# Awesome Opencode

> 108 agents, 15 skills, smart model config, and interactive CLI for OpenCode — npx @weisser-dev/awesome-opencode

- **Type:** MCP server
- **Install:** `agentstack add mcp-weisser-dev-awesome-opencode`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [weisser-dev](https://agentstack.voostack.com/s/weisser-dev)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [weisser-dev](https://github.com/weisser-dev)
- **Source:** https://github.com/weisser-dev/awesome-opencode
- **Website:** https://www.npmjs.com/package/@weisser-dev/awesome-opencode

## Install

```sh
agentstack add mcp-weisser-dev-awesome-opencode
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# OpenCode Best Practices

The most comprehensive collection of agents, skills, and tooling for [OpenCode](https://opencode.ai) -- the open-source AI coding agent.

**108 agents** | **15 skills** | **18 curated MCP servers** | **Live MCP registry search** | **Smart model detection**

> Inspired by [VoltAgent/awesome-claude-code-subagents](https://github.com/VoltAgent/awesome-claude-code-subagents), fully adapted for OpenCode with permissions, skills, and markdown agent format.

---

## Quickstart

```bash
npx @weisser-dev/awesome-opencode
```

One command. It analyzes your project, walks you through agent/skill/model/MCP setup interactively, generates everything, and launches OpenCode.

---

## What it Does

```shell
  Awesome OpenCode
  108 agents, 15 skills, smart model config
  https://github.com/weisser-dev/awesome-opencode

? How would you like to set up your project?
❯ Auto-detect languages (recommended for existing projects)
  Select languages manually (recommended for fresh projects)

✔ Project analyzed

  Auto-detected:
    - TypeScript
    - Python

? Select project languages (2 detected / 28 total, scroll with arrows):
  ── Auto-Detected (2) ──
    ◉ JavaScript / TypeScript
    ◉ Python
  ── Other (26) ──
    ◯ Java
    ◯ Go
    ◯ Rust
    ...

? Select agents (12 recommended / 108 total, scroll with arrows):
  ── Recommended for your project (12/108) ──
    ◉ code-reviewer - Code quality review (default)
    ◉ test-writer - Test generation (default)
    ◉ devops-engineer - CI/CD pipelines (default)
    ◉ typescript-pro - TypeScript specialist (JavaScript / TypeScript)
    ◉ python-pro - Python ecosystem master (Python)
    ◉ fastapi-developer - FastAPI async APIs (Python)
    ...
  ── Core Development (3) ──
    ◯ backend-developer
    ...
  (108 agents across 10 categories)

? Select skills (5 recommended / 15 total, scroll with arrows):
    ◉ git-release - Release notes and version bumps
    ◉ ci-pipeline - CI pipeline configuration
    ◉ dependency-audit - Audit dependencies for vulnerabilities
    ◉ test-patterns - Test generation following project conventions
    ◉ changelog-generate - Changelog generation from commit history
    ◯ pr-review
    ...

  Models found in your config:

    my-provider/eu.anthropic.claude-sonnet-4-6
      -> claude-sonnet-4 (anthropic) | Strong | Cost: $$$ | Coding: 90/100
    my-provider/eu.anthropic.claude-haiku-4-5-20251001-v1:0
      -> claude-haiku-4 (anthropic) | Fast   | Cost: $$  | Coding: 75/100
    my-provider/eu.anthropic.claude-opus-4-6-v1
      -> claude-opus-4 (anthropic) | Frontier | Cost: $$$$ | Coding: 95/100

? Model strategy:
❯ Auto-optimize YOUR models (Build: claude-opus-4, Plan/Explore: claude-haiku-4)
  Cost Optimized (Haiku for Plan/Explore, Sonnet for Build)
  Quality Focused (Opus for Build, Sonnet for others)
  OpenAI Stack
  Mixed
  Keep existing

? Select MCP servers (14 available for your languages, scroll with arrows):
  ── Universal ──
    ◉ context7 - Library documentation search
    ◉ git - Read, search, and manipulate Git repos
    ◯ memory - Persistent knowledge graph (official)
    ...
  ── Database ──
    ◯ postgres - PostgreSQL read-only access (official)
    ...

? Search mcp.so for additional MCP servers? Yes
? Search mcp.so: playwright
  Found 45 server(s) on mcp.so:
? Select servers to add (45 found, scroll with arrows):
    ◯ Playwright Mcp (microsoft)
    ...

? Apply recommended step limits per agent? (controls context/cost) Yes
  Code-writing agents: unlimited | Review agents: 10-15 | Fast agents: 5-10

✔ No AGENTS.md found. Generate one with project-specific rules? Yes

  Generated:
    .opencode/agents/ (5 agents)
    .opencode/skills/ (3 skills)
    opencode.json (updated)
    .opencode/advanced.json (state)
    AGENTS.md (generated)

  Setup complete!

? Run OpenCode in a sandbox? (Docker, recommended for enterprise) No
? Start OpenCode? Yes

  Starting OpenCode...
```

On **re-run**, it remembers your setup:

```shell
  Awesome OpenCode
  108 agents, 15 skills, smart model config
  https://github.com/weisser-dev/awesome-opencode

  Already configured!
  Last setup: 2026-03-27
  Languages:  node, python
  Agents:     code-reviewer, test-writer, typescript-pro, python-pro
  Skills:     git-release, ci-pipeline, dependency-audit
  Models:     auto

? What would you like to do?
❯ Start OpenCode
  Start OpenCode (Sandboxed via Docker)
  Reconfigure (run setup again)
  Configure agents
  Configure skills
  Configure models
  Configure MCP servers
  Exit
```

---

## Features

### 108 Agents in 10 Categories

Core Development (8 agents)

| Agent | Description |
|-------|-------------|
| `api-designer` | REST/GraphQL API design and schema-first approach |
| `backend-developer` | Server-side expert for scalable APIs and backend systems |
| `frontend-developer` | UI/UX specialist for React, Vue, Angular and modern web |
| `fullstack-developer` | End-to-end feature development across frontend and backend |
| `graphql-architect` | GraphQL schema design, federation, and resolver patterns |
| `microservices-architect` | Distributed systems design and service decomposition |
| `mobile-developer` | Cross-platform mobile development |
| `websocket-engineer` | Real-time communication and event-driven systems |

Language Specialists (22 agents)

| Agent | Description |
|-------|-------------|
| `angular-architect` | Angular 15+ enterprise patterns, signals, RxJS |
| `cpp-pro` | Modern C++20/23, RAII, templates, memory management |
| `csharp-developer` | ASP.NET Core, EF Core, LINQ, async patterns |
| `django-developer` | Django 4+ ORM, REST framework, Celery |
| `elixir-expert` | Elixir/OTP, GenServer, Phoenix, LiveView |
| `fastapi-developer` | FastAPI, Pydantic, dependency injection |
| `flutter-expert` | Flutter 3+ widgets, state management |
| `golang-pro` | Go concurrency, goroutines, channels, interfaces |
| `java-architect` | Enterprise Java, Spring patterns, JVM tuning |
| `javascript-pro` | ES2024+, async patterns, module systems |
| `kotlin-specialist` | Coroutines, Kotlin Multiplatform, DSLs |
| `laravel-specialist` | Laravel 10+ Eloquent, Livewire, queues |
| `nextjs-developer` | Next.js 14+ App Router, Server Actions, RSC |
| `php-pro` | PHP 8.x, Composer, PSR standards |
| `python-pro` | Python typing, asyncio, packaging |
| `react-specialist` | React 18+ hooks, server components, Suspense |
| `ruby-pro` | Ruby metaprogramming, Rails patterns |
| `rust-engineer` | Ownership, lifetimes, async Rust |
| `spring-boot-engineer` | Spring Boot 3+ WebFlux, Security, Data JPA |
| `swift-expert` | SwiftUI, Combine, async/await |
| `typescript-pro` | Strict typing, generics, utility types |
| `vue-expert` | Vue 3 Composition API, Pinia, Nuxt |

Infrastructure (13 agents)

| Agent | Description |
|-------|-------------|
| `azure-infra-engineer` | Azure ARM/Bicep, AKS, Azure DevOps |
| `cloud-architect` | AWS/GCP/Azure multi-cloud architecture |
| `database-administrator` | DB replication, backup, recovery |
| `deployment-engineer` | Blue/green, canary, rollback automation |
| `devops-engineer` | CI/CD pipelines and build automation |
| `docker-expert` | Dockerfile optimization and container security |
| `incident-responder` | System incident triage and recovery |
| `kubernetes-specialist` | K8s, Helm, service mesh, cluster management |
| `network-engineer` | DNS, load balancing, firewalls |
| `platform-engineer` | Internal developer platform and golden paths |
| `security-engineer` | IAM, encryption, network segmentation |
| `sre-engineer` | SLI/SLO, observability, incident response |
| `terraform-engineer` | Infrastructure as Code with Terraform |

Quality & Security (11 agents)

| Agent | Description |
|-------|-------------|
| `accessibility-tester` | WCAG 2.1 compliance and inclusive design |
| `architect-reviewer` | Architecture review and ADR creation |
| `chaos-engineer` | Resilience testing and failure injection |
| `code-reviewer` | Code quality, security, and performance review |
| `compliance-auditor` | GDPR, SOC2, HIPAA, and OSS license audit |
| `debugger` | Bug investigation and root cause analysis |
| `error-detective` | Systemic error pattern analysis |
| `penetration-tester` | OWASP testing and ethical hacking |
| `performance-engineer` | Performance profiling and optimization |
| `security-auditor` | Security vulnerability scanning |
| `test-automator` | E2E/integration test framework design |

Data & AI (12 agents)

| Agent | Description |
|-------|-------------|
| `ai-engineer` | AI system design and deployment architecture |
| `data-analyst` | Data insights, visualization, BI |
| `data-engineer` | ETL/ELT pipelines, streaming, data lakes |
| `data-scientist` | Statistical analysis, predictive modeling |
| `database-optimizer` | Schema, query, and index optimization |
| `llm-architect` | RAG, fine-tuning, prompt engineering, evaluation |
| `machine-learning-engineer` | ML model training and optimization |
| `mlops-engineer` | ML deployment, monitoring, lifecycle |
| `nlp-engineer` | Tokenization, embeddings, transformers |
| `postgres-pro` | PostgreSQL advanced queries, extensions, tuning |
| `prompt-engineer` | Prompt optimization and chain-of-thought design |
| `sql-pro` | Window functions, CTEs, query optimization |

Developer Experience (11 agents)

| Agent | Description |
|-------|-------------|
| `build-engineer` | Build systems (webpack, vite, esbuild, gradle) |
| `cli-developer` | Command-line tool design and implementation |
| `dependency-manager` | Dependency audit, CVEs, license checks |
| `docs-writer` | Technical documentation writer |
| `dx-optimizer` | Developer experience and workflow optimization |
| `git-workflow-manager` | Branching strategy and commit hygiene |
| `legacy-modernizer` | Incremental legacy codebase modernization |
| `mcp-developer` | MCP server development and integration |
| `refactorer` | Code refactoring with test verification |
| `test-writer` | Test generation following project patterns |
| `tooling-engineer` | Linters, formatters, IDE plugins |

Specialized Domains (8 agents)

| Agent | Description |
|-------|-------------|
| `blockchain-developer` | Solidity, smart contracts, DeFi |
| `embedded-systems` | Firmware, RTOS, hardware interfaces |
| `fintech-engineer` | Payment processing, compliance, ledgers |
| `game-developer` | Game loops, physics, rendering |
| `iot-engineer` | MQTT, edge computing, sensor data |
| `mobile-app-developer` | Native iOS/Android, app store deployment |
| `payment-integration` | Stripe, PayPal, PCI compliance |
| `seo-specialist` | Technical SEO, Core Web Vitals |

Business & Product (9 agents)

| Agent | Description |
|-------|-------------|
| `business-analyst` | Requirements, user stories, process analysis |
| `content-marketer` | Content strategy, SEO writing |
| `legal-advisor` | Software licensing and compliance |
| `product-manager` | Product strategy and roadmaps |
| `project-manager` | Project planning and timelines |
| `sales-engineer` | Technical demos and proof-of-concept |
| `scrum-master` | Agile ceremonies and sprint planning |
| `technical-writer` | API docs, tutorials, guides |
| `ux-researcher` | User research and usability testing |

Meta & Orchestration (7 agents)

| Agent | Description |
|-------|-------------|
| `agent-organizer` | Multi-agent coordination and task routing |
| `context-manager` | Token optimization and context management |
| `error-coordinator` | Cross-system error handling and recovery |
| `knowledge-synthesizer` | Multi-source knowledge aggregation |
| `multi-agent-coordinator` | Complex workflow orchestration |
| `task-distributor` | Task allocation and load balancing |
| `workflow-orchestrator` | End-to-end workflow automation |

Research & Analysis (7 agents)

| Agent | Description |
|-------|-------------|
| `competitive-analyst` | Competitive intelligence and positioning |
| `data-researcher` | Dataset evaluation and statistical analysis |
| `market-researcher` | Market analysis and consumer insights |
| `research-analyst` | Comprehensive research and source evaluation |
| `scientific-literature-researcher` | Paper search and evidence synthesis |
| `search-specialist` | Advanced information retrieval |
| `trend-analyst` | Technology trend forecasting |

### 15 Skills

| Skill | Description |
|-------|-------------|
| `git-release` | Release notes and semantic version bumps |
| `pr-review` | Structured PR review checklist |
| `migration` | Database/framework migration with rollback |
| `test-patterns` | Test generation following project conventions |
| `deploy` | CI/CD pipeline and deployment setup |
| `dependency-audit` | CVE scan, license check, unused dependencies |
| `incident-postmortem` | Blameless postmortem with 5 Whys |
| `docker-optimize` | Dockerfile multi-stage and security hardening |
| `adr-write` | Architecture Decision Records (Nygard template) |
| `api-contract` | OpenAPI/AsyncAPI spec generation and validation |
| `changelog-generate` | CHANGELOG.md from git history (Keep a Changelog) |
| `ci-pipeline` | CI/CD config generation (GitHub Actions, GitLab CI) |
| `env-setup` | Developer environment bootstrap |
| `error-triage` | Stack trace parsing and root cause classification |
| `performance-profile` | Performance hotspot analysis and optimization plan |

### Smart Model Detection

The CLI recognizes models from **any provider** -- including custom Bedrock, Azure, or self-hosted endpoints:

```shell
abcd/eu.anthropic.claude-opus-4-6-v1     -> claude-opus-4   | Frontier | $$$$  | Coding: 95/100
abcd/eu.anthropic.claude-sonnet-4-6      -> claude-sonnet-4 | Strong   | $$$   | Coding: 90/100
abcd/eu.anthropic.claude-haiku-4-5       -> claude-haiku-4  | Fast     | $$    | Coding: 75/100
```

Supports 26+ model fingerprints across Anthropic, OpenAI, Google, DeepSeek, Meta, and Mistral.

**Agent-tier mapping** assigns the right model quality per agent type:
- **Frontier** (Opus, GPT-5.2, o3): Code-writing agents, language specialists
- **Strong** (Sonnet, GPT-5.1): Code review, architecture, security
- **Fast** (Haiku, Flash, mini): Exploration, docs, context management

### 18 Curated MCP Servers + Live Registry Search

| Category | Servers |
|----------|---------|
| **Universal** | context7, gh-grep, memory, fetch, sequential-thinking |
| **Git** | git |
| **Monitoring** | sentry, axiom |
| **Database** | postgres, sqlite, redis |
| **Cloud** | aws, kubernetes |
| **Deployment** | vercel |
| **Testing** | puppeteer |
| **Collaboration** | atlassian, linear |
| **Design** | figma |

MCP servers are **filtered by your selected languages** -- Terraform projects see AWS/K8s, Node projects see Vercel/Figma.

Plus: **live search** of the official MCP Registry (`registry.modelcontextprotocol.io`) to find and install any registered server.

---

## Documentation

| Document | Description |
|----------|-------------|
| [Agents](docs/01-agents.md) | Primary & sub-agents, built-in vs. custom, markdown definitions, permissions |
| [Skills](docs/02-skills.md) | SKILL.md structure, examples, discovery mechanism |
| [MCP Servers](docs/03-mcp-servers.md) | Local & remote servers, OAuth, recommended servers |
| [Models](docs/04-models.md) | Model recommendations per task, token optimization, costs |
| [Rules](docs/05-rules.md) | AGENTS.md, custom instructions, project conventions |
| [Tools & Custom Tools](docs/06-tools-and-custom-tools.md) | Built-in tools, creating custom tools |
| [Permissions](docs/07-permissions.md) | Granular permissions, wildcards, per-agent config |

---

## Installation

### Via npx (recommended)

```bash
npx @weisser-dev/awesome-opencode
```

### Global install

```bash
npm install -g @weisser-dev/awesome-opencode
awesome-opencode
```

### CLI Subcommands

```bash
awesome-opencode                      # Interactive setup or re-run menu
awesome-opencode configure            # Reconfigure everything
awesome-opencode configure agents     # Add/remove agents
awe

…

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [weisser-dev](https://github.com/weisser-dev)
- **Source:** [weisser-dev/awesome-opencode](https://github.com/weisser-dev/awesome-opencode)
- **License:** MIT
- **Homepage:** https://www.npmjs.com/package/@weisser-dev/awesome-opencode

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** yes
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-weisser-dev-awesome-opencode
- Seller: https://agentstack.voostack.com/s/weisser-dev
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.