OpenCode vs Claude Code: 161K Stars, Agent View, and the Provider War (June 2026)

OpenCode = Open source + 75 providers + desktop app + 7.5M monthly devs + Scout subagent + background agents.
Claude Code = Proprietary + Anthropic-only + Agent View fleet management + /goal autonomy + 10%+ of all GitHub commits.

Claude Code Prompt Structure (Extracted, v2.1.176)

// Claude Code System Prompt Components
├── Core System Prompt (2,896 tokens)
│ ├── Identity & capabilities
│ ├── Tool usage instructions
│ └── Response formatting rules
│
├── Subagent Prompts
│ ├── Plan Mode Enhanced (633 tokens)
│ ├── Explore Agent (516 tokens)
│ ├── Task Tool (294 tokens)
│ └── Agent View orchestration (new)
│
├── Tool Descriptions (20+ built-in tools)
│ ├── Write, Read, Edit, Bash
│ ├── Task, TodoWrite, Glob, Grep
│ ├── WebFetch, WebSearch
│ ├── NotebookEdit, KillShell
│ ├── EnterWorktree, ExitWorktree
│ └── Plugin-provided tools (dynamic)
│
├── Autonomy Prompts (new in v2.1.139+)
│ ├── /goal evaluator (validator model)
│ ├── Agent View session management
│ ├── /ultrareview code review skill
│ └── /ultraplan cloud environment planner
│
├── Utility Prompts
│ ├── Conversation summarization + recap
│ ├── Session management + persistence
│ ├── CLAUDE.md creation (384 tokens)
│ ├── Security review (2,610 tokens)
│ └── Agent creation architect (1,110 tokens)
│
└── Slash Command Prompts (expanded)
 ├── /goal, /loop, /focus, /effort
 ├── /ultrareview, /ultraplan
 ├── /pr-comments, /review-pr
 ├── /team-onboarding
 └── /security-review (2,610 tokens)

OpenCode Agent Configuration

# .opencode/agents/build.md (Primary Agent)
---
name: build
description: Default agent for development work
mode: primary
model: anthropic/claude-sonnet-4 # Or any provider
temperature: 0.7
tools:
 write: true
 edit: true
 bash: true
 webfetch: true
 task: true
 todo: true
permission:
 edit: allow
 bash: ask
 webfetch: allow
maxSteps: 50
---

You are a coding assistant focused on software development.
[Custom instructions follow...]

# .opencode/agents/plan.md (Read-only Agent)
---
name: plan
description: Analysis and exploration agent
mode: primary
permission:
 edit: deny
 bash: ask
---

You are an analyst. Read code, explain patterns,
but do not modify files unless explicitly asked.

Claude Code: Core prompts are still baked in, but the plugin ecosystem (v2.1.117+) now allows third-party skills, hooks, and MCP servers to inject behavior. Custom themes via /theme, vim visual mode, and /effort sliders give more control. The gateway /v1/models endpoint lets you point at compatible proxies.

OpenCode: Everything is a markdown file. Drop new agents in .opencode/agents/ and they're instantly available. v1.15.0 added effect-based event systems and background subagents. The Tauri desktop app ships on macOS/Windows/Linux with MCP connection status UI. Remote config via .well-known/opencode enables enterprise fleet management.

Claude Code Tool Inventory

// Claude Code v2.1.176 Built-in Tools
const CLAUDE_CODE_TOOLS = [
 // File Operations
 "Read", // Read files with line ranges
 "Write", // Create/overwrite files
 "Edit", // Search-replace edits
 "Glob", // Find files by pattern (native binary)
 "Grep", // Search file contents (native binary)

 // Execution
 "Bash", // Execute shell commands
 "KillShell", // Terminate running shells
 "NotebookEdit", // Edit Jupyter notebooks

 // Agent System
 "Task", // Spawn subagents
 "TodoWrite", // Track task progress

 // Worktree Management (new)
 "EnterWorktree", // Isolate background work
 "ExitWorktree", // Return to main working copy

 // Web & External
 "WebFetch", // Fetch web content
 "WebSearch", // Search the web

 // IDE Integration
 "AskUserQuestion", // Request user input
 "EnterPlanMode", // Switch to planning
 "ExitPlanMode", // Exit planning

 // Plugin Tools (new in 2.1.117+)
 "plugin__*", // Plugin-provided tools/skills

 // MCP Tools
 "mcp__*", // Dynamically loaded MCP tools
];

OpenCode Tool Inventory

// OpenCode v1.15.0 Built-in Tools
const OPENCODE_TOOLS = [
 // File Operations
 "read", // Read files with line ranges
 "write", // Create/overwrite files
 "edit", // Search-replace edits
 "glob", // Find files by pattern
 "grep", // Search with ripgrep

 // Execution
 "bash", // Execute shell commands

 // Agent System
 "task", // Spawn subagents (General, Explore, Scout)
 "todo", // Track task progress
 "skill", // Load reusable instruction sets

 // Web
 "webfetch", // Fetch and process web content

 // MCP Tools
 "mcp_*", // Declaratively configured MCP tools
];

// Built-in Subagents (v1.14.42+):
// General - full tool access, multi-step tasks
// Explore - read-only codebase navigation
// Scout - read-only external docs & dependency research

MCP Tool Configuration Comparison

// Claude Code: MCP tools via mcp.json
{
 "mcpServers": {
 "filesystem": {
 "command": "npx",
 "args": ["-y", "@modelcontextprotocol/server-filesystem", "/path"]
 }
 }
}
// All tools loaded into context at startup
// New: Tool Search enables lazy loading

// OpenCode: Declarative per-agent control
// opencode.json
{
 "tools": {
 "mymcp_*": true, // Enable for all agents
 "dangerous_tool": false // Disable globally
 },
 "agent": {
 "build": {
 "tools": {
 "mymcp_write": true,
 "mymcp_delete": false // Disable for this agent
 }
 }
 }
}

Claude Code: Agent View gives you a single dashboard for every session (running, blocked, done). The /goal command makes Claude autonomous: a validator model checks completion after every step. Native worktree isolation keeps parallel sessions from stepping on each other.

OpenCode: Tab to switch agents, @mention to invoke subagents, HTTP API for remote control. Scout subagent researches external docs without leaving your session. Background subagents run tasks while you keep working.

Claude Code Agent Hierarchy (v2.1.176)

// Claude Code Subagent Architecture (May 2026)
Agent View Dashboard (new: v2.1.139)
│ ├── Shows all sessions: Running / Blocked / Done
│ ├── Navigate between sessions
│ └── Peek at results without switching
│
├── /goal Command (new: v2.1.139)
│ ├── Set completion condition
│ ├── Validator model checks after every step
│ ├── Claude works autonomously until goal met
│ └── Enables true fire-and-forget workflows
│
├── Plan Mode (633 tokens prompt)
│ ├── Triggered via /plan or EnterPlanMode
│ ├── Read-only by default
│ ├── /ultraplan for cloud environment planning
│ └── Exits with ExitPlanMode tool
│
├── Explore Agent (516 tokens prompt)
│ ├── Fast codebase navigation
│ ├── Read-only access
│ └── Returns findings to parent
│
├── Task Agent (294 tokens prompt)
│ ├── Complex multi-step workflows
│ ├── Own context window + worktree isolation
│ ├── Background sessions with --bg flag
│ └── Results summarized to parent
│
├── Custom Agents (user-defined)
│ ├── Defined in .claude/agents/
│ ├── Inherit tool access from config
│ └── Agent-specific hooks and MCP servers
│
└── Plugin Agents (new: v2.1.117+)
 ├── Installed from plugin marketplace
 ├── Provide skills, hooks, and MCP servers
 └── Dependency enforcement between plugins

// Key Features:
// Esc twice = instant rewind to last checkpoint
// /loop = proactive monitoring mode
// /focus = distraction-free fullscreen
// Worktree isolation for parallel sessions

OpenCode Agent Hierarchy + Interactivity (v1.15.0)

// OpenCode Agent Architecture (May 2026)
// KEY ADVANTAGE: Superior interactivity + Scout

Primary Agents (Tab to switch instantly)
├── Build Agent (default)
│ ├── All tools enabled
│ ├── Full filesystem access
│ └── For development work
│
└── Plan Agent
 ├── Read-only by default
 ├── Asks permission for bash
 └── For analysis/exploration

Subagents (via Task tool or @mention)
├── @general - Complex multi-step tasks (parallel)
├── @explore - Read-only codebase navigation
├── @scout - External docs & dependency research (new)
│ ├── Clones dependency repos into cache
│ ├── Inspects library source code
│ └── Read-only, never modifies workspace
└── @custom - Your own agents from .opencode/agents/

// Background Subagents (new: v1.14.51)
// Tasks keep running while you continue working
// Session pinning with quick slots (v1.14.49)

// INTERACTIVITY FEATURES:
// 1. Tab - instant agent switching
// 2. @agent_name - invoke any subagent inline
// 3. HTTP API - control from mobile/remote
// 4. Persistent sessions - survives terminal close
// 5. Session pinning - quick slots for fast access
// 6. Auto-compact - intelligent context summarization

Agent View: A single dashboard showing every session (running, blocked, done). Navigate between sessions, peek at results. Shipped as a research preview in v2.1.139.

/goal command: Set a completion condition. A small, fast validator model runs after every step and answers one question: "Has the goal been met?" If no, the main model keeps going. Enables true fire-and-forget autonomous workflows.

Instant rewind: Esc twice to restore to the last checkpoint. "Summarize up to here" option added in v2.1.141.

Worktree isolation: Background sessions run in separate git worktrees, so parallel agents never step on each other's changes.

Scout subagent: Dedicated read-only agent for external docs and dependency research. Clones library repos into cache, inspects source without modifying your workspace.

Background subagents: Tasks keep running while you continue working (v1.14.51). Combined with session pinning and quick slots for fast access.

Tab switching + @mentions: Instantly swap between Build and Plan agents. Invoke @explore, @scout, @general, or custom agents inline.

HTTP API: Control sessions from mobile, tablets, or remote machines. Start a task at your desk, review on your phone.

Claude Code Context Management

// Claude Code uses automatic compaction
// Triggered near context limit

// Compaction process:
1. Detect approaching context limit
2. Summarize previous messages (utility prompt)
3. Preserve critical context (file contents, etc.)
4. Continue with reduced token count

// Manual compaction:
$ /compact # Slash command to force compaction

// Context advice from Anthropic:
// "If using Claude in an agent harness that compacts context,
// add this to your prompt so Claude can behave accordingly.
// Otherwise Claude may try to wrap up work as it
// approaches the context limit."

OpenCode Context Management

// OpenCode now has auto-compact (v1.14+)
// Plus provider-dependent Vercel AI SDK handling

// Auto-compact:
// - Intelligently summarizes conversation history
// - Manages token usage across long sessions
// - System agent handles compaction automatically

// Session persistence:
// - Server-side state via Hono HTTP API
// - Sessions survive terminal closure
// - Session pinning + quick slots (v1.14.49)
// - Can reconnect from mobile app

// LSP Integration:
// - Automatic symbol awareness
// - Language-specific context enrichment
// - Better code navigation than text-based approaches

Claude Code Permission Configuration

// claude.permissions in settings.json
{
 "claude.permissions": {
 "edit": "ask", // ask | allow | deny
 "bash": "ask",
 "bash.rm": "deny", // Specific command patterns
 "bash.git": "allow",
 "webfetch": "allow"
 }
}

// Permission flow:
1. Tool call requested
2. Check permission config
3. If "ask": Show confirmation dialog
4. If "allow": Execute immediately
5. If "deny": Block with error

// Dangerous operation detection:
// Built-in heuristics for destructive commands
// Even with "allow", warns on rm -rf /, etc.

OpenCode Permission Configuration

// opencode.json permission configuration
{
 "permission": {
 "edit": "allow",
 "bash": {
 "*": "ask", // Default: ask for all
 "git *": "allow", // Allow git commands
 "npm test": "allow",
 "npm install": "ask",
 "rm -rf *": "deny", // Block dangerous patterns
 "sudo *": "deny"
 },
 "webfetch": "allow",
 "task": {
 "general": "allow",
 "explore": "allow",
 "custom-*": "ask"
 },
 "skill": {
 "pr-review": "allow",
 "dangerous-*": "deny"
 }
 }
}

// Permission inheritance:
// Agent-specific overrides in frontmatter
// Last matching glob pattern wins

Claude Code assumes you want protection by default, with explicit allows. Better for teams with mixed trust levels.

OpenCode assumes power users who want granular control via glob patterns. More flexible but requires careful configuration.

MCP Configuration Comparison

// Claude Code: mcp.json
{
 "mcpServers": {
 "postgres": {
 "command": "npx",
 "args": ["-y", "@modelcontextprotocol/server-postgres"],
 "env": { "DATABASE_URL": "..." }
 },
 "github": {
 "command": "npx",
 "args": ["-y", "@modelcontextprotocol/server-github"]
 }
 }
}

// OpenCode: opencode.json
{
 "mcp": {
 "postgres": {
 "command": "npx",
 "args": ["-y", "@modelcontextprotocol/server-postgres"],
 "env": { "DATABASE_URL": "..." }
 }
 },
 "agent": {
 "build": {
 "tools": {
 "postgres_query": true,
 "postgres_execute": false // Read-only for this agent
 }
 }
 }
}

OpenCode now has three gateway tiers: Go ($10/mo for open-weight models like GLM-5.1, Kimi K2.5, DeepSeek V4), Zen (pay-as-you-go curated gateway at pass-through pricing), and Black ($200/mo for Anthropic + OpenAI + open-weight, sold out). Users can also bring their own API keys, use free tiers, or run local models via Ollama (streaming v2 reduces first-token latency by 40%). Claude Code requires $20/month Claude Pro at minimum. Max 5x ($100/mo) and Max 20x ($200/mo) provide higher limits. Claude Code now also supports gateway /v1/models endpoints via ANTHROPIC_BASE_URL, giving some provider flexibility through compatible proxies. Installation via brew install --cask claude-code or curl (npm deprecated).