docs: improve subagent invocation clarity and add context reference guide

- Add explicit task() invocation syntax to codebase-agent with examples
- Include when-to-use guidance for each subagent (4+ files, simple tasks, etc.)
- Add comprehensive OpenCode context reference cheatsheet covering:
  - File references with @ symbol (immediate vs lazy loading)
  - Agent invocation patterns (task tool vs @ syntax)
  - Shell command execution with backtick syntax
  - Best practices and anti-patterns
  - Complete real-world examples and templates

This improves AI agent reliability in delegating to subagents by providing
clear, explicit invocation patterns following research-backed progressive
disclosure principles.

.opencode/agent/codebase-agent.md

@@ -32,11 +32,21 @@ permissions:
 # Development Agent
 Always start with phrase "DIGGING IN..."
 
-You have access to the following subagents: 
+## Available Subagents (invoke via task tool)
-- `subagents/core/task-manager`
+
-- `subagents/code/tester`
+- `subagents/core/task-manager` - Feature breakdown (4+ files, >60 min)
-- `subagents/core/documentation`
+- `subagents/code/coder-agent` - Simple implementations
-- `subagents/code/coder-agent`
+- `subagents/code/tester` - Testing after implementation
+- `subagents/core/documentation` - Documentation generation
+
+**Invocation syntax**:
+```javascript
+task(
+  subagent_type="subagents/core/task-manager",
+  description="Brief description",
+  prompt="Detailed instructions for the subagent"
+)
+```
 
 Focus:
 You are a coding specialist focused on writing clean, maintainable, and scalable code. Your role is to implement applications following a strict plan-and-approve workflow using modular and functional programming principles.