Token-efficient codebase exploration using RepoPrompt - USE FIRST for brownfield projects
Token-efficient codebase exploration using RepoPrompt CLI. Automatically triggers when you need to understand existing code structure before planning features or debugging issues.
/plugin marketplace add SiTaggart/claude-devbench/plugin install devbench@devbench-marketplaceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Token-efficient codebase exploration using RepoPrompt CLI. Use this for brownfield projects before planning or debugging.
rp-cli -e '<command>' # Run single command
rp-cli -e '<cmd1> && <cmd2>' # Chain commands
rp-cli -w <id> -e '<command>' # Target specific window
| Command | Aliases | Purpose |
|---|---|---|
tree | - | File/folder tree |
structure | map | Code signatures (token-efficient) |
search | grep | Search with context |
read | cat | Read file contents |
select | sel | Manage file selection |
context | ctx | Export workspace context |
builder | - | AI-powered file selection |
chat | - | Send to AI chat |
rp-cli -e 'tree' # Full tree
rp-cli -e 'tree --folders' # Folders only
rp-cli -e 'tree --mode selected' # Selected files only
rp-cli -e 'structure src/' # Signatures for path
rp-cli -e 'structure .' # Whole project
rp-cli -e 'structure --scope selected' # Selected files only
rp-cli -e 'search "pattern"'
rp-cli -e 'search "TODO" --extensions .ts,.tsx'
rp-cli -e 'search "error" --context-lines 3'
rp-cli -e 'search "function" --max-results 20'
rp-cli -e 'read path/to/file.ts'
rp-cli -e 'read file.ts --start-line 50 --limit 30' # Slice
rp-cli -e 'read file.ts --start-line -20' # Last 20 lines
rp-cli -e 'select add src/' # Add to selection
rp-cli -e 'select set src/ lib/' # Replace selection
rp-cli -e 'select clear' # Clear selection
rp-cli -e 'select get' # View selection
rp-cli -e 'context' # Full context
rp-cli -e 'context --include prompt,selection,tree'
rp-cli -e 'context --all > output.md' # Export to file
rp-cli -e 'builder "understand auth system"'
rp-cli -e 'builder "find API endpoints" --response-type plan'
rp-cli -e 'chat "How does auth work?"'
rp-cli -e 'chat "Design new feature" --mode plan'
rp-cli -e 'workspace list' # List workspaces
rp-cli -e 'workspace switch "Name"' # Switch workspace
rp-cli -e 'workspace tabs' # List tabs
# Quick operations without -e syntax
rp-cli --workspace MyProject --select-set src/ --export-context ~/out.md
rp-cli --chat "How does auth work?"
rp-cli --builder "implement user authentication"
Save repeatable workflows:
# export.rp
workspace switch MyProject
select set src/
context --all > output.md
Run with: rp-cli --exec-file ~/scripts/export.rp
rp-cli -e 'tree'
rp-cli -e 'structure .'
rp-cli -e 'search "auth" --context-lines 2'
rp-cli -e 'builder "understand authentication"'
rp-cli -e 'select set src/auth/'
rp-cli -e 'structure --scope selected'
rp-cli -e 'read src/auth/login.ts'
rp-cli -e 'context --all > codebase-map.md'
Create codebase-map at: .ai/handoffs/<session>/codebase-map.md
rp-cli -d <cmd> for detailed help on any commandstructure gives signatures without full contentThis skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.