read the full file on GitHub · 691 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 · 691 lines · 76 tokens per session scan A a0562cd2b119

Subscribe to this mod's changes

plugin-dev is a skill published in the GitHub repository andisab/swe-marketplace (21 stars, last pushed 14d ago), licensed MIT. It adds 76 tokens to every session and 4,090 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

skill-extractor

Skill "skill-extractor" from rawveg/skillsforge-marketplace, covering skill extractor, purpose, when to use, how it works and 1. component analysis.

rawveg/skillsforge-marketplace · 0 tokens

agent-team-builder

Designs and executes multi-agent teams to accomplish complex tasks through iterative collaboration, quality gates, and refinement loops. Use when a user wants to accomplish any non-trivial task that would benefit from specialised agents working in sequence or parallel - e.g. writing an article, building a software…

rawveg/skillsforge-marketplace · 139 tokens

crewai-multi-agent

Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies…

davila7/claude-code-templates · 61 tokens

langchain

Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG…

davila7/claude-code-templates · 79 tokens

autogpt-agents

Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.

davila7/claude-code-templates · 39 tokens

computer-use-agents

Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Anthropic's Computer Use, OpenAI's Operator/CUA, and open-source alternatives. Critical focus on sandboxing, security, and handling the unique challenges of vision-based control. Use…

davila7/claude-code-templates · 88 tokens