moai-adk 0.32.8__py3-none-any.whl → 0.41.0__py3-none-any.whl

moai_adk/templates/.claude/skills/moai-tool-opencode/index.md

@@ -0,0 +1,96 @@
+---
+source: https://opencode.ai/docs
+fetched: 2026-01-08
+title: OpenCode Documentation Index
+---
+
+# OpenCode Documentation Index
+
+Complete navigation index for all OpenCode.ai documentation modules.
+
+## Core (7 modules)
+
+| Module | Path | Description |
+|--------|------|-------------|
+| Introduction | [modules/core/intro.md](modules/core/intro.md) | Installation, setup, primary use cases |
+| Configuration | [modules/core/config.md](modules/core/config.md) | JSON/JSONC config files, merge order |
+| Providers | [modules/core/providers.md](modules/core/providers.md) | 75+ LLM providers, custom providers |
+| Network | [modules/core/network.md](modules/core/network.md) | Proxy, authentication, certificates |
+| Enterprise | [modules/core/enterprise.md](modules/core/enterprise.md) | SSO, central config, AI gateway |
+| Troubleshooting | [modules/core/troubleshooting.md](modules/core/troubleshooting.md) | Logs, common issues, solutions |
+| Migration 1.0 | [modules/core/migration-1.0.md](modules/core/migration-1.0.md) | Upgrade from pre-1.0 versions |
+
+## Usage (7 modules)
+
+| Module | Path | Description |
+|--------|------|-------------|
+| TUI | [modules/usage/tui.md](modules/usage/tui.md) | Terminal interface, commands, keybinds |
+| CLI | [modules/usage/cli.md](modules/usage/cli.md) | Command-line interface, flags |
+| IDE | [modules/usage/ide.md](modules/usage/ide.md) | VS Code, Cursor, IDE integration |
+| Zen | [modules/usage/zen.md](modules/usage/zen.md) | Curated models, pricing, teams |
+| Share | [modules/usage/share.md](modules/usage/share.md) | Session sharing, privacy |
+| GitHub | [modules/usage/github.md](modules/usage/github.md) | GitHub Actions automation |
+| GitLab | [modules/usage/gitlab.md](modules/usage/gitlab.md) | GitLab CI/CD integration |
+
+## Configure (14 modules)
+
+| Module | Path | Description |
+|--------|------|-------------|
+| Tools | [modules/configure/tools.md](modules/configure/tools.md) | Built-in tools, enable/disable |
+| Rules | [modules/configure/rules.md](modules/configure/rules.md) | AGENTS.md, custom instructions |
+| Agents | [modules/configure/agents.md](modules/configure/agents.md) | Agent types, configuration |
+| Models | [modules/configure/models.md](modules/configure/models.md) | Model selection, variants |
+| Themes | [modules/configure/themes.md](modules/configure/themes.md) | Built-in and custom themes |
+| Keybinds | [modules/configure/keybinds.md](modules/configure/keybinds.md) | Keyboard shortcuts, leader key |
+| Commands | [modules/configure/commands.md](modules/configure/commands.md) | Custom slash commands |
+| Formatters | [modules/configure/formatters.md](modules/configure/formatters.md) | Code formatting setup |
+| Permissions | [modules/configure/permissions.md](modules/configure/permissions.md) | Tool approval system |
+| LSP Servers | [modules/configure/lsp-servers.md](modules/configure/lsp-servers.md) | Language server protocol |
+| MCP Servers | [modules/configure/mcp-servers.md](modules/configure/mcp-servers.md) | Model Context Protocol |
+| ACP Support | [modules/configure/acp.md](modules/configure/acp.md) | Agent Client Protocol |
+| Skills | [modules/configure/skills.md](modules/configure/skills.md) | Reusable instructions |
+| Custom Tools | [modules/configure/custom-tools.md](modules/configure/custom-tools.md) | TypeScript tool creation |
+
+## Develop (4 modules)
+
+| Module | Path | Description |
+|--------|------|-------------|
+| SDK | [modules/develop/sdk.md](modules/develop/sdk.md) | JavaScript/TypeScript client |
+| Server | [modules/develop/server.md](modules/develop/server.md) | HTTP API, OpenAPI spec |
+| Plugins | [modules/develop/plugins.md](modules/develop/plugins.md) | Plugin development, hooks |
+| Ecosystem | [modules/develop/ecosystem.md](modules/develop/ecosystem.md) | Community projects, plugins |
+
+## Quick Links
+
+### Getting Started
+1. [Introduction](modules/core/intro.md) - Installation and first steps
+2. [Configuration](modules/core/config.md) - Basic configuration
+3. [Providers](modules/core/providers.md) - Connect to LLM providers
+
+### Common Tasks
+- [Agents](modules/configure/agents.md) - Create custom agents
+- [Commands](modules/configure/commands.md) - Create custom commands
+- [Skills](modules/configure/skills.md) - Create reusable skills
+- [MCP Servers](modules/configure/mcp-servers.md) - Add external tools
+
+### Development
+- [SDK](modules/develop/sdk.md) - Build integrations
+- [Plugins](modules/develop/plugins.md) - Extend OpenCode
+- [Server](modules/develop/server.md) - HTTP API reference
+
+## Statistics
+
+| Section | Module Count |
+|---------|--------------|
+| Core | 7 |
+| Usage | 7 |
+| Configure | 14 |
+| Develop | 4 |
+| **Total** | **32** |
+
+## External Resources
+
+- [OpenCode Website](https://opencode.ai)
+- [GitHub Repository](https://github.com/anomalyco/opencode)
+- [Discord Community](https://opencode.ai/discord)
+- [OpenAPI Documentation](http://localhost:4096/doc)

moai_adk/templates/.claude/skills/moai-tool-opencode/modules/configure/acp.md

@@ -0,0 +1,115 @@
+---
+source: https://opencode.ai/docs/acp/
+fetched: 2026-01-08
+title: ACP Support
+---
+
+# ACP Support in OpenCode
+
+## Overview
+
+OpenCode integrates with the Agent Client Protocol (ACP), an open standard that enables communication between code editors and AI agents. This allows you to use OpenCode directly in compatible IDEs.
+
+## Supported Editors
+
+- Zed Editor
+- JetBrains IDEs
+- Neovim (via plugins)
+
+## Configuration Examples
+
+### Zed Editor
+
+Add to Zed settings:
+
+```json
+{
+  "agent_servers": {
+    "OpenCode": {
+      "command": "opencode",
+      "args": ["acp"]
+    }
+  }
+}
+```
+
+### JetBrains IDEs
+
+Requires absolute path to the OpenCode binary in `acp.json`:
+
+```json
+{
+  "agent_servers": {
+    "OpenCode": {
+      "command": "/absolute/path/bin/opencode",
+      "args": ["acp"]
+    }
+  }
+}
+```
+
+**Note:** JetBrains requires the full absolute path to the binary.
+
+### Avante.nvim
+
+Add to your Neovim configuration:
+
+```lua
+{
+  acp_providers = {
+    ["opencode"] = {
+      command = "opencode",
+      args = { "acp" }
+    }
+  }
+}
+```
+
+### CodeCompanion.nvim
+
+```lua
+require("codecompanion").setup({
+  strategies = {
+    chat = {
+      adapter = {
+        name = "opencode",
+        model = "claude-sonnet-4",
+      },
+    },
+  },
+})
+```
+
+## Supported Features
+
+The ACP interface maintains full feature parity with terminal usage:
+
+| Feature | Supported |
+|---------|-----------|
+| File operations | Yes |
+| Custom tools | Yes |
+| MCP servers | Yes |
+| Project rules | Yes |
+| Formatters | Yes |
+| Permissions system | Yes |
+| `/undo` command | No |
+| `/redo` command | No |
+
+**Note:** Built-in slash commands like `/undo` and `/redo` remain unsupported via ACP.
+
+## Running ACP Mode
+
+Start OpenCode in ACP mode:
+
+```bash
+opencode acp
+```
+
+This starts OpenCode in Agent Client Protocol mode via stdin/stdout.
+
+## Best Practices
+
+1. **Use absolute paths**: JetBrains requires full paths
+2. **Verify binary location**: Use `which opencode` to find path
+3. **Test connection**: Start with simple commands to verify setup
+4. **Configure per-project**: Use project-level config for specific needs

moai_adk/templates/.claude/skills/moai-tool-opencode/modules/configure/agents.md

@@ -0,0 +1,241 @@
+---
+source: https://opencode.ai/docs/agents/
+fetched: 2026-01-08
+title: Agents Configuration
+---
+
+# OpenCode Agents Documentation
+
+## Overview
+
+OpenCode provides specialized AI assistants called agents that can be configured for specific tasks and workflows. They enable focused tools with custom prompts, models, and tool access.
+
+## Agent Types
+
+### Primary Agents
+
+Main assistants you interact with directly. Switch between them using Tab or configured keybinds.
+
+**Built-in Primary Agents:**
+- **Build**: Default agent with all tools enabled for full development work
+- **Plan**: Restricted agent for analysis (file edits and bash set to "ask")
+
+### Subagents
+
+Specialized assistants that primary agents can invoke. Manually invoked via @ mentions.
+
+**Built-in Subagents:**
+- **General**: Research and multi-step tasks
+- **Explore**: Fast codebase exploration
+
+## Built-in Agents Summary
+
+| Agent | Type | Description |
+|-------|------|-------------|
+| Build | Primary | All tools enabled for full development work |
+| Plan | Primary | Restricted permissions for analysis |
+| General | Subagent | Researching questions and executing multi-step tasks |
+| Explore | Subagent | Quick codebase exploration |
+
+## Usage
+
+### Switching Primary Agents
+
+- Press `Tab` to cycle through primary agents
+- Use `switch_agent` keybind
+
+### Invoking Subagents
+
+- Automatic: Primary agents invoke subagents as needed
+- Manual: Use `@general` or `@explore` syntax
+
+### Navigation
+
+- `<Leader>+Right`: Navigate to child session
+- `<Leader>+Left`: Navigate to parent session
+- Configure with `session_child_cycle` keybinds
+
+## Configuration Methods
+
+### JSON Configuration
+
+In `opencode.json`:
+
+```json
+{
+  "$schema": "https://opencode.ai/config.json",
+  "agent": {
+    "security-auditor": {
+      "description": "Security vulnerability scanner",
+      "model": "anthropic/claude-sonnet-4",
+      "temperature": 0.3,
+      "maxSteps": 20,
+      "tools": {
+        "write": false,
+        "bash": false
+      },
+      "permission": {
+        "edit": "deny"
+      }
+    }
+  }
+}
+```
+
+### Markdown Files
+
+Create markdown files in:
+- Global: `~/.config/opencode/agent/`
+- Per-project: `.opencode/agent/`
+
+**Example: `.opencode/agent/docs-writer.md`**
+
+```markdown
+---
+description: Technical documentation writer
+model: anthropic/claude-sonnet-4
+temperature: 0.7
+---
+
+You are a technical documentation specialist.
+
+Focus on:
+- Clear, concise writing
+- Code examples
+- API documentation
+- User guides
+```
+
+## Configuration Options
+
+| Option | Description | Default |
+|--------|-------------|---------|
+| `description` | Brief description (required) | - |
+| `temperature` | Randomness (0.0-1.0) | Model default |
+| `maxSteps` | Max iterations before text-only response | Unlimited |
+| `disable` | Set true to disable | false |
+| `prompt` | Custom system prompt or file path | - |
+| `model` | Override global model | Global model |
+| `tools` | Enable/disable specific tools | All enabled |
+| `permission` | Tool permissions (ask/allow/deny) | - |
+| `mode` | "primary", "subagent", or "all" | "all" |
+| `hidden` | Hide from @ autocomplete | false |
+| `taskPermissions` | Control subagent invocation | - |
+
+### Tools Configuration
+
+```json
+{
+  "agent": {
+    "readonly": {
+      "tools": {
+        "write": false,
+        "edit": false,
+        "bash": false,
+        "mcp_*": false
+      }
+    }
+  }
+}
+```
+
+Supports wildcards for pattern matching.
+
+### Permissions Configuration
+
+```json
+{
+  "agent": {
+    "careful": {
+      "permission": {
+        "edit": "ask",
+        "bash": "ask",
+        "webfetch": "allow"
+      }
+    }
+  }
+}
+```
+
+## Creating Agents
+
+### Interactive Wizard
+
+```bash
+opencode agent create
+```
+
+The wizard handles:
+1. Location selection (global/project)
+2. Description input
+3. System prompt generation
+4. Tool selection
+5. Markdown file creation
+
+## Example Use Cases
+
+### Documentation Agent
+
+```json
+{
+  "agent": {
+    "docs": {
+      "description": "Technical writing specialist",
+      "model": "anthropic/claude-sonnet-4",
+      "temperature": 0.7,
+      "tools": {
+        "bash": false
+      }
+    }
+  }
+}
+```
+
+### Security Auditor
+
+```json
+{
+  "agent": {
+    "security": {
+      "description": "Vulnerability identification",
+      "model": "anthropic/claude-opus-4",
+      "temperature": 0.1,
+      "permission": {
+        "edit": "deny",
+        "write": "deny"
+      }
+    }
+  }
+}
+```
+
+### Code Reviewer
+
+```json
+{
+  "agent": {
+    "reviewer": {
+      "description": "Code review with read-only access",
+      "tools": {
+        "write": false,
+        "edit": false,
+        "bash": false
+      }
+    }
+  }
+}
+```
+
+### Debug Agent
+
+```json
+{
+  "agent": {
+    "debug": {
+      "description": "Issue investigation specialist",
+      "model": "anthropic/claude-sonnet-4",
+      "prompt": "Focus on debugging and root cause analysis."
+    }
+  }
+}
+```

moai_adk/templates/.claude/skills/moai-tool-opencode/modules/configure/commands.md

@@ -0,0 +1,197 @@
+---
+source: https://opencode.ai/docs/commands/
+fetched: 2026-01-08
+title: Custom Commands
+---
+
+# OpenCode Commands Documentation
+
+## Overview
+
+OpenCode enables users to create custom commands for repetitive tasks using the `/command-name` syntax, supplementing built-in commands like `/init`, `/undo`, and `/share`.
+
+## File Creation & Configuration
+
+### Markdown Approach
+
+Create `.md` files in:
+- Project-level: `.opencode/command/`
+- Global: `~/.config/opencode/command/`
+
+The filename becomes the command identifier.
+
+**Example: `.opencode/command/review.md`**
+
+```markdown
+---
+description: Review current changes
+agent: plan
+---
+
+Review the current git diff and provide feedback on:
+- Code quality
+- Potential bugs
+- Performance concerns
+```
+
+### JSON Configuration
+
+Use the `command` object in `opencode.jsonc`:
+
+```json
+{
+  "$schema": "https://opencode.ai/config.json",
+  "command": {
+    "review": {
+      "description": "Review current changes",
+      "agent": "plan",
+      "template": "Review the current git diff and provide feedback."
+    }
+  }
+}
+```
+
+## Template Features
+
+### Arguments
+
+Use placeholders for dynamic content:
+
+- `$ARGUMENTS`: All arguments as string
+- `$1`, `$2`, `$3`: Positional arguments
+
+**Example:**
+```markdown
+Fix the issue described: $ARGUMENTS
+```
+
+Usage: `/fix The button is not clickable`
+
+### Shell Integration
+
+Execute bash and embed output with `` !`command` `` syntax:
+
+```markdown
+Review the following changes:
+
+!`git diff --staged`
+```
+
+### File References
+
+Include file content with `@filename` syntax:
+
+```markdown
+Analyze this component:
+
+@src/components/Button.tsx
+```
+
+## Configuration Options
+
+| Option | Purpose | Required |
+|--------|---------|----------|
+| `template` | The prompt sent to the LLM | Yes |
+| `description` | UI label displayed in TUI | No |
+| `agent` | Specifies which agent executes | No |
+| `subtask` | Forces subagent invocation | No |
+| `model` | Overrides default model | No |
+
+## Override Built-in Commands
+
+Custom commands can override built-in commands:
+
+```json
+{
+  "command": {
+    "init": {
+      "description": "Custom project initialization",
+      "template": "Initialize project with my custom setup..."
+    }
+  }
+}
+```
+
+If you define a custom command with the same name as a built-in, it will override the built-in command.
+
+## Examples
+
+### Code Review Command
+
+```markdown
+---
+description: Comprehensive code review
+agent: plan
+---
+
+Review the following code changes:
+
+!`git diff HEAD~1`
+
+Focus on:
+1. Security vulnerabilities
+2. Performance issues
+3. Code style consistency
+4. Test coverage gaps
+```
+
+### Test Generator
+
+```markdown
+---
+description: Generate tests for a file
+---
+
+Generate comprehensive tests for $1:
+
+@$1
+
+Include:
+- Unit tests
+- Edge cases
+- Error handling tests
+```
+
+Usage: `/test src/utils/validator.ts`
+
+### Documentation Generator
+
+```markdown
+---
+description: Generate API documentation
+agent: docs
+model: anthropic/claude-sonnet-4
+---
+
+Generate API documentation for:
+
+@$1
+
+Format as:
+- Function signature
+- Parameters table
+- Return value
+- Usage examples
+```
+
+### Commit Message Generator
+
+```markdown
+---
+description: Generate commit message
+---
+
+Generate a conventional commit message for these changes:
+
+!`git diff --staged`
+
+Follow the format: type(scope): description
+```
+
+## Best Practices
+
+1. **Use descriptive names**: Command names should indicate their purpose
+2. **Add descriptions**: Help users understand command purpose
+3. **Specify agents**: Use appropriate agents for different tasks
+4. **Combine features**: Mix file refs, shell output, and arguments
+5. **Version control**: Store project commands in `.opencode/command/`