agents
starsforks
How to install agents?
wshobson/agents
$git clone https://github.com/wshobson/agents> Production-ready agentic workflow building blocks: 94 plugins, 203 agents, > 175 skills, 109 commands — built for Claude Code and consumed natively by > OpenAI Codex CLI, Cursor, OpenCode, Gemini CLI, and GitHub Copilot from a single Markdown source.
README.md
| 1 | # Agentic Plugin Marketplace |
| 2 | |
| 3 | > Production-ready agentic workflow building blocks: **94 plugins**, **203 agents**, |
| 4 | > **175 skills**, **109 commands** — built for Claude Code and consumed natively by |
| 5 | > OpenAI Codex CLI, Cursor, OpenCode, Gemini CLI, and GitHub Copilot from a single Markdown source. |
| 6 | |
| 7 | [](#claude-code) [](docs/harnesses.md) [](docs/harnesses.md) [](docs/harnesses.md) [](GEMINI.md) [](docs/harnesses.md) |
| 8 | |
| 9 | > [!NOTE] |
| 10 | > One source-of-truth (`plugins/`), five harnesses. Each harness gets idiomatic, |
| 11 | > harness-native artifacts — not lowest-common-denominator translations. |
| 12 | > See [docs/harnesses.md](docs/harnesses.md) for the capability matrix. |
| 13 | |
| 14 | ## Quick start |
| 15 | |
| 16 | Pick your harness: |
| 17 | |
| 18 | ### Claude Code |
| 19 | |
| 20 | ```bash |
| 21 | /plugin marketplace add wshobson/agents |
| 22 | /plugin install python-development # or any of 94 plugins |
| 23 | ``` |
| 24 | |
| 25 | [→ Full Claude Code setup, troubleshooting, and plugin catalog](docs/usage.md) |
| 26 | |
| 27 | ### Codex CLI · Cursor · OpenCode · Gemini CLI · Copilot |
| 28 | |
| 29 | Codex and Cursor install natively from the committed registries (which point at the source `plugins/`): |
| 30 | |
| 31 | ```bash |
| 32 | npx codex-marketplace add wshobson/agents # Codex; then install individual plugins |
| 33 | # Cursor: add the marketplace, then `/plugin install <name>` (reads .cursor-plugin/ + source) |
| 34 | ``` |
| 35 | |
| 36 | Gemini and OpenCode install via clone + generate (the transformed trees are gitignored): |
| 37 | |
| 38 | ```bash |
| 39 | gh repo clone wshobson/agents ~/agents && cd ~/agents |
| 40 | make generate HARNESS=gemini && gemini extensions install . # Gemini |
| 41 | make install-opencode # OpenCode (runs generate + symlinks) |
| 42 | ``` |
| 43 | |
| 44 | Setup details and per-harness gotchas: [docs/harnesses.md](docs/harnesses.md). Gemini-specific setup: [GEMINI.md](GEMINI.md) (also auto-loaded by Gemini CLI). |
| 45 | |
| 46 | ## What's inside |
| 47 | |
| 48 | | | Count | What it is | |
| 49 | |---|---:|---| |
| 50 | | **Plugins** | 94 | Granular, single-purpose installable units (90 local + 4 external via git-subdir) | |
| 51 | | **Agents** | 203 | Domain experts (architecture, languages, infra, security, data, ML, docs, business, SEO) | |
| 52 | | **Skills** | 175 | Modular knowledge packages with progressive disclosure (load when activated) | |
| 53 | | **Commands** | 109 | Slash commands: scaffolding, security scans, test gen, infrastructure setup | |
| 54 | | **Orchestrators** | 16 | Multi-agent coordination workflows (full-stack, security, ML, incident response) | |
| 55 | |
| 56 | Browse the catalog: [docs/plugins.md](docs/plugins.md) · [docs/agents.md](docs/agents.md) · [docs/agent-skills.md](docs/agent-skills.md) |
| 57 | |
| 58 | ## How it works |
| 59 | |
| 60 | Each plugin is isolated and composable: agents, commands, and skills are auto-discovered |
| 61 | from directory structure. **Installing a plugin loads only its components into |
| 62 | context** — not the whole marketplace. |
| 63 | |
| 64 | ``` |
| 65 | plugins/python-development/ |
| 66 | ├── .claude-plugin/plugin.json |
| 67 | ├── agents/ # 3 Python agents (python-pro, django-pro, fastapi-pro) |
| 68 | ├── commands/ # 1 scaffolding command |
| 69 | └── skills/ # 16 specialized skills (async, testing, packaging, …) |
| 70 | ``` |
| 71 | |
| 72 | Tiered model strategy: |
| 73 | |
| 74 | | Tier | Model | Use | |
| 75 | |---|---|---| |
| 76 | | 0 | Fable 5 | Longest-horizon autonomous work — large migrations, multi-hour runs (opt-in, premium cost) | |
| 77 | | 1 | Opus | Architecture, security, code review, production-critical | |
| 78 | | 2 | inherit | User-chosen — backend, frontend, AI/ML, specialized | |
| 79 | | 3 | Sonnet | Docs, testing, debugging, API references | |
| 80 | | 4 | Haiku | Fast operational tasks, SEO, deployment, content | |
| 81 | |
| 82 | [→ Model configuration details](docs/agents.md#model-configuration) |
| 83 | |
| 84 | ## Multi-harness support |
| 85 | |
| 86 | This marketplace ships to five agentic harnesses from one Ma |
People who liked this also viewed
6 picksType
- Scrapling🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!MCP ServersJul 2026
- excel-mcp-serverA Model Context Protocol server for Excel file manipulationMCP ServersApr 2026
- Excel-MCP-Server-MasterExcel MCP Server - Manipulate Excel files without Microsoft Excel. Model Context Protocol for XLSX, XLSM with Claude AI integrationMCP ServersJun 2025
- agent-deviceCLI to control iOS and Android devices for AI agentsMCP ServersJul 2026
- n8n-mcpA MCP for Claude Desktop / Claude Code / Windsurf / Cursor to build n8n workflows for you MCP ServersJul 2026
- ha-mcpThe Unofficial and Awesome Home Assistant MCP ServerMCP ServersJul 2026
