Agents Marketplace
Open-source multi-harness plugin marketplace for shipping agents, skills, commands, and workflows across Claude Code, Codex CLI, Cursor, OpenCode, Gemini CLI, and Copilot.
Do not bounce yet
Read the fit check, compare one alternative, then decide whether the vendor page is still your best next click.
Quick Verdict
Fast fit check before you leave the page
Make the fit call first. Vendor pages are good at selling, but they rarely tell you where the product is a bad match.
- Developers using Claude Code, Codex CLI, Cursor, OpenCode, Gemini CLI, or GitHub Copilot in the same broader workflow
- Teams standardizing reusable agent skills, subagents, commands, and orchestration patterns across projects
- Power users who want a large but inspectable catalog of specialist coding-agent workflows
- The huge catalog can become its own form of clutter if teams install plugins without curating which agents and skills actually fit their repo.
- Claude Code is still the native source-of-truth harness, so other environments inherit adapter limitations and occasional graceful degradation.
- Quality varies by plugin and workflow; the presence of many skills does not remove the need for human review and project-specific instructions.
Compare Next
Take one more internal step before the vendor pitch
This is where visitors usually jump out too early. Read one deeper take or open one alternative so the next click is informed instead of impulsive.
Alternative profile
Claude-Mem
Open-source persistent memory layer for Claude Code and other coding agents that captures session observations, compresses them, and injects relevant context back into future work.
Alternative profile
oh-my-codex
Open-source orchestration layer for OpenAI Codex CLI with reusable skills, team worktrees, hooks, and persistent workflow state.
Alternative profile
SuperClaude
Transform generic Claude Code into your specialized development partner with zero-friction configuration
Agents Marketplace is for developers who have already learned that one coding-agent harness is not the whole workflow. Instead of maintaining separate prompt packs for Claude Code, Codex CLI, Cursor, OpenCode, Gemini CLI, and Copilot, it keeps plugins, agents, skills, commands, and orchestrators in one source tree and emits the harness-native pieces each tool can actually consume.
Agents Marketplace is a shared library of production-oriented agentic workflow building blocks rather than another standalone coding agent. The project keeps Claude Code plugins, subagents, skills, slash commands, and orchestration workflows in one Markdown source of truth, then emits harness-native artifacts for OpenAI Codex CLI, Cursor, OpenCode, Gemini CLI, and GitHub Copilot. That makes it directly relevant to serious vibe-coding teams that want reusable skills and specialist agents across tools instead of rebuilding the same prompt packs for every harness.
Why Choose Agents Marketplace?
Choose Agents Marketplace when your team wants reusable agent workflow assets across several coding tools instead of rebuilding the same skills per harness.
The source-of-truth model matters because it turns plugin portability into a maintained system rather than a set of stale copy-pasted markdown folders.
The catalog is useful for serious vibe coding because it includes specialist agents, skills, commands, and multi-agent orchestrators rather than only vague prompt templates.
Because it is MIT-licensed and public, teams can inspect the marketplace, generated artifacts, and validation approach before trusting it inside repo workflows.
Key Features
Ships 84 installable plugins, 192 specialist agents, 156 skills, 102 commands, and 16 orchestrator workflows from one public repository.
Uses Claude Code plugin content as the source of truth, then generates or exposes harness-native artifacts for Codex CLI, Cursor, OpenCode, Gemini CLI, and GitHub Copilot.
Keeps plugin installs scoped so a harness loads the selected components instead of dumping the whole marketplace into context.
Includes domain coverage across architecture, backend, frontend, infrastructure, security, testing, data, machine learning, documentation, business, and SEO workflows.
Provides adapter documentation, capability matrices, generation commands, validation checks, and round-trip recipes for keeping generated harness outputs from drifting.
Includes a plugin-eval framework for static checks, LLM-judge scoring, and Monte Carlo-style reliability tests around skill and plugin quality.
Pros & Cons
- It solves a real portability problem: teams are already mixing Claude Code, Codex, Cursor, OpenCode, Gemini CLI, and Copilot, but their reusable workflow assets usually stay trapped in one harness.
- The source-of-truth plus adapter model is more durable than copying prompt packs into five slightly different folder formats by hand.
- The catalog is broad enough to be useful immediately, while still structured as composable plugins rather than one giant context blob.
- MIT licensing, strong GitHub traction, and explicit validation tooling make it much easier to audit than closed prompt marketplaces.
- The huge catalog can become its own form of clutter if teams install plugins without curating which agents and skills actually fit their repo.
- Claude Code is still the native source-of-truth harness, so other environments inherit adapter limitations and occasional graceful degradation.
- Quality varies by plugin and workflow; the presence of many skills does not remove the need for human review and project-specific instructions.
- The project improves reusable agent workflows but does not replace the underlying coding agents, subscriptions, model costs, or permission discipline.
Detailed Use Cases for Agents Marketplace
Use Agents Marketplace when Claude Code, Codex CLI, Cursor, OpenCode, Gemini CLI, or Copilot should share the same core workflow assets instead of drifting apart.
The catalog is useful when a team wants architecture, security, testing, frontend, backend, infrastructure, data, ML, or documentation agents without starting from a blank file.
Install selected plugins when the current project needs them, keeping context narrower than a monolithic prompt pack.
The adapter and validation flow helps teams treat agent instructions as maintained engineering assets rather than informal snippets copied between tools.
Who Should Use Agents Marketplace?
Developers using Claude Code, Codex CLI, Cursor, OpenCode, Gemini CLI, or GitHub Copilot in the same broader workflow
Teams standardizing reusable agent skills, subagents, commands, and orchestration patterns across projects
Power users who want a large but inspectable catalog of specialist coding-agent workflows
Builders comparing prompt packs, skill libraries, and plugin marketplaces for agentic coding
Perfect For
Giving Claude Code, Codex CLI, Cursor, OpenCode, Gemini CLI, and Copilot access to the same curated agentic workflow building blocks.
Installing specialist agents and skills for common engineering domains without hand-writing every subagent profile from scratch.
Standardizing portable agent resources across a team that experiments with multiple coding-agent harnesses.
Evaluating and maintaining prompt, skill, and plugin quality through generated artifacts and structural validation instead of ad hoc copy-paste.
Technical Details
Agents Marketplace Comparisons & Alternatives
Agents Marketplace review
wshobson agents review
Claude Code plugin marketplace for Codex CLI
cross harness agent skills marketplace
Agents Marketplace vs SuperClaude
portable skills for Claude Code and Codex
Developers compare Agents Marketplace with other vibe coding tools when they need a better workflow fit, not just a better landing page.
Direct Competitors
Planning with Files
SuperClaude
oh-my-codex
Claude-Mem
Similar Tools You Might Like
Open-source persistent planning skill and plugin for coding agents that keeps task plans, findings, and progress on disk so work survives /clear, compaction, and crashes.
Open-source coding agent for VS Code and the terminal with browser automation, MCP extensibility, and human-in-the-loop approvals.
Fully local Claude Code memory plugin that logs sessions and writes compact resume context without sending project data to an external model.
Alternative Tools to Consider
Open-source persistent memory layer for Claude Code and other coding agents that captures session observations, compresses them, and injects relevant context back into future work.
Open-source orchestration layer for OpenAI Codex CLI with reusable skills, team worktrees, hooks, and persistent workflow state.
Transform generic Claude Code into your specialized development partner with zero-friction configuration
Open-source persistent planning skill and plugin for coding agents that keeps task plans, findings, and progress on disk so work survives /clear, compaction, and crashes.
Do one more comparison before you commit to Agents Marketplace
Strong picks usually survive one more internal check. Read deeper, compare a neighbor, then leave for the vendor page if the fit still holds.