f09e282d72
* feat: add OpenCode integration implementation plan for BMAD-METHOD * installer(opencode): add OpenCode target metadata in install.config.yaml * chore(deps): add comment-json for JSONC parsing in OpenCode integration * feat(installer/opencode): implement setupOpenCode with minimal instructions merge and BMAD-managed agents/commands * feat(installer): add OpenCode (SST) to IDE selector and CLI --ide help * fix(opencode): align generated opencode.json(c) with schema (instructions as strings; agent.prompt; command.template; remove unsupported fields) * feat(installer): enhance OpenCode setup with agent selection and prefix options * fix: update configuration file references from `bmad-core/core-config.yaml` to `.bmad-core/core-config.yaml` across multiple agent and task files for consistency and clarity. * refactor: streamline OpenCode configuration prompts and normalize instruction paths for agents and tasks * feat: add tools property to agent definitions for enhanced functionality. Otherwise opencode consders the subagents as readonly * feat: add extraction of 'whenToUse' from agents markdown files for improved agent configuration in opencode * feat: enhance task purpose extraction from markdown files with improved parsing and cleanup logic * feat: add collision warnings for non-BMAD-managed agent and command keys during setup * feat: generate and update AGENTS.md for OpenCode integration with agent and task details * feat: add compact AGENTS.md generator and JSON-only integration for OpenCode * chore(docs): remove completed OpenCode integration implementation plans * feat: enable default prefixes for agent and command keys to avoid collisions * fix: remove unnecessary line breaks in 'whenToUse' descriptions for QA agents to mathc the rest of the agents definitions and improve programatic parsing of whenToUse prop * fix: update OpenCode references to remove 'SST' for consistency across documentation and configuration * fix: update agent mode from 'subagent' to 'all' for consistency in agent definitions * fix: consolidate 'whenToUse' description format for clarity and consistent parsing
185 lines
7.0 KiB
YAML
185 lines
7.0 KiB
YAML
installation-options:
|
|
full:
|
|
name: Complete BMad Core
|
|
description: Copy the entire .bmad-core folder with all agents, templates, and tools
|
|
action: copy-folder
|
|
source: bmad-core
|
|
single-agent:
|
|
name: Single Agent
|
|
description: Select and install a single agent with its dependencies
|
|
action: copy-agent
|
|
ide-configurations:
|
|
cursor:
|
|
name: Cursor
|
|
rule-dir: .cursor/rules/bmad/
|
|
format: multi-file
|
|
command-suffix: .mdc
|
|
instructions: |
|
|
# To use BMad agents in Cursor:
|
|
# 1. Press Ctrl+L (Cmd+L on Mac) to open the chat
|
|
# 2. Type @agent-name (e.g., "@dev", "@pm", "@architect")
|
|
# 3. The agent will adopt that persona for the conversation
|
|
claude-code:
|
|
name: Claude Code
|
|
rule-dir: .claude/commands/BMad/
|
|
format: multi-file
|
|
command-suffix: .md
|
|
instructions: |
|
|
# To use BMad agents in Claude Code:
|
|
# 1. Type /agent-name (e.g., "/dev", "/pm", "/architect")
|
|
# 2. Claude will switch to that agent's persona
|
|
iflow-cli:
|
|
name: iFlow CLI
|
|
rule-dir: .iflow/commands/BMad/
|
|
format: multi-file
|
|
command-suffix: .md
|
|
instructions: |
|
|
# To use BMad agents in iFlow CLI:
|
|
# 1. Type /agent-name (e.g., "/dev", "/pm", "/architect")
|
|
# 2. iFlow will switch to that agent's persona
|
|
crush:
|
|
name: Crush
|
|
rule-dir: .crush/commands/BMad/
|
|
format: multi-file
|
|
command-suffix: .md
|
|
instructions: |
|
|
# To use BMad agents in Crush:
|
|
# 1. Press CTRL + P and press TAB
|
|
# 2. Select agent or task
|
|
# 3. Crush will switch to that agent's persona / task
|
|
windsurf:
|
|
name: Windsurf
|
|
rule-dir: .windsurf/workflows/
|
|
format: multi-file
|
|
command-suffix: .md
|
|
instructions: |
|
|
# To use BMad agents in Windsurf:
|
|
# 1. Type /agent-name (e.g., "/dev", "/pm")
|
|
# 2. Windsurf will adopt that agent's persona
|
|
trae:
|
|
name: Trae
|
|
rule-dir: .trae/rules/
|
|
format: multi-file
|
|
command-suffix: .md
|
|
instructions: |
|
|
# To use BMad agents in Trae:
|
|
# 1. Type @agent-name (e.g., "@dev", "@pm", "@architect")
|
|
# 2. Trae will adopt that agent's persona
|
|
roo:
|
|
name: Roo Code
|
|
format: custom-modes
|
|
file: .roomodes
|
|
instructions: |
|
|
# To use BMad agents in Roo Code:
|
|
# 1. Open the mode selector (usually in the status bar)
|
|
# 2. Select any bmad-{agent} mode (e.g., "bmad-dev", "bmad-pm")
|
|
# 3. The AI will adopt that agent's full personality and capabilities
|
|
cline:
|
|
name: Cline
|
|
rule-dir: .clinerules/
|
|
format: multi-file
|
|
command-suffix: .md
|
|
instructions: |
|
|
# To use BMad agents in Cline:
|
|
# 1. Open the Cline chat panel in VS Code
|
|
# 2. Type @agent-name (e.g., "@dev", "@pm", "@architect")
|
|
# 3. The agent will adopt that persona for the conversation
|
|
# 4. Rules are stored in .clinerules/ directory in your project
|
|
gemini:
|
|
name: Gemini CLI
|
|
rule-dir: .gemini/commands/BMad/
|
|
format: multi-file
|
|
command-suffix: .toml
|
|
instructions: |
|
|
# To use BMad agents with the Gemini CLI:
|
|
# 1. The installer creates a `BMad` folder in `.gemini/commands`.
|
|
# 2. This adds custom commands for each agent and task.
|
|
# 3. Type /BMad:agents:<agent-name> (e.g., "/BMad:agents:dev", "/BMad:agents:pm") or /BMad:tasks:<task-name> (e.g., "/BMad:tasks:create-doc").
|
|
# 4. The agent will adopt that persona for the conversation or preform the task.
|
|
github-copilot:
|
|
name: Github Copilot
|
|
rule-dir: .github/chatmodes/
|
|
format: multi-file
|
|
command-suffix: .md
|
|
instructions: |
|
|
# To use BMad agents with Github Copilot:
|
|
# 1. The installer creates a .github/chatmodes/ directory in your project
|
|
# 2. Open the Chat view (`⌃⌘I` on Mac, `Ctrl+Alt+I` on Windows/Linux) and select **Agent** from the chat mode selector.
|
|
# 3. The agent will adopt that persona for the conversation
|
|
# 4. Requires VS Code 1.101+ with `chat.agent.enabled: true` in settings
|
|
# 5. Agent files are stored in .github/chatmodes/
|
|
# 6. Use `*help` to see available commands and agents
|
|
kilo:
|
|
name: Kilo Code
|
|
format: custom-modes
|
|
file: .kilocodemodes
|
|
instructions: |
|
|
# To use BMAD™ agents in Kilo Code:
|
|
# 1. Open the mode selector in VSCode
|
|
# 2. Select a bmad-{agent} mode (e.g. "bmad-dev")
|
|
# 3. The AI adopts that agent's persona and capabilities
|
|
|
|
qwen-code:
|
|
name: Qwen Code
|
|
rule-dir: .qwen/bmad-method/
|
|
format: single-file
|
|
command-suffix: .md
|
|
instructions: |
|
|
# To use BMad agents with Qwen Code:
|
|
# 1. The installer creates a .qwen/bmad-method/ directory in your project.
|
|
# 2. It concatenates all agent files into a single QWEN.md file.
|
|
# 3. Simply mention the agent in your prompt (e.g., "As *dev, ...").
|
|
# 4. The Qwen Code CLI will automatically have the context for that agent.
|
|
|
|
auggie-cli:
|
|
name: Auggie CLI (Augment Code)
|
|
format: multi-location
|
|
locations:
|
|
user:
|
|
name: User Commands (Global)
|
|
rule-dir: ~/.augment/commands/bmad/
|
|
description: Available across all your projects (user-wide)
|
|
workspace:
|
|
name: Workspace Commands (Project)
|
|
rule-dir: ./.augment/commands/bmad/
|
|
description: Stored in your repository and shared with your team
|
|
command-suffix: .md
|
|
instructions: |
|
|
# To use BMad agents in Auggie CLI (Augment Code):
|
|
# 1. Type /bmad:agent-name (e.g., "/bmad:dev", "/bmad:pm", "/bmad:architect")
|
|
# 2. The agent will adopt that persona for the conversation
|
|
# 3. Commands are available based on your selected location(s)
|
|
|
|
codex:
|
|
name: Codex CLI
|
|
format: project-memory
|
|
file: AGENTS.md
|
|
instructions: |
|
|
# To use BMAD agents with Codex CLI:
|
|
# 1. The installer updates/creates AGENTS.md at your project root with BMAD agents and tasks.
|
|
# 2. Run `codex` in your project. Codex automatically reads AGENTS.md as project memory.
|
|
# 3. Mention agents in your prompt (e.g., "As dev, please implement ...") or reference tasks.
|
|
# 4. You can further customize global Codex behavior via ~/.codex/config.toml.
|
|
|
|
codex-web:
|
|
name: Codex Web Enabled
|
|
format: project-memory
|
|
file: AGENTS.md
|
|
instructions: |
|
|
# To enable BMAD agents for Codex Web (cloud):
|
|
# 1. The installer updates/creates AGENTS.md and ensures `.bmad-core` is NOT ignored by git.
|
|
# 2. Commit `.bmad-core/` and `AGENTS.md` to your repository.
|
|
# 3. Open the repo in Codex Web and reference agents naturally (e.g., "As dev, ...").
|
|
# 4. Re-run this installer to refresh agent sections when the core changes.
|
|
|
|
opencode:
|
|
name: OpenCode CLI
|
|
format: jsonc-config
|
|
file: opencode.jsonc
|
|
instructions: |
|
|
# To use BMAD agents with OpenCode CLI:
|
|
# 1. The installer creates/updates `opencode.jsonc` at your project root.
|
|
# 2. It ensures the BMAD core instructions file is referenced: `./.bmad-core/core-config.yaml`.
|
|
# 3. If an existing `opencode.json` or `opencode.jsonc` is present, it is preserved and only `instructions` are minimally merged.
|
|
# 4. Run `opencode` in this project to use your configured agents and commands.
|