refactor: rename slash commands tw-* → taskwing:* and MCP server → taskwing (#24)

* refactor: rename slash commands from tw-* to taskwing:* and MCP server to taskwing

Standardize naming convention across the entire codebase:
- Slash commands: /tw-ask → /taskwing:ask, /tw-next → /taskwing:next, etc.
- MCP server name: taskwing-mcp → taskwing
- No backward compatibility shims — old names detected as legacy for cleanup

* fix(bootstrap): use subdirectory for namespaced slash commands

Fix three critical runtime bugs identified by Greptile review:

1. macOS filesystem failure: colons in filenames (taskwing:ask.md) are
   invalid on HFS+/APFS. Now uses subdirectory approach:
   .claude/commands/taskwing/ask.md → /taskwing:ask

2. OpenCode validation failure: regex rejects colons. Now uses SlashCmd
   field (ask, next, etc.) instead of BaseName for OpenCode filenames.

3. Migration cleanup: managedSlashCommandBases() now includes legacy
   tw-* names so old files are properly pruned during upgrade.

Also fixes misleading comment on SlashCommandNames().

* fix(config): remove hardcoded dev path from opencode.json

Replace absolute dev binary path with portable "taskwing" command name
so the config works on any machine.

Author: josephgoksu

AGENTS.md

@@ -79,15 +79,15 @@ Brand names and logos are trademarks of their respective owners; usage here indi
 
 ### Slash Commands
 
-- /tw-ask - Use when you need to search project knowledge (decisions, patterns, constraints).
-- /tw-remember - Use when you want to persist a decision, pattern, or insight to project memory.
-- /tw-next - Use when you are ready to start the next approved TaskWing task with full context.
-- /tw-done - Use when implementation is verified and you are ready to complete the current task.
-- /tw-status - Use when you need current task progress and acceptance criteria status.
-- /tw-plan - Use when you need to clarify a goal and build an approved execution plan.
-- /tw-debug - Use when an issue requires root-cause-first debugging before proposing fixes.
-- /tw-explain - Use when you need a deep explanation of a code symbol and its call graph.
-- /tw-simplify - Use when you want to simplify code while preserving behavior.
+- /taskwing:ask - Use when you need to search project knowledge (decisions, patterns, constraints).
+- /taskwing:remember - Use when you want to persist a decision, pattern, or insight to project memory.
+- /taskwing:next - Use when you are ready to start the next approved TaskWing task with full context.
+- /taskwing:done - Use when implementation is verified and you are ready to complete the current task.
+- /taskwing:status - Use when you need current task progress and acceptance criteria status.
+- /taskwing:plan - Use when you need to clarify a goal and build an approved execution plan.
+- /taskwing:debug - Use when an issue requires root-cause-first debugging before proposing fixes.
+- /taskwing:explain - Use when you need a deep explanation of a code symbol and its call graph.
+- /taskwing:simplify - Use when you want to simplify code while preserving behavior.
 
 ### Core Commands
 

CHANGELOG.md

@@ -22,7 +22,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   - "TaskWing helps turn a goal into executed tasks with persistent context across AI sessions."
 - Updated slash and MCP prompt contracts to unified `task` and `plan` action-based interfaces.
 - Purged stale/outdated architecture documentation that no longer matches shipped behavior.
-- Reworked `/tw-plan`, `/tw-next`, `/tw-done`, and `/tw-debug` prompts as explicit process contracts with hard gates and refusal fallbacks.
+- Reworked `/taskwing:plan`, `/taskwing:next`, `/taskwing:done`, and `/taskwing:debug` prompts as explicit process contracts with hard gates and refusal fallbacks.
 - Updated slash command descriptions to trigger-focused "Use when ..." phrasing across assistant command generation.
 - Session initialization output now injects TaskWing Workflow Contract v1 for hook-enabled assistants.
 

CLAUDE.md

@@ -15,7 +15,7 @@ Two MCP servers are available for testing:
 
 | MCP Server               | Binary                         | Use Case                            |
 | ------------------------ | ------------------------------ | ----------------------------------- |
-| `taskwing-mcp`           | Production (`taskwing`)        | Stable features, production testing |
+| `taskwing`               | Production (`taskwing`)        | Stable features, production testing |
 | `taskwing-local-dev-mcp` | Development (`./bin/taskwing`) | Testing new/changed features        |
 
 ### Testing New Features
@@ -28,7 +28,7 @@ When developing new MCP tools or modifying existing ones:
 
 ### Important: MCP Server Caching
 
-The production MCP server (`taskwing-mcp`) uses the installed Homebrew binary. Changes to code are **NOT reflected** until:
+The production MCP server (`taskwing`) uses the installed Homebrew binary. Changes to code are **NOT reflected** until:
 
 - You rebuild: `make build && brew reinstall taskwing` (if using Homebrew)
 - Or test with: `go run . mcp` directly
@@ -339,15 +339,15 @@ Brand names and logos are trademarks of their respective owners; usage here indi
 
 ### Slash Commands
 
-- /tw-ask - Use when you need to search project knowledge (decisions, patterns, constraints).
-- /tw-remember - Use when you want to persist a decision, pattern, or insight to project memory.
-- /tw-next - Use when you are ready to start the next approved TaskWing task with full context.
-- /tw-done - Use when implementation is verified and you are ready to complete the current task.
-- /tw-status - Use when you need current task progress and acceptance criteria status.
-- /tw-plan - Use when you need to clarify a goal and build an approved execution plan.
-- /tw-debug - Use when an issue requires root-cause-first debugging before proposing fixes.
-- /tw-explain - Use when you need a deep explanation of a code symbol and its call graph.
-- /tw-simplify - Use when you want to simplify code while preserving behavior.
+- /taskwing:ask - Use when you need to search project knowledge (decisions, patterns, constraints).
+- /taskwing:remember - Use when you want to persist a decision, pattern, or insight to project memory.
+- /taskwing:next - Use when you are ready to start the next approved TaskWing task with full context.
+- /taskwing:done - Use when implementation is verified and you are ready to complete the current task.
+- /taskwing:status - Use when you need current task progress and acceptance criteria status.
+- /taskwing:plan - Use when you need to clarify a goal and build an approved execution plan.
+- /taskwing:debug - Use when an issue requires root-cause-first debugging before proposing fixes.
+- /taskwing:explain - Use when you need a deep explanation of a code symbol and its call graph.
+- /taskwing:simplify - Use when you want to simplify code while preserving behavior.
 
 ### Core Commands
 

GEMINI.md

@@ -218,15 +218,15 @@ Brand names and logos are trademarks of their respective owners; usage here indi
 
 ### Slash Commands
 
-- /tw-ask - Use when you need to search project knowledge (decisions, patterns, constraints).
-- /tw-remember - Use when you want to persist a decision, pattern, or insight to project memory.
-- /tw-next - Use when you are ready to start the next approved TaskWing task with full context.
-- /tw-done - Use when implementation is verified and you are ready to complete the current task.
-- /tw-status - Use when you need current task progress and acceptance criteria status.
-- /tw-plan - Use when you need to clarify a goal and build an approved execution plan.
-- /tw-debug - Use when an issue requires root-cause-first debugging before proposing fixes.
-- /tw-explain - Use when you need a deep explanation of a code symbol and its call graph.
-- /tw-simplify - Use when you want to simplify code while preserving behavior.
+- /taskwing:ask - Use when you need to search project knowledge (decisions, patterns, constraints).
+- /taskwing:remember - Use when you want to persist a decision, pattern, or insight to project memory.
+- /taskwing:next - Use when you are ready to start the next approved TaskWing task with full context.
+- /taskwing:done - Use when implementation is verified and you are ready to complete the current task.
+- /taskwing:status - Use when you need current task progress and acceptance criteria status.
+- /taskwing:plan - Use when you need to clarify a goal and build an approved execution plan.
+- /taskwing:debug - Use when an issue requires root-cause-first debugging before proposing fixes.
+- /taskwing:explain - Use when you need a deep explanation of a code symbol and its call graph.
+- /taskwing:simplify - Use when you want to simplify code while preserving behavior.
 
 ### Core Commands
 

README.md

@@ -116,9 +116,9 @@ taskwing goal "Add Stripe billing"
 # → Plan decomposed into 5 executable tasks
 
 # 3. Execute with your AI assistant
-/tw-next       # Get next task with full context
+/taskwing:next       # Get next task with full context
 # ...work...
-/tw-done       # Mark complete, advance to next
+/taskwing:done       # Mark complete, advance to next
 ```
 
 ## MCP Tools
@@ -141,7 +141,7 @@ Add to your AI tool's MCP config:
 ```json
 {
   "mcpServers": {
-    "taskwing-mcp": {
+    "taskwing": {
       "command": "taskwing",
       "args": ["mcp"]
     }
@@ -155,15 +155,15 @@ Once connected, use these slash commands from your AI assistant:
 
 | Command | When to use |
 |:--------|:------------|
-| `/tw-ask` | Search project knowledge (decisions, patterns, constraints) |
-| `/tw-remember` | Persist a decision, pattern, or insight to project memory |
-| `/tw-next` | Start the next approved task with full context |
-| `/tw-done` | Complete the current task after verification |
-| `/tw-status` | Check current task progress and acceptance criteria |
-| `/tw-plan` | Clarify a goal and build an approved execution plan |
-| `/tw-debug` | Root-cause-first debugging before proposing fixes |
-| `/tw-explain` | Deep explanation of a code symbol and its call graph |
-| `/tw-simplify` | Simplify code while preserving behavior |
+| `/taskwing:ask` | Search project knowledge (decisions, patterns, constraints) |
+| `/taskwing:remember` | Persist a decision, pattern, or insight to project memory |
+| `/taskwing:next` | Start the next approved task with full context |
+| `/taskwing:done` | Complete the current task after verification |
+| `/taskwing:status` | Check current task progress and acceptance criteria |
+| `/taskwing:plan` | Clarify a goal and build an approved execution plan |
+| `/taskwing:debug` | Root-cause-first debugging before proposing fixes |
+| `/taskwing:explain` | Deep explanation of a code symbol and its call graph |
+| `/taskwing:simplify` | Simplify code while preserving behavior |
 
 ## Core Commands
 

cmd/doctor.go

@@ -517,12 +517,12 @@ func printNextSteps(checks []DoctorCheck) {
 	fmt.Println("Next steps:")
 	if !hasActivePlan {
 		fmt.Println("  1. Create and activate plan: taskwing goal \"your development goal\"")
-		fmt.Println("  2. Open Claude Code and run: /tw-next")
+		fmt.Println("  2. Open Claude Code and run: /taskwing:next")
 	} else if !hasSession {
 		fmt.Println("  1. Open Claude Code (session will auto-initialize)")
-		fmt.Println("  2. Run: /tw-next")
+		fmt.Println("  2. Run: /taskwing:next")
 	} else {
-		fmt.Println("  • In Claude Code, run: /tw-next")
+		fmt.Println("  • In Claude Code, run: /taskwing:next")
 		fmt.Println("  • Tasks will auto-continue until circuit breaker triggers")
 	}
 }

cmd/goal.go

@@ -151,7 +151,7 @@ func runGoal(cmd *cobra.Command, args []string) error {
 
 	fmt.Printf("Plan created and activated: %s (%d task(s))\n", genRes.PlanID, len(genRes.Tasks))
 	fmt.Println("Next:")
-	fmt.Println("  1. In your AI tool, run /tw-next")
+	fmt.Println("  1. In your AI tool, run /taskwing:next")
 	fmt.Println("  2. Or use MCP tool task with action=next")
 	return nil
 }

cmd/hook.go

@@ -209,7 +209,7 @@ func runContinueCheck(maxTasks, maxMinutes int) error {
 		_ = saveHookSession(session)
 
 		return outputHookResponse(HookResponse{
-			Reason: fmt.Sprintf("Sentinel circuit breaker: Critical deviation detected in previous task. %s\n\nReview the changes before proceeding. Use /tw-next to continue after review.", session.LastDeviationSummary),
+			Reason: fmt.Sprintf("Sentinel circuit breaker: Critical deviation detected in previous task. %s\n\nReview the changes before proceeding. Use /taskwing:next to continue after review.", session.LastDeviationSummary),
 		})
 	}
 
@@ -232,11 +232,11 @@ func runContinueCheck(maxTasks, maxMinutes int) error {
 	if err != nil {
 		if isMissingProjectMemoryError(err) {
 			return outputHookResponse(HookResponse{
-				Reason: "No project memory found. Run 'taskwing bootstrap' to initialize project memory, or use /tw-next to continue manually.",
+				Reason: "No project memory found. Run 'taskwing bootstrap' to initialize project memory, or use /taskwing:next to continue manually.",
 			})
 		}
 		return outputHookResponse(HookResponse{
-			Reason: fmt.Sprintf("Could not open repository: %v. Use /tw-next to continue manually.", err),
+			Reason: fmt.Sprintf("Could not open repository: %v. Use /taskwing:next to continue manually.", err),
 		})
 	}
 	defer func() { _ = repo.Close() }()
@@ -332,7 +332,7 @@ func runContinueCheck(maxTasks, maxMinutes int) error {
 	blockDecision := "block"
 	return outputHookResponse(HookResponse{
 		Decision: &blockDecision,
-		Reason:   fmt.Sprintf("Continue to task %d/%d: %s\n\n%s\n\nIf auto-continue fails, use /tw-next to proceed manually.", session.TasksCompleted+1, len(activePlan.Tasks), nextTask.Title, contextStr),
+		Reason:   fmt.Sprintf("Continue to task %d/%d: %s\n\n%s\n\nIf auto-continue fails, use /taskwing:next to proceed manually.", session.TasksCompleted+1, len(activePlan.Tasks), nextTask.Title, contextStr),
 	})
 }
 
@@ -415,7 +415,7 @@ Circuit breakers are configured in .claude/settings.json (defaults: %d tasks, %d
 
 %s
 
-Use /tw-next to start the first task, or it will auto-continue after each task.
+Use /taskwing:next to start the first task, or it will auto-continue after each task.
 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 `, session.SessionID, session.StartedAt.Format("15:04:05"), planInfo, DefaultMaxTasksPerSession, DefaultMaxSessionMinutes, workflowContractBanner)
 

cmd/mcp_detect.go

@@ -36,7 +36,7 @@ func detectExistingMCPConfigs() []string {
 	return found
 }
 
-// detectClaudeMCP checks if Claude Code CLI has taskwing-mcp configured.
+// detectClaudeMCP checks if Claude Code CLI has taskwing configured.
 func detectClaudeMCP() bool {
 	// First check if claude CLI is available
 	_, err := exec.LookPath("claude")
@@ -56,7 +56,7 @@ func detectClaudeMCP() bool {
 	return mcpcfg.ContainsCanonicalServerName(string(output))
 }
 
-// detectGeminiMCP checks if Gemini CLI has taskwing-mcp configured.
+// detectGeminiMCP checks if Gemini CLI has taskwing configured.
 func detectGeminiMCP() bool {
 	// First check if gemini CLI is available
 	_, err := exec.LookPath("gemini")
@@ -78,7 +78,7 @@ func detectGeminiMCP() bool {
 	return mcpcfg.ContainsCanonicalServerName(string(output))
 }
 
-// detectCodexMCP checks if Codex CLI has taskwing-mcp configured.
+// detectCodexMCP checks if Codex CLI has taskwing configured.
 func detectCodexMCP() bool {
 	// First check if codex CLI is available
 	_, err := exec.LookPath("codex")

cmd/mcp_server.go

@@ -146,7 +146,7 @@ func runMCPServer(ctx context.Context) error {
 
 	// Create MCP server
 	impl := &mcpsdk.Implementation{
-		Name:    "taskwing-mcp",
+		Name:    "taskwing",
 		Version: version,
 	}