spec-kitty-cli 0.7.0__tar.gz → 0.10.9__tar.gz

spec_kitty_cli-0.10.9/.kittify/missions/research/command-templates/implement.md

@@ -0,0 +1,78 @@
+---
+description: Execute the implementation plan by processing and executing all tasks defined in tasks.md
+---
+
+## Work Package Selection
+
+**User specified**: `$ARGUMENTS`
+
+**Your task**: Determine which WP to implement:
+- If `$ARGUMENTS` is empty → Find first WP file with `lane: "planned"` in `tasks/` directory
+- If `$ARGUMENTS` provided → Normalize it:
+  - `wp01` → `WP01`
+  - `WP01` → `WP01`
+  - `WP01-foo-bar` → `WP01`
+  - Then find: `tasks/WP01*.md`
+
+**Once you know which WP**, proceed to setup.
+
+---
+
+## Setup (Do This First)
+
+**1. Move WP to doing lane:**
+```bash
+spec-kitty agent tasks move-task <WPID> --to doing --note "Started implementation" --agent "codex"
+```
+This updates frontmatter, captures shell PID, adds activity log, and creates a commit.
+
+**2. Get the prompt file path:**
+The WP file is at: `kitty-specs/<feature>/tasks/<WPID>-<slug>.md`
+Find the full absolute path.
+
+**3. Verify the move worked:**
+```bash
+git log -1  # Should show "Start <WPID>: Move to doing lane"
+```
+
+---
+
+## Implementation (Do This Second)
+
+**1. READ THE PROMPT FILE** (`tasks/<WPID>-slug.md`)
+   - This is your complete implementation guide
+   - Check `review_status` in frontmatter:
+     - If `has_feedback` → Read `## Review Feedback` section first
+     - Treat action items as your TODO list
+
+**2. Read supporting docs:**
+   - `tasks.md` - Full task breakdown
+   - `plan.md` - Tech stack and architecture
+   - `spec.md` - Requirements
+   - `data-model.md`, `contracts/`, `research.md`, `quickstart.md` (if exist)
+
+**3. Implement following the prompt's guidance:**
+   - Follow subtask order
+   - Respect dependencies (sequential vs parallel `[P]`)
+   - Run tests if required
+   - Commit as you complete major milestones
+
+**4. When complete:**
+```bash
+spec-kitty agent tasks move-task <WPID> --to for_review --note "Ready for review"
+git add <your-changes>
+git commit -m "Complete <WPID>: <description>"
+```
+
+---
+
+## That's It
+
+**Simple workflow:**
+1. Find which WP (from `$ARGUMENTS` or first planned)
+2. Move it to doing
+3. Read the prompt file
+4. Do the work
+5. Move to for_review
+
+**No busywork, no shell PID tracking, just implement.**

{spec_kitty_cli-0.7.0 → spec_kitty_cli-0.10.9}/.kittify/missions/research/command-templates/merge.md

@@ -1,9 +1,5 @@
 ---
 description: Merge a completed feature into the main branch and clean up worktree
-scripts:
-  sh: ".kittify/scripts/bash/merge-feature.sh"
-  ps: ".kittify/scripts/powershell/Merge-Feature.ps1"
----
 
 # Merge Feature Branch
 
@@ -14,7 +10,7 @@ This command merges a completed feature branch into the main/target branch and h
 Before running this command:
 
 1. ✅ Feature must pass `/spec-kitty.accept` checks
-2. ✅ All work packages must be in `tasks/done/`
+2. ✅ All work packages must be in `tasks/`
 3. ✅ Working directory must be clean (no uncommitted changes)
 4. ✅ You must be on the feature branch (or in its worktree)
 
@@ -23,14 +19,6 @@ Before running this command:
 Before merging, verify you are in the correct working directory by running the shared pre-flight validation:
 
 ```python
-from specify_cli.guards import validate_worktree_location
-
-# Validate location
-result = validate_worktree_location()
-if not result.is_valid:
-    print(result.format_error())
-    print("\nThis command MUST run from a feature worktree, not the main repository.")
-    exit(1)
 ```
 
 **What this validates**:

{spec_kitty_cli-0.7.0/.kittify/missions/software-dev → spec_kitty_cli-0.10.9/.kittify/missions/research}/command-templates/plan.md

@@ -1,12 +1,5 @@
 ---
 description: Execute the implementation planning workflow using the plan template to generate design artifacts.
-scripts:
-  sh: scripts/bash/setup-plan.sh --json
-  ps: scripts/powershell/setup-plan.ps1 -Json
-agent_scripts:
-  sh: scripts/bash/update-agent-context.sh __AGENT__
-  ps: scripts/powershell/update-agent-context.ps1 -AgentType __AGENT__
----
 
 ## User Input
 
@@ -21,14 +14,6 @@ You **MUST** consider the user input before proceeding (if not empty).
 Before proceeding with planning, verify you are in the correct working directory by running the shared pre-flight validation:
 
 ```python
-from specify_cli.guards import validate_worktree_location
-
-# Validate location
-result = validate_worktree_location()
-if not result.is_valid:
-    print(result.format_error())
-    print("\nThis command MUST run from a feature worktree, not the main repository.")
-    exit(1)
 ```
 
 **What this validates**:

{spec_kitty_cli-0.7.0 → spec_kitty_cli-0.10.9}/.kittify/missions/research/command-templates/review.md

@@ -1,9 +1,5 @@
 ---
 description: Perform structured research review with citation validation.
-scripts:
-  sh: scripts/bash/check-prerequisites.sh --json --include-tasks
-  ps: scripts/powershell/check-prerequisites.ps1 -Json -IncludeTasks
----
 
 ## User Input
 
@@ -18,14 +14,6 @@ You **MUST** consider the user input before proceeding (if not empty).
 Before proceeding with review, verify you are in the correct working directory by running the shared pre-flight validation:
 
 ```python
-from specify_cli.guards import validate_worktree_location
-
-# Validate location
-result = validate_worktree_location()
-if not result.is_valid:
-    print(result.format_error())
-    print("\nThis command MUST run from a feature worktree, not the main repository.")
-    exit(1)
 ```
 
 **What this validates**:
@@ -76,8 +64,8 @@ if source_register.exists():
 1. Run `{SCRIPT}` from repo root; capture `FEATURE_DIR`, `AVAILABLE_DOCS`, and `tasks.md` path.
 
 2. Determine the review target:
-   - If user input specifies a filename, validate it exists under `tasks/for_review/` (support phase subdirectories).
-   - Otherwise, select the oldest file in `tasks/for_review/` (lexical order is sufficient because filenames retain task ordering).
+   - If user input specifies a filename, validate it exists under `tasks/` (flat structure, check `lane: "for_review"` in frontmatter).
+   - Otherwise, select the oldest file in `tasks/` (lexical order is sufficient because filenames retain task ordering).
    - Abort with instructional message if no files are waiting for review.
 
 3. Load context for the selected task:
@@ -96,15 +84,15 @@ if source_register.exists():
      * Append a new entry in the prompt’s **Activity Log** detailing feedback (include timestamp, reviewer agent, shell PID).
      * Update frontmatter `lane` back to `planned`, clear `assignee` if necessary, keep history entry.
      * Add/revise a `## Review Feedback` section (create if missing) summarizing action items.
-     * Run `.kittify/scripts/bash/tasks-move-to-lane.sh <FEATURE> <TASK_ID> planned --note "Returned for changes"` (use the PowerShell equivalent on Windows) so the move and history update are staged consistently.
+     * Run `spec-kitty agent tasks move-task <FEATURE> <TASK_ID> planned --note "Returned for changes"` (use the PowerShell equivalent on Windows) so the move and history update are staged consistently.
   - **Approved**:
      * Append Activity Log entry capturing approval details (capture shell PID via `echo $$` or helper script).
      * Update frontmatter: set `lane=done`, set reviewer metadata (`agent`, `shell_pid`), optional `assignee` for approver.
      * Use helper script to mark the task complete in `tasks.md` (see Step 6).
-     * Run `.kittify/scripts/bash/tasks-move-to-lane.sh <FEATURE> <TASK_ID> done --note "Approved for release"` (PowerShell variant available) to transition the prompt into `tasks/done/`.
+     * Run `spec-kitty agent tasks move-task <FEATURE> <TASK_ID> done --note "Approved for release"` (PowerShell variant available) to transition the prompt into `tasks/`.
 
 6. Update `tasks.md` automatically:
-   - Run `scripts/bash/mark-task-status.sh --task-id <TASK_ID> --status done` (POSIX) or `scripts/powershell/Set-TaskStatus.ps1 -TaskId <TASK_ID> -Status done` (PowerShell) from repo root.
+   - Run `spec-kitty agent tasks mark-status --task-id <TASK_ID> --status done` (POSIX) or `spec-kitty agent tasks mark-status --task-id <TASK_ID> --status done` (PowerShell) from repo root.
    - Confirm the task entry now shows `[X]` and includes a reference to the prompt file in its notes.
 
 7. Produce a review report summarizing:

{spec_kitty_cli-0.7.0 → spec_kitty_cli-0.10.9}/.kittify/missions/research/templates/tasks-template.md

@@ -28,7 +28,7 @@ description: "Work package task list template for research methodology execution
 
 **Goal**: Identify and collect all relevant sources for the research question.  
 **Independent Test**: `research/source-register.csv` contains the minimum required high-quality sources with relevance ratings.  
-**Prompt**: `/tasks/planned/WP01-literature-search.md`
+**Prompt**: `/tasks/WP01-literature-search.md`
 
 ### Included Subtasks
 - [ ] T001 Define search keywords and inclusion/exclusion criteria
@@ -49,7 +49,7 @@ description: "Work package task list template for research methodology execution
 
 **Goal**: Review prioritized sources and extract key findings.  
 **Independent Test**: `research/evidence-log.csv` contains findings from all high-relevance sources with confidence levels.  
-**Prompt**: `/tasks/planned/WP02-source-review.md`
+**Prompt**: `/tasks/WP02-source-review.md`
 
 ### Included Subtasks
 - [ ] T008 [P] Review high-relevance sources (parallelizable by researcher/source)
@@ -68,7 +68,7 @@ description: "Work package task list template for research methodology execution
 
 **Goal**: Synthesize findings and answer the research question.  
 **Independent Test**: findings.md contains synthesized conclusions backed by citations.  
-**Prompt**: `/tasks/planned/WP03-analysis-synthesis.md`
+**Prompt**: `/tasks/WP03-analysis-synthesis.md`
 
 ### Included Subtasks
 - [ ] T013 Code findings by theme/category

{spec_kitty_cli-0.7.0 → spec_kitty_cli-0.10.9}/.kittify/missions/software-dev/command-templates/accept.md

@@ -1,9 +1,5 @@
 ---
 description: Validate feature readiness and guide final acceptance steps.
-scripts:
-  sh: .kittify/scripts/bash/accept-feature.sh --json {ARGS}
-  ps: .kittify/scripts/powershell/accept-feature.ps1 --json {ARGS}
----
 
 ## User Input
 

{spec_kitty_cli-0.7.0 → spec_kitty_cli-0.10.9}/.kittify/missions/software-dev/command-templates/analyze.md

@@ -1,9 +1,5 @@
 ---
 description: Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
-scripts:
-  sh: scripts/bash/check-prerequisites.sh --json --require-tasks --include-tasks
-  ps: scripts/powershell/check-prerequisites.ps1 -Json -RequireTasks -IncludeTasks
----
 
 ## User Input
 

{spec_kitty_cli-0.7.0 → spec_kitty_cli-0.10.9}/.kittify/missions/software-dev/command-templates/checklist.md

@@ -1,9 +1,5 @@
 ---
 description: Generate a custom checklist for the current feature based on user requirements.
-scripts:
-  sh: scripts/bash/check-prerequisites.sh --json
-  ps: scripts/powershell/check-prerequisites.ps1 -Json
----
 
 ## Checklist Purpose: "Unit Tests for English"
 

{spec_kitty_cli-0.7.0 → spec_kitty_cli-0.10.9}/.kittify/missions/software-dev/command-templates/clarify.md

@@ -1,9 +1,5 @@
 ---
 description: Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
-scripts:
-   sh: scripts/bash/check-prerequisites.sh --json --paths-only
-   ps: scripts/powershell/check-prerequisites.ps1 -Json -PathsOnly
----
 
 ## User Input
 

spec_kitty_cli-0.10.9/.kittify/missions/software-dev/command-templates/implement.md

@@ -0,0 +1,11 @@
+---
+description: Execute the implementation plan by processing and executing all tasks defined in tasks.md
+---
+
+Run this command to get your work package prompt and instructions:
+
+```bash
+spec-kitty agent workflow implement $ARGUMENTS
+```
+
+If no WP ID is provided, it will automatically find the first work package with `lane: "planned"` and move it to "doing" for you.

{spec_kitty_cli-0.7.0 → spec_kitty_cli-0.10.9}/.kittify/missions/software-dev/command-templates/merge.md

@@ -1,9 +1,5 @@
 ---
 description: Merge a completed feature into the main branch and clean up worktree
-scripts:
-  sh: ".kittify/scripts/bash/merge-feature.sh"
-  ps: ".kittify/scripts/powershell/Merge-Feature.ps1"
----
 
 # Merge Feature Branch
 
@@ -14,7 +10,7 @@ This command merges a completed feature branch into the main/target branch and h
 Before running this command:
 
 1. ✅ Feature must pass `/spec-kitty.accept` checks
-2. ✅ All work packages must be in `tasks/done/`
+2. ✅ All work packages must be in `tasks/`
 3. ✅ Working directory must be clean (no uncommitted changes)
 4. ✅ You must be on the feature branch (or in its worktree)
 
@@ -23,14 +19,6 @@ Before running this command:
 Before merging, verify you are in the correct working directory by running the shared pre-flight validation:
 
 ```python
-from specify_cli.guards import validate_worktree_location
-
-# Validate location
-result = validate_worktree_location()
-if not result.is_valid:
-    print(result.format_error())
-    print("\nThis command MUST run from a feature worktree, not the main repository.")
-    exit(1)
 ```
 
 **What this validates**:

{spec_kitty_cli-0.7.0/templates → spec_kitty_cli-0.10.9/.kittify/missions/software-dev}/command-templates/plan.md

@@ -1,14 +1,6 @@
 ---
 description: Execute the implementation planning workflow using the plan template to generate design artifacts.
-scripts:
-  sh: scripts/bash/setup-plan.sh --json
-  ps: scripts/powershell/setup-plan.ps1 -Json
-agent_scripts:
-  sh: scripts/bash/update-agent-context.sh __AGENT__
-  ps: scripts/powershell/update-agent-context.ps1 -AgentType __AGENT__
 ---
-*Path: [templates/commands/plan.md](templates/commands/plan.md)*
-
 
 ## User Input
 
@@ -20,29 +12,18 @@ You **MUST** consider the user input before proceeding (if not empty).
 
 ## Location Pre-flight Check (CRITICAL for AI Agents)
 
-Before proceeding with planning, verify you are in the correct working directory:
+Before proceeding with planning, verify you are in the correct working directory by running the shared pre-flight validation:
 
-**Check your current branch:**
-```bash
-git branch --show-current
+```python
 ```
 
-**Expected output:** A feature branch like `001-feature-name`
-**If you see `main`:** You are in the wrong location!
-
-**This command MUST run from a feature worktree, not the main repository.**
+**What this validates**:
+- Current branch follows the feature pattern like `001-feature-name`
+- You're not attempting to run from `main` or any release branch
+- The validator prints clear navigation instructions if you're outside the feature worktree
 
-If you're on the `main` branch:
-1. Check for available worktrees: `ls .worktrees/`
-2. Navigate to the appropriate feature worktree: `cd .worktrees/<feature-name>`
-3. Verify you're in the right place: `git branch --show-current` should show the feature branch
-4. Then re-run this command
-
-The script will fail if you're not in a feature worktree.
 **Path reference rule:** When you mention directories or files, provide either the absolute path or a path relative to the project root (for example, `kitty-specs/<feature>/tasks/`). Never refer to a folder by name alone.
 
-This is intentional - worktrees provide isolation for parallel feature development.
-
 ## Planning Interrogation (mandatory)
 
 Before executing any scripts or generating artifacts you must interrogate the specification and stakeholders.
@@ -73,10 +54,13 @@ Planning requirements (scale to complexity):
 ## Outline
 
 1. **Check planning discovery status**:
-   - If any planning questions remain unanswered or the user has not confirmed the **Engineering Alignment** summary, stay in the one-question cadence, capture the user’s response, update your internal table, and end with `WAITING_FOR_PLANNING_INPUT`. Do **not** surface the table. Do **not** run `{SCRIPT}` yet.
+   - If any planning questions remain unanswered or the user has not confirmed the **Engineering Alignment** summary, stay in the one-question cadence, capture the user's response, update your internal table, and end with `WAITING_FOR_PLANNING_INPUT`. Do **not** surface the table. Do **not** run the setup command yet.
    - Once every planning question has a concrete answer and the alignment summary is confirmed by the user, continue.
 
-2. **Setup**: Run `{SCRIPT}` from repo root and parse JSON for FEATURE_SPEC, IMPL_PLAN, SPECS_DIR, BRANCH.
+2. **Setup**: Run `spec-kitty agent feature setup-plan --json` from the worktree root and parse JSON for:
+   - `result`: "success" or error message
+   - `plan_file`: Absolute path to the created plan.md
+   - `feature_dir`: Absolute path to the feature directory
 
 3. **Load context**: Read FEATURE_SPEC and `.kittify/memory/constitution.md`. Load IMPL_PLAN template (already copied).
 
@@ -84,19 +68,19 @@ Planning requirements (scale to complexity):
    - Update Technical Context with explicit statements from the user or discovery research; mark `[NEEDS CLARIFICATION: …]` only when the user deliberately postpones a decision
    - Fill Constitution Check section from constitution and challenge any conflicts directly with the user
    - Evaluate gates (ERROR if violations unjustified or questions remain unanswered)
-   - Phase 0: Run `spec-kitty research` (or `/spec-kitty.research`) to scaffold research.md, data-model.md, and research CSV logs, then populate findings using the validated planning answers
-   - Phase 1: Generate data-model.md, contracts/, quickstart.md based on confirmed intent (building on the Phase 0 outputs)
+   - Phase 0: Generate research.md (commission research to resolve every outstanding clarification)
+   - Phase 1: Generate data-model.md, contracts/, quickstart.md based on confirmed intent
    - Phase 1: Update agent context by running the agent script
    - Re-evaluate Constitution Check post-design, asking the user to resolve new gaps before proceeding
 
-5. **Stop and report**: Command ends after Phase 2 planning. Report branch, IMPL_PLAN path, and generated artifacts.
+5. **STOP and report**: This command ends after Phase 1 planning. Report branch, IMPL_PLAN path, and generated artifacts.
+
+   **⚠️ CRITICAL: DO NOT proceed to task generation!** The user must explicitly run `/spec-kitty.tasks` to generate work packages. Your job is COMPLETE after reporting the planning artifacts.
 
 ## Phases
 
 ### Phase 0: Outline & Research
 
-> Kick off this phase by running `spec-kitty research` to scaffold the mission-specific files listed below. Then use the checklist to enrich each artifact with the clarifications uncovered during planning.
-
 1. **Extract unknowns from Technical Context** above:
    - For each NEEDS CLARIFICATION → research task
    - For each dependency → best practices task
@@ -144,3 +128,28 @@ Planning requirements (scale to complexity):
 
 - Use absolute paths
 - ERROR on gate failures or unresolved clarifications
+
+---
+
+## ⛔ MANDATORY STOP POINT
+
+**This command is COMPLETE after generating planning artifacts.**
+
+After reporting:
+- `plan.md` path
+- `research.md` path (if generated)
+- `data-model.md` path (if generated)
+- `contracts/` contents (if generated)
+- Agent context file updated
+
+**YOU MUST STOP HERE.**
+
+Do NOT:
+- ❌ Generate `tasks.md`
+- ❌ Create work package (WP) files
+- ❌ Create `tasks/` subdirectories
+- ❌ Proceed to implementation
+
+The user will run `/spec-kitty.tasks` when they are ready to generate work packages.
+
+**Next suggested command**: `/spec-kitty.tasks` (user must invoke this explicitly)

spec_kitty_cli-0.10.9/.kittify/missions/software-dev/command-templates/review.md

@@ -0,0 +1,11 @@
+---
+description: Perform structured code review and kanban transitions for completed task prompt files
+---
+
+Run this command to get the work package prompt and review instructions:
+
+```bash
+spec-kitty agent workflow review $ARGUMENTS
+```
+
+If no WP ID is provided, it will automatically find the first work package with `lane: "for_review"` and move it to "doing" for you.

{spec_kitty_cli-0.7.0 → spec_kitty_cli-0.10.9}/.kittify/missions/software-dev/command-templates/specify.md

@@ -1,8 +1,5 @@
 ---
 description: Create or update the feature specification from a natural language feature description.
-scripts:
-  sh: .kittify/scripts/bash/create-new-feature.sh --json "{ARGS}"
-  ps: .kittify/scripts/powershell/create-new-feature.ps1 -Json "{ARGS}"
 ---
 
 ## User Input
@@ -40,6 +37,42 @@ Discovery requirements (scale to feature complexity):
 3. When you have sufficient context for the feature's scope, paraphrase into an **Intent Summary** and confirm. For trivial features, this can be very brief.
 4. If user explicitly asks to skip questions or says "just testing", acknowledge and proceed with minimal discovery.
 
+## Mission Selection
+
+After completing discovery and confirming the Intent Summary, determine the appropriate mission for this feature.
+
+### Available Missions
+
+- **software-dev**: For building software features, APIs, CLI tools, applications
+  - Phases: research → design → implement → test → review
+  - Best for: code changes, new features, bug fixes, refactoring
+
+- **research**: For investigations, literature reviews, technical analysis
+  - Phases: question → methodology → gather → analyze → synthesize → publish
+  - Best for: feasibility studies, market research, technology evaluation
+
+### Mission Inference
+
+1. **Analyze the feature description** to identify the primary goal:
+   - Building, coding, implementing, creating software → **software-dev**
+   - Researching, investigating, analyzing, evaluating → **research**
+
+2. **Check for explicit mission requests** in the user's description:
+   - If user mentions "research project", "investigation", "analysis" → use research
+   - If user mentions "build", "implement", "create feature" → use software-dev
+
+3. **Confirm with user** (unless explicit):
+   > "Based on your description, this sounds like a **[software-dev/research]** project.
+   > I'll use the **[mission name]** mission. Does that work for you?"
+
+4. **Handle user response**:
+   - If confirmed: proceed with selected mission
+   - If user wants different mission: use their choice
+
+5. **Handle --mission flag**: If the user provides `--mission <key>` in their command, skip inference and use the specified mission directly.
+
+Store the final mission selection to pass to the script via `--mission "<selected-mission>"`.
+
 ## Outline
 
 ### 0. Generate a Friendly Feature Title
@@ -56,44 +89,60 @@ Given that feature description, do this:
 - **Interactive Interview Mode (no arguments)**: Use the discovery interview to elicit all necessary context, synthesize the working feature description, and confirm it with the user before you generate any specification artifacts.
 
 1. **Check discovery status**:
-   - If this is your first message or discovery questions remain unanswered, stay in the one-question loop, capture the user’s response, update your internal table, and end with `WAITING_FOR_DISCOVERY_INPUT`. Do **not** surface the table; keep it internal. Do **not** call `{SCRIPT}` yet.
+   - If this is your first message or discovery questions remain unanswered, stay in the one-question loop, capture the user's response, update your internal table, and end with `WAITING_FOR_DISCOVERY_INPUT`. Do **not** surface the table; keep it internal. Do **not** call the creation command yet.
    - Only proceed once every discovery question has an explicit answer and the user has acknowledged the Intent Summary.
-   - Empty invocation rule: stay in interview mode until you can restate the agreed-upon feature description. Do **not** call `{SCRIPT}` while the description is missing or provisional.
-
-2. When discovery is complete and the intent summary **and title** are confirmed, run the script `{SCRIPT}` from repo root, inserting `--feature-name "<Friendly Title>"` (replace the quoted text with the confirmed title) immediately before the feature description argument. For example:
-
-   - **bash/zsh**: `.kittify/scripts/bash/create-new-feature.sh --json --feature-name "Checkout Upsell Flow" "$ARGUMENTS"`
-   - **PowerShell**: `.kittify/scripts/powershell/create-new-feature.ps1 -Json -FeatureName "Checkout Upsell Flow" "$ARGUMENTS"`
-
-   Parse its JSON output for `BRANCH_NAME`, `SPEC_FILE`, `FEATURE_NUM`, and `FRIENDLY_NAME`. All file paths must be absolute.
-
-   **IMPORTANT** You must only ever run this script once. The JSON is provided in the terminal as output - always refer to it to get the actual content you're looking for.
-3. Load `templates/spec-template.md` to understand required sections.
-
-4. Follow this execution flow:
-
-    1. Use the discovery answers as your authoritative source of truth (do **not** rely on raw `$ARGUMENTS`). For empty invocations, treat the synthesized interview summary as the canonical feature description and propagate the confirmed friendly title anywhere `[FEATURE NAME]` appears.
-       Identify: actors, actions, data, constraints, motivations, success metrics
-    2. For any remaining ambiguity:
-       - Ask the user a focused follow-up question immediately and halt work until they answer
-       - Only use `[NEEDS CLARIFICATION: …]` when the user explicitly defers the decision
-       - Record any interim assumption in the Assumptions section and flag it for confirmation later
-       - Prioritize clarifications by impact: scope > outcomes > risks/security > user experience > technical details
-    4. Fill User Scenarios & Testing section
-       If no clear user flow: ERROR "Cannot determine user scenarios"
-    5. Generate Functional Requirements
-       Each requirement must be testable
-       Use reasonable defaults for unspecified details (document assumptions in Assumptions section)
-    6. Define Success Criteria
-       Create measurable, technology-agnostic outcomes
-       Include both quantitative metrics (time, performance, volume) and qualitative measures (user satisfaction, task completion)
-       Each criterion must be verifiable without implementation details
-    7. Identify Key Entities (if data involved)
-    8. Return: SUCCESS (spec ready for planning)
-
-4. Write the specification to SPEC_FILE using the template structure, replacing placeholders with concrete details derived from the feature description (arguments) while preserving section order and headings.
-
-5. **Specification Quality Validation**: After writing the initial spec, validate it against quality criteria:
+   - Empty invocation rule: stay in interview mode until you can restate the agreed-upon feature description. Do **not** call the creation command while the description is missing or provisional.
+
+2. When discovery is complete and the intent summary, **title**, and **mission** are confirmed, run the feature creation command from repo root:
+
+   ```bash
+   spec-kitty agent feature create-feature "<slug>" --json
+   ```
+
+   Where `<slug>` is a kebab-case version of the friendly title (e.g., "Checkout Upsell Flow" → "checkout-upsell-flow").
+
+   The command returns JSON with:
+   - `result`: "success" or error message
+   - `feature`: Feature number and slug (e.g., "014-checkout-upsell-flow")
+   - `worktree_path`: Absolute path to the created worktree
+   - `feature_dir`: Absolute path to the feature directory inside the worktree
+
+   Parse these values for use in subsequent steps. All file paths are absolute.
+
+   **IMPORTANT**: You must only ever run this command once. The JSON is provided in the terminal output - always refer to it to get the actual paths you're looking for.
+3. **Navigate to the worktree**: After feature creation, change directory to the worktree path returned by the command.
+
+4. Load the spec template from `.kittify/templates/spec-template.md` (or `templates/spec-template.md`) to understand required sections.
+
+5. Create meta.json in the feature directory with:
+   ```json
+   {
+     "feature_number": "<number>",
+     "slug": "<full-slug>",
+     "friendly_name": "<Friendly Title>",
+     "mission": "<selected-mission>",
+     "source_description": "$ARGUMENTS",
+     "created_at": "<ISO timestamp>"
+   }
+   ```
+
+6. Generate the specification content by following this flow:
+    - Use the discovery answers as your authoritative source of truth (do **not** rely on raw `$ARGUMENTS`)
+    - For empty invocations, treat the synthesized interview summary as the canonical feature description
+    - Identify: actors, actions, data, constraints, motivations, success metrics
+    - For any remaining ambiguity:
+      * Ask the user a focused follow-up question immediately and halt work until they answer
+      * Only use `[NEEDS CLARIFICATION: …]` when the user explicitly defers the decision
+      * Record any interim assumption in the Assumptions section
+      * Prioritize clarifications by impact: scope > outcomes > risks/security > user experience > technical details
+    - Fill User Scenarios & Testing section (ERROR if no clear user flow can be determined)
+    - Generate Functional Requirements (each requirement must be testable)
+    - Define Success Criteria (measurable, technology-agnostic outcomes)
+    - Identify Key Entities (if data involved)
+
+7. Write the specification to `<feature_dir>/spec.md` using the template structure, replacing placeholders with concrete details derived from the feature description while preserving section order and headings.
+
+8. **Specification Quality Validation**: After writing the initial spec, validate it against quality criteria:
 
    a. **Create Spec Quality Checklist**: Generate a checklist file at `FEATURE_DIR/checklists/requirements.md` using the checklist template structure with these validation items:
    
@@ -169,7 +218,7 @@ Given that feature description, do this:
    
    d. **Update Checklist**: After each validation iteration, update the checklist file with current pass/fail status
 
-6. Report completion with branch name, spec file path, checklist results, and readiness for the next phase (`/spec-kitty.clarify` or `/spec-kitty.plan`).
+9. Report completion with worktree path, feature directory, spec file path, checklist results, and readiness for the next phase (`/spec-kitty.clarify` or `/spec-kitty.plan`).
 
 **NOTE:** The script creates and checks out the new branch and initializes the spec file before writing.