specdacular 0.9.2 → 0.10.1

package/README.md

@@ -59,14 +59,14 @@ For monorepos and multi-repo setups, it maps each sub-project in parallel, then
 Three commands drive the entire task lifecycle:
 
 ```
-/specd:new my-feature              # Initialize + first discussion
-/specd:continue my-feature         # Everything else — discussion, research, planning, execution, review
-/specd:toolbox my-feature          # Advanced operations menu
+/specd.new my-feature              # Initialize + first discussion
+/specd.continue my-feature         # Everything else — discussion, research, planning, execution, review
+/specd.toolbox my-feature          # Advanced operations menu
 ```
 
 `continue` reads your task's current state and offers the natural next step. You never need to remember which command comes next.
 
-`toolbox` gives you direct access to advanced operations — discuss, research, plan, execute, review — and codebase context management (status dashboard, section-by-section review with edit/re-map/add).
+`toolbox` gives you direct access to advanced task operations — discuss, research, plan, execute, review. Use `/specd.codebase.review` for section-by-section context file review with edit/re-map/add.
 
 Works with single projects and multi-project setups (monorepos, multi-repo). In multi-project mode, features are discussed at the system level and routed to the relevant sub-projects, with cross-project dependency tracking and contract validation.
 
@@ -94,7 +94,7 @@ Choose:
 
 In Claude Code:
 ```
-/specd:help
+/specd.help
 ```
 
 ---
@@ -104,7 +104,7 @@ In Claude Code:
 ### Map a Codebase
 
 ```
-/specd:map-codebase
+/specd.codebase.map
 ```
 
 Creates `.specd/codebase/` with 4 AI-optimized documents. This gives Claude context about your codebase's architecture, patterns, structure, and gotchas. For multi-project setups, it detects sub-projects automatically and maps each one in parallel before producing system-level documentation.
@@ -114,7 +114,7 @@ Creates `.specd/codebase/` with 4 AI-optimized documents. This gives Claude cont
 **Step 1: Initialize**
 
 ```
-/specd:new user-dashboard
+/specd.new user-dashboard
 ```
 
 Creates `.specd/tasks/user-dashboard/` and starts the first discussion. Claude asks what you're building, follows the thread, and captures technical requirements. When done, offers to continue discussing or stop.
@@ -122,7 +122,7 @@ Creates `.specd/tasks/user-dashboard/` and starts the first discussion. Claude a
 **Step 2: Drive the lifecycle**
 
 ```
-/specd:continue user-dashboard
+/specd.continue user-dashboard
 ```
 
 That's it. `continue` reads the current state and guides you through each stage:
@@ -133,20 +133,20 @@ That's it. `continue` reads the current state and guides you through each stage:
 4. **Phase execution** — Plans each phase just-in-time, then implements with progress tracking
 5. **Phase review** — Code review agent compares plans against actual code
 
-After each step, you can continue or stop. Resume anytime with `/specd:continue`.
+After each step, you can continue or stop. Resume anytime with `/specd.continue`.
 
 **Execution modes:**
 
 ```
-/specd:continue user-dashboard                # Default — auto-runs, pauses at phase steps
-/specd:continue user-dashboard --interactive  # Prompt at every step with skip/jump options
-/specd:continue user-dashboard --auto         # Run everything, stop only on review issues
+/specd.continue user-dashboard                # Default — auto-runs, pauses at phase steps
+/specd.continue user-dashboard --interactive  # Prompt at every step with skip/jump options
+/specd.continue user-dashboard --auto         # Run everything, stop only on review issues
 ```
 
 **No argument? It picks for you:**
 
 ```
-/specd:continue
+/specd.continue
 ```
 
 Scans for in-progress tasks and shows a picker.
@@ -154,10 +154,18 @@ Scans for in-progress tasks and shows a picker.
 **Need a specific operation?**
 
 ```
-/specd:toolbox user-dashboard
+/specd.toolbox user-dashboard
 ```
 
-Opens a menu with task operations (Discuss, Research, Plan, Execute, Review) and context management (Status, Review). Useful when you want to jump to a specific action outside the normal flow.
+Opens a menu with task operations (Discuss, Research, Plan, Execute, Review). Useful when you want to jump to a specific action outside the normal flow.
+
+**Need to review codebase context?**
+
+```
+/specd.codebase.review
+```
+
+Section-by-section review of any context file: confirm, edit, remove, re-map, or add new content.
 
 ---
 
@@ -167,25 +175,25 @@ Opens a menu with task operations (Discuss, Research, Plan, Execute, Review) and
 
 | Command | Description |
 |---------|-------------|
-| `/specd:new [name]` | Initialize a task, start first discussion |
-| `/specd:continue [name] [--interactive\|--auto]` | **Drive the entire lifecycle** — picks up where you left off |
-| `/specd:toolbox [tasks name\|context]` | Task operations or codebase context management |
+| `/specd.new [name]` | Initialize a task, start first discussion |
+| `/specd.continue [name] [--interactive\|--auto]` | **Drive the entire lifecycle** — picks up where you left off |
+| `/specd.toolbox [name]` | Advanced task operations |
 
 ### Codebase Documentation
 
 | Command | Description |
 |---------|-------------|
-| `/specd:map-codebase` | Analyze codebase with parallel agents |
-| `/specd:toolbox context` | Status dashboard or section-by-section review |
+| `/specd.codebase.map` | Analyze codebase with parallel agents |
+| `/specd.codebase.review` | Review and edit codebase context files section by section |
 
 ### Utilities
 
 | Command | Description |
 |---------|-------------|
-| `/specd:config` | Configure auto-commit settings for docs and code |
-| `/specd:status [--all]` | Show task status dashboard |
-| `/specd:help` | Show available commands |
-| `/specd:update` | Update to latest version |
+| `/specd.config` | Configure auto-commit settings for docs and code |
+| `/specd.status [--all]` | Show task status dashboard |
+| `/specd.help` | Show available commands |
+| `/specd.update` | Update to latest version |
 
 ---
 
@@ -207,18 +215,14 @@ Opens a menu with task operations (Discuss, Research, Plan, Execute, Review) and
 - **Phase review** — Code review agent inspects executed code against plan intent. Generates fix plans (decimal phases like `phase-01.1`) if needed.
 - **Revise** — Collects feedback from review, creates fix plans, signals brain to re-execute.
 
-**`toolbox`** provides direct access to advanced operations outside the normal flow. Two subdomains:
-
-**Tasks** (`/specd:toolbox tasks my-feature`):
+**`toolbox`** (`/specd.toolbox my-feature`) provides direct access to task operations outside the normal flow:
 - **Discuss** — Explore open questions, record decisions
 - **Research** — Spawn parallel agents for patterns/pitfalls
 - **Plan** — Create execution phases from task context
 - **Execute** — Execute the next phase's plan
 - **Review** — Review executed phase, approve or request fixes
 
-**Context** (`/specd:toolbox context`):
-- **Status** — Dashboard showing all context files with freshness indicators
-- **Review** — Section-by-section review of any context file: confirm, edit, remove, re-map (spawns a mapper agent to regenerate a section), or add new content. Sections are tracked with `AUTO_GENERATED` and `USER_MODIFIED` tags with dates.
+**`codebase.review`** (`/specd.codebase.review`) — Section-by-section review of any codebase context file: confirm, edit, remove, re-map (spawns a mapper agent to regenerate a section), or add new content. Sections are tracked with `AUTO_GENERATED` and `USER_MODIFIED` tags with dates.
 
 ---
 
@@ -368,7 +372,7 @@ Specdacular spawns specialized agents that run simultaneously:
 
 ```
 ┌─────────────────────────────────────────────────────────┐
-│                  /specd:map-codebase                    │
+│                  /specd.codebase.map                    │
 └─────────────────────────────────────────────────────────┘
                           │
           ┌───────────────┼───────────────┐
@@ -396,7 +400,7 @@ Specdacular supports monorepos and multi-repo setups through an orchestrator lay
 ### Setup
 
 ```
-/specd:map-codebase
+/specd.codebase.map
 ```
 
 When it detects multiple projects (via `package.json`, `go.mod`, `Cargo.toml`, etc.), it offers to enable multi-project mode. This:
@@ -423,8 +427,8 @@ Planning creates per-project roadmaps plus a cross-project dependency graph (`DE
 `continue` schedules across projects, respecting cross-project dependencies. After each phase, it performs contract review — comparing what was implemented against system-level expectations and flagging deviations before they cascade to downstream projects.
 
 ```
-/specd:continue auth-system       # Auto-picks next unblocked phase across projects
-/specd:continue auth-system api   # Target a specific sub-project
+/specd.continue auth-system       # Auto-picks next unblocked phase across projects
+/specd.continue auth-system api   # Target a specific sub-project
 ```
 
 ---
@@ -441,7 +445,7 @@ your-project/
 │   │   ├── pre-execute.md
 │   │   └── post-review.md
 │   │
-│   ├── codebase/              # From /specd:map-codebase
+│   ├── codebase/              # From /specd.codebase.map
 │   │   ├── MAP.md
 │   │   ├── PATTERNS.md
 │   │   ├── STRUCTURE.md
@@ -537,7 +541,7 @@ npx specdacular@latest
 
 Or in Claude Code:
 ```
-/specd:update
+/specd.update
 ```
 
 ---

package/agents/specd-codebase-mapper.md

@@ -8,7 +8,7 @@ color: cyan
 <role>
 You are a codebase mapper optimized for AI consumption. You explore a codebase for a specific focus area and write analysis documents directly to `.specd/codebase/`.
 
-You are spawned by `/specd:map-codebase` with one of four focus areas:
+You are spawned by `/specd.codebase.map` with one of four focus areas:
 - **map**: Create navigation map → write MAP.md
 - **patterns**: Extract code patterns → write PATTERNS.md
 - **structure**: Document organization → write STRUCTURE.md

package/bin/install.js

@@ -166,13 +166,27 @@ function uninstall(isGlobal) {
 
   let removedCount = 0;
 
-  // Remove specd commands
+  // Remove specd commands (both old directory format and new flat format)
   const specCommandsDir = path.join(targetDir, 'commands', 'specd');
   if (fs.existsSync(specCommandsDir)) {
     fs.rmSync(specCommandsDir, { recursive: true });
     removedCount++;
     console.log(`  ${green}✓${reset} Removed commands/specd/`);
   }
+  const commandsDir = path.join(targetDir, 'commands');
+  if (fs.existsSync(commandsDir)) {
+    let cmdCount = 0;
+    for (const file of fs.readdirSync(commandsDir)) {
+      if (file.startsWith('specd.') && file.endsWith('.md')) {
+        fs.unlinkSync(path.join(commandsDir, file));
+        cmdCount++;
+      }
+    }
+    if (cmdCount > 0) {
+      removedCount++;
+      console.log(`  ${green}✓${reset} Removed ${cmdCount} specd commands`);
+    }
+  }
 
   // Remove specdacular directory
   const specDir = path.join(targetDir, 'specdacular');
@@ -292,14 +306,34 @@ function install(isGlobal) {
   const commandsDir = path.join(targetDir, 'commands');
   fs.mkdirSync(commandsDir, { recursive: true });
 
-  const specSrc = path.join(src, 'commands', 'specd');
-  const specDest = path.join(commandsDir, 'specd');
-  if (fs.existsSync(specSrc)) {
-    copyWithPathReplacement(specSrc, specDest, pathPrefix);
-    if (verifyInstalled(specDest, 'commands/specd')) {
-      console.log(`  ${green}✓${reset} Installed commands/specd`);
+  // Remove old commands/specd/ directory if it exists (pre-0.10.0 format)
+  const oldSpecDir = path.join(commandsDir, 'specd');
+  if (fs.existsSync(oldSpecDir)) {
+    fs.rmSync(oldSpecDir, { recursive: true });
+  }
+
+  // Remove old specd.*.md command files before copying new ones
+  for (const file of fs.readdirSync(commandsDir)) {
+    if (file.startsWith('specd.') && file.endsWith('.md')) {
+      fs.unlinkSync(path.join(commandsDir, file));
+    }
+  }
+
+  const commandsSrc = path.join(src, 'commands');
+  if (fs.existsSync(commandsSrc)) {
+    let commandCount = 0;
+    for (const file of fs.readdirSync(commandsSrc)) {
+      if (file.startsWith('specd.') && file.endsWith('.md')) {
+        let content = fs.readFileSync(path.join(commandsSrc, file), 'utf8');
+        content = content.replace(/~\/\.claude\//g, pathPrefix);
+        fs.writeFileSync(path.join(commandsDir, file), content);
+        commandCount++;
+      }
+    }
+    if (commandCount > 0) {
+      console.log(`  ${green}✓${reset} Installed ${commandCount} specd commands`);
     } else {
-      failures.push('commands/specd');
+      failures.push('commands');
     }
   }
 
@@ -430,12 +464,12 @@ function install(isGlobal) {
   }
 
   console.log(`
-  ${green}Done!${reset} Launch Claude Code and run ${cyan}/specd:help${reset}.
+  ${green}Done!${reset} Launch Claude Code and run ${cyan}/specd.help${reset}.
 
   ${yellow}Commands:${reset}
-    /specd:map-codebase  - Analyze and document your codebase
-    /specd:update        - Update to latest version
-    /specd:help          - Show all commands
+    /specd.codebase.map  - Analyze and document your codebase
+    /specd.update        - Update to latest version
+    /specd.help          - Show all commands
 `);
 }
 

package/commands/{specd/map-codebase.md → specd.codebase.map.md}

@@ -1,5 +1,5 @@
 ---
-name: specd:map-codebase
+name: specd.codebase.map
 description: Analyze codebase with parallel agents to produce AI-optimized documentation
 argument-hint: ""
 allowed-tools:

package/commands/specd.codebase.review.md

@@ -0,0 +1,39 @@
+---
+name: specd.codebase.review
+description: "Review and edit codebase context files section by section"
+argument-hint: ""
+allowed-tools:
+  - Read
+  - Write
+  - Edit
+  - Bash
+  - Glob
+  - Grep
+  - Task
+  - AskUserQuestion
+---
+
+<objective>
+Walk through and review a codebase context file (.specd/codebase/*.md) section by section. Confirm, edit, remove, or re-map individual sections.
+
+Output: Updated context file with reviewed/edited sections and updated timestamps.
+</objective>
+
+<execution_context>
+Follow the context-manual-review workflow:
+@~/.claude/specdacular/workflows/context-manual-review.md
+</execution_context>
+
+<context>
+**Context workflows:**
+@~/.claude/specdacular/workflows/context-manual-review.md
+@~/.claude/specdacular/workflows/context-add.md
+</context>
+
+<success_criteria>
+- [ ] User selects a context file to review
+- [ ] Section list shown with tag status
+- [ ] User can confirm, edit, remove, or re-map each section
+- [ ] Timestamps updated after review
+- [ ] Changes committed
+</success_criteria>

package/commands/{specd/config.md → specd.config.md}

@@ -1,5 +1,5 @@
 ---
-name: specd:config
+name: specd.config
 description: Create or update .specd/config.json with commit settings
 argument-hint: ""
 allowed-tools:

package/commands/{specd/continue.md → specd.continue.md}

@@ -1,5 +1,5 @@
 ---
-name: specd:continue
+name: specd.continue
 description: Continue task lifecycle — picks up where you left off
 argument-hint: "[task-name] [--interactive|--auto]"
 allowed-tools:

package/commands/{specd/help.md → specd.help.md}

@@ -1,5 +1,5 @@
 ---
-name: specd:help
+name: specd.help
 description: Show all specdacular commands and usage guide
 allowed-tools:
   - Read

package/commands/specd.new-project.md

@@ -0,0 +1,58 @@
+---
+name: specd.new-project
+description: Bootstrap a new project from idea to structured plan
+argument-hint: "[project-name]"
+allowed-tools:
+  - Read
+  - Bash
+  - Glob
+  - Grep
+  - Write
+  - AskUserQuestion
+  - Task
+---
+
+<objective>
+Guide users from "I have an idea" to a structured project plan for greenfield projects. Unlike `/specd.new` which adds tasks to existing codebases, this bootstraps entire projects (or multi-service systems) through collaborative questioning, domain research, requirements scoping, and roadmap generation — producing an orchestrator setup with per-project task lifecycles.
+
+**Stages:**
+1. **Questioning** — Collaborative discussion to understand vision, goals, users, constraints
+2. **Research** — Parallel agents investigate stack, features, architecture, pitfalls
+3. **Requirements** — Multi-select scoping from research findings → REQUIREMENTS.md
+4. **Roadmap** — Phase planning mapped to requirements, identifies sub-projects
+5. **Scaffolding** — Create orchestrator config, sub-project directories, seed setup tasks
+
+**Creates:**
+- `.specd/tasks/project/PROJECT.md` — Project vision and goals
+- `.specd/tasks/project/research/` — Stack, features, architecture, pitfalls findings
+- `.specd/tasks/project/REQUIREMENTS.md` — Scoped v1 requirements with REQ-IDs
+- `.specd/tasks/project/ROADMAP.md` — Phased execution plan
+- `.specd/config.json` — Orchestrator config with projects array
+- Per sub-project: `.specd/config.json` + `.specd/tasks/setup/FEATURE.md`
+
+**This is a standalone command.** It runs its own sequential flow and exits. After scaffolding, use `/specd.new` and `/specd.continue` on individual sub-projects.
+</objective>
+
+<execution_context>
+@~/.claude/specdacular/workflows/new-project.md
+</execution_context>
+
+<context>
+Project name: $ARGUMENTS
+
+**No codebase context needed** — this is for greenfield projects with no existing code.
+
+**References:**
+- `~/.claude/specdacular/templates/tasks/PROJECT.md` — Project vision template
+- `~/.claude/specdacular/templates/tasks/REQUIREMENTS.md` — Requirements template (Phase 3)
+- `~/.claude/specdacular/agents/project-researcher.md` — Research agent (Phase 2)
+</context>
+
+<success_criteria>
+- [ ] Questioning produces PROJECT.md with clear vision, goals, users, constraints
+- [ ] Research spawns parallel agents for 4 domains (Phase 2)
+- [ ] Requirements scoped via multi-select from research (Phase 3)
+- [ ] Roadmap generated with phases mapped to requirements (Phase 3)
+- [ ] Sub-projects scaffolded with orchestrator config (Phase 4)
+- [ ] Each sub-project independently runnable via `/specd.new` and `/specd.continue`
+</success_criteria>

package/commands/{specd/new.md → specd.new.md}

@@ -1,5 +1,5 @@
 ---
-name: specd:new
+name: specd.new
 description: Initialize a new task and start the first discussion
 argument-hint: "[task-name]"
 allowed-tools:
@@ -22,7 +22,7 @@ Initialize a task folder and start the first discussion. Creates structure, asks
 - `.specd/tasks/{name}/STATE.md` — Progress tracking
 - `.specd/tasks/{name}/config.json` — Task configuration
 
-**This is the entry point.** After this, continue with `/specd:continue` to drive the entire lifecycle.
+**This is the entry point.** After this, continue with `/specd.continue` to drive the entire lifecycle.
 </objective>
 
 <execution_context>
@@ -35,7 +35,7 @@ Task name: $ARGUMENTS
 **Codebase context discovery:**
 1. Check for `.specd/config.json` — if exists, read `codebase_docs` path
 2. If no config, check for `.specd/codebase/` (default location)
-3. If neither found, offer `/specd:map-codebase`
+3. If neither found, offer `/specd.codebase.map`
 
 **Referenced docs (when available):**
 - `MAP.md` — System structure
@@ -61,5 +61,5 @@ Task name: $ARGUMENTS
 - [ ] STATE.md tracks current position
 - [ ] config.json created
 - [ ] Committed to git
-- [ ] User offered to continue with `/specd:continue`
+- [ ] User offered to continue with `/specd.continue`
 </success_criteria>

package/commands/{specd/status.md → specd.status.md}

@@ -1,5 +1,5 @@
 ---
-name: specd:status
+name: specd.status
 description: Show feature status dashboard
 argument-hint: "[--all]"
 allowed-tools:

package/commands/specd.toolbox.md

@@ -0,0 +1,63 @@
+---
+name: specd.toolbox
+description: "Advanced task operations"
+argument-hint: "[<task-name>]"
+allowed-tools:
+  - Read
+  - Write
+  - Edit
+  - Bash
+  - Glob
+  - Grep
+  - Task
+  - AskUserQuestion
+  - WebSearch
+  - WebFetch
+---
+
+<objective>
+Task lifecycle operations: discuss, research, plan, execute, review.
+</objective>
+
+<execution_context>
+**Parse $ARGUMENTS as task name.**
+
+- If a bare word that matches a directory in `.specd/tasks/` or `.specd/features/` → use as task name
+- If empty → check `.specd/tasks/` for available tasks. If only one task exists, use it automatically. If multiple, ask.
+
+Validate using:
+@~/.claude/specdacular/references/validate-task.md
+
+Then present the menu using AskUserQuestion:
+- header: "Operation"
+- question: "What would you like to do with {task-name}?"
+- options:
+  - "Discuss" — Explore gray areas and record decisions
+  - "Research" — Spawn parallel agents for patterns/pitfalls
+  - "Plan" — Create execution phases
+  - "Execute" — Execute the next phase
+  - "Review" — Review executed phase
+
+Based on selection, delegate to the appropriate workflow:
+- Discuss → @~/.claude/specdacular/workflows/discuss.md
+- Research → @~/.claude/specdacular/workflows/research.md
+- Plan → @~/.claude/specdacular/workflows/plan.md
+- Execute → @~/.claude/specdacular/workflows/execute.md
+- Review → @~/.claude/specdacular/workflows/review.md
+
+</execution_context>
+
+<context>
+Arguments: $ARGUMENTS
+
+@~/.claude/specdacular/workflows/discuss.md
+@~/.claude/specdacular/workflows/research.md
+@~/.claude/specdacular/workflows/plan.md
+@~/.claude/specdacular/workflows/execute.md
+@~/.claude/specdacular/workflows/review.md
+</context>
+
+<success_criteria>
+- [ ] Task validated and operation menu shown
+- [ ] Selected operation executed via correct workflow
+</success_criteria>

package/commands/{specd/update.md → specd.update.md}

@@ -1,5 +1,5 @@
 ---
-name: specd:update
+name: specd.update
 description: Update Specdacular to the latest version
 allowed-tools:
   - Bash

package/hooks/specd-statusline.js

@@ -49,7 +49,7 @@ process.stdin.on('end', () => {
       try {
         const cache = JSON.parse(fs.readFileSync(cacheFile, 'utf8'));
         if (cache.update_available) {
-          specdUpdate = '\x1b[33m⬆ /specd:update\x1b[0m │ ';
+          specdUpdate = '\x1b[33m⬆ /specd.update\x1b[0m │ ';
         }
       } catch (e) {}
     }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "specdacular",
-  "version": "0.9.2",
+  "version": "0.10.1",
   "description": "Feature planning system for existing codebases. Map, understand, and plan features in large projects.",
   "bin": {
     "specdacular": "bin/install.js"

package/specdacular/HELP.md

@@ -8,48 +8,52 @@
 
 | Command | Description |
 |---------|-------------|
-| `/specd:new [name]` | Initialize a task, start first discussion |
-| `/specd:continue [name] [--interactive\|--auto]` | Continue task lifecycle — picks up where you left off |
+| `/specd.new [name]` | Initialize a task, start first discussion |
+| `/specd.new-project [name]` | Bootstrap a new project from idea to structured plan |
+| `/specd.continue [name] [--interactive\|--auto]` | Continue task lifecycle — picks up where you left off |
 
-| `/specd:toolbox [tasks <name>\|context]` | Task operations or context management |
+| `/specd.toolbox [<name>]` | Advanced task operations |
 
 ### Utilities
 
 | Command | Description |
 |---------|-------------|
-| `/specd:map-codebase` | Analyze codebase with parallel agents → AI-optimized docs |
-| `/specd:config` | Configure auto-commit settings for docs and code |
-| `/specd:status [--all]` | Show task status dashboard |
-| `/specd:help` | Show this help |
-| `/specd:update` | Update Specdacular to the latest version |
+| `/specd.codebase.map` | Analyze codebase with parallel agents → AI-optimized docs |
+| `/specd.codebase.review` | Review and edit codebase context files section by section |
+| `/specd.config` | Configure auto-commit settings for docs and code |
+| `/specd.status [--all]` | Show task status dashboard |
+| `/specd.help` | Show this help |
+| `/specd.update` | Update Specdacular to the latest version |
 
 ---
 
 ## Task Flow
 
 ```
-/specd:new → /specd:continue → continue → continue → done
+/specd.new → /specd.continue → continue → continue → done
+```
+
+**For new projects (greenfield):**
+```
+/specd.new-project → (questioning → research → requirements → roadmap → scaffold)
 ```
 
 **You only need three commands:**
 
-1. **`/specd:new [name]`** — Start here. Creates task folder, asks initial questions.
-2. **`/specd:continue [name]`** — Picks up where you left off. Drives the entire lifecycle:
+1. **`/specd.new [name]`** — Start here. Creates task folder, asks initial questions.
+2. **`/specd.continue [name]`** — Picks up where you left off. Drives the entire lifecycle:
    - Discussion → Research → Planning → Phase Execution → Review
    - After each step, offers the next step or "stop for now"
    - Works across context windows — reads state fresh each time
    - Modes: default (auto-runs, pauses at phase steps), `--interactive` (prompt at each step), `--auto` (run everything)
-3. **`/specd:toolbox`** — Two subdomains:
-   - **`/specd:toolbox tasks <name>`** — Task operations:
-     - Discuss, Research, Plan, Execute, Review
-   - **`/specd:toolbox context`** — Context management:
-     - Status, Review, Add
+3. **`/specd.toolbox [name]`** — Direct access to task operations: Discuss, Research, Plan, Execute, Review
+4. **`/specd.codebase.review`** — Review and edit codebase context files section by section
 
 ### Quick Start
 
 ```
-/specd:new user-dashboard
-/specd:continue user-dashboard
+/specd.new user-dashboard
+/specd.continue user-dashboard
 ```
 
 After initialization, just keep running `continue`. It figures out what's next.
@@ -121,7 +125,7 @@ Hooks are markdown workflow files that run before and after pipeline steps. They
 ## Codebase Documentation
 
 ```
-/specd:map-codebase
+/specd.codebase.map
 ```
 
 Spawns 4 parallel agents to analyze your codebase and creates `.specd/codebase/`:
@@ -139,7 +143,7 @@ Spawns 4 parallel agents to analyze your codebase and creates `.specd/codebase/`
 
 When an update is available, you'll see `update available` in your statusline. Run:
 ```
-/specd:update
+/specd.update
 ```
 Or manually: `npx specdacular@latest`