claude-code-orchestrator-kit 1.4.0 → 1.4.15

package/.claude/commands/speckit.implement.md

@@ -17,13 +17,6 @@ You **MUST** consider the user input before proceeding (if not empty).
 
 ## Outline
 
-0. **Session Check** (DeksdenFlow):
-   - Invoke `resume-session` skill to check for existing session
-   - If valid session found: ask user "Resume previous session or start fresh?"
-   - If resume: load context.md and session-log.md, jump to saved phase
-   - If fresh or no session: proceed to step 1
-   - **Also**: Invoke `load-project-context` skill to load project structure map
-
 1. Run `.specify/scripts/bash/check-prerequisites.sh --json --require-tasks --include-tasks` from repo root and parse FEATURE_DIR and AVAILABLE_DOCS list. All paths must be absolute. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot").
 
 2. **Check checklists status** (if FEATURE_DIR/checklists/ exists):
@@ -192,10 +185,6 @@ You **MUST** consider the user input before proceeding (if not empty).
    - Provide clear error messages with context for debugging
    - Suggest next steps if implementation cannot proceed
    - **IMPORTANT** For completed tasks, make sure to mark the task off as [X] in the tasks file
-   - **Session Context** (DeksdenFlow):
-     * After completing each PHASE (not task): invoke `save-session-context` skill
-     * On error or pause: save context before stopping
-     * Log significant decisions to session-log.md (architecture choices, issue resolutions)
    - **Critical Rules**:
      * NEVER skip verification
      * NEVER proceed if task failed

package/.claude/commands/speckit.taskstoissues.md

@@ -1,6 +1,5 @@
 ---
 description: Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.
-tools: ['github/github-mcp-server/issue_write']
 scripts:
   sh: .specify/scripts/bash/check-prerequisites.sh --json --require-tasks --include-tasks
   ps: .specify/scripts/powershell/check-prerequisites.ps1 -Json -RequireTasks -IncludeTasks
@@ -18,18 +17,109 @@ You **MUST** consider the user input before proceeding (if not empty).
 
 1. Run `.specify/scripts/bash/check-prerequisites.sh --json --require-tasks --include-tasks` from repo root and parse FEATURE_DIR and AVAILABLE_DOCS list. All paths must be absolute. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot").
 
-2. From the executed script, extract the path to **tasks**.
+2. From the executed script, extract the path to **tasks.md**.
 
-3. Get the Git remote by running:
+3. **Verify GitHub remote**:
 
 ```bash
 git config --get remote.origin.url
 ```
 
 > [!CAUTION]
-> ONLY PROCEED TO NEXT STEPS IF THE REMOTE IS A GITHUB URL
+> ONLY PROCEED TO NEXT STEPS IF THE REMOTE IS A GITHUB URL (contains `github.com`)
 
-4. For each task in the list, use the GitHub MCP server to create a new issue in the repository that is representative of the Git remote.
+4. **Check `gh` CLI availability**:
+
+```bash
+gh --version
+```
+
+If `gh` is not installed, inform the user:
+```
+GitHub CLI (gh) is not installed. Install it:
+- macOS: brew install gh
+- Ubuntu: sudo apt install gh
+- Windows: winget install GitHub.cli
+
+Then authenticate: gh auth login
+```
+
+5. **Verify authentication**:
+
+```bash
+gh auth status
+```
+
+If not authenticated, prompt user to run `gh auth login`.
+
+6. **Parse tasks.md** and extract all incomplete tasks:
+   - Tasks matching `- [ ] T### ...` pattern
+   - Extract: Task ID, description, phase, parallel marker [P], user story [US#]
+
+7. **For each task, create a GitHub issue** using `gh` CLI:
+
+```bash
+gh issue create \
+  --title "T001: Create project structure" \
+  --body "## Task Details
+
+**ID**: T001
+**Phase**: Setup
+**Parallel**: No
+**User Story**: N/A
+
+### Description
+Create project structure per implementation plan
+
+### Acceptance Criteria
+- [ ] Task completed as specified in tasks.md
+
+---
+*Generated from tasks.md by /speckit.taskstoissues*" \
+  --label "speckit"
+```
+
+**Formatting rules**:
+- Title: `T###: <short description>`
+- Body: Task details, phase, parallel info, acceptance criteria
+- Label: `speckit` (create if doesn't exist)
+- Optional labels based on phase: `setup`, `foundational`, `user-story`, `polish`
+
+8. **Create labels if needed** (first run only):
+
+```bash
+gh label create speckit --description "Generated from spec-kit tasks" --color "0052CC" 2>/dev/null || true
+gh label create setup --description "Setup phase task" --color "C5DEF5" 2>/dev/null || true
+gh label create user-story --description "User story implementation" --color "D4C5F9" 2>/dev/null || true
+```
+
+9. **Report results**:
+   - Number of issues created
+   - Links to created issues
+   - Any errors encountered
 
 > [!CAUTION]
 > UNDER NO CIRCUMSTANCES EVER CREATE ISSUES IN REPOSITORIES THAT DO NOT MATCH THE REMOTE URL
+
+## Options
+
+User can specify in `$ARGUMENTS`:
+- `--dry-run` — показать какие issues будут созданы, но не создавать
+- `--phase N` — создать issues только для Phase N
+- `--limit N` — создать только первые N issues
+
+## Examples
+
+```bash
+# Создать issues для всех задач
+/speckit.taskstoissues
+
+# Только показать что будет создано
+/speckit.taskstoissues --dry-run
+
+# Только Phase 1 (Setup)
+/speckit.taskstoissues --phase 1
+
+# Первые 5 задач
+/speckit.taskstoissues --limit 5
+```

package/.claude/commands/worktree.md

@@ -0,0 +1,150 @@
+---
+description: Manage git worktrees for parallel feature development (create, remove, list, cleanup)
+---
+
+# Git Worktree Manager
+
+Manage git worktrees for parallel feature development.
+
+## Usage
+
+```bash
+/worktree create <feature-name> [base-branch]
+/worktree remove <feature-name> [--force] [--delete-branch]
+/worktree list
+/worktree cleanup [--dry-run] [--remove-dirs]
+```
+
+---
+
+## Commands
+
+### create
+
+Create new worktree for parallel development.
+
+**What it does:**
+- Creates `megacampus2-worktrees/` directory (if not exists)
+- Creates new branch `feature/<name>` from base
+- Creates worktree in separate directory
+- Copies gitignored files per `.worktree-sync.json`
+
+**Process:**
+1. Validate feature name (alphanumeric, hyphens only)
+2. Check for uncommitted changes (warn if present)
+3. Create worktree: `git worktree add ../megacampus2-worktrees/<name> -b feature/<name> <base>`
+4. Sync files from `.worktree-sync.json`:
+   - `sync.files`: `.env`, `.env.local`, `.mcp.json`, etc.
+   - `sync.directories`: `.vscode`
+   - `sync.patterns`: `packages/*/.env`, `services/*/.env`
+5. Output next steps (open in IDE, commit workflow)
+
+**Errors:**
+- Worktree exists: suggest different name or remove existing
+- Branch exists: checkout existing or use different name
+
+---
+
+### remove
+
+Remove worktree and optionally delete branch.
+
+**What it does:**
+- Checks for uncommitted changes
+- Removes worktree directory
+- Optionally deletes local and remote branch
+- Runs `git worktree prune`
+
+**Process:**
+1. Find worktree by name
+2. Check git status (if uncommitted changes, require --force or user choice)
+3. Remove: `git worktree remove [--force] <path>`
+4. If --delete-branch:
+   - Check if merged: `git branch --merged main | grep feature/<name>`
+   - Delete local: `git branch -d/-D feature/<name>`
+   - Delete remote: `git push origin --delete feature/<name>`
+5. Cleanup: `git worktree prune`
+
+**Errors:**
+- Not found: show available worktrees
+- Main worktree: cannot remove
+- Uncommitted changes: offer commit/force/cancel
+- Unmerged branch: warn, offer PR/force/keep-branch
+
+---
+
+### list
+
+Show all worktrees with status.
+
+**Output:**
+```
+# Git Worktrees (N total)
+
+| Name | Branch | Path | Status |
+|------|--------|------|--------|
+| main (основной) | main | /home/me/code/megacampus2 | Active |
+| feature-name | feature/feature-name | .../megacampus2-worktrees/feature-name | Active |
+
+Commands: /worktree create <name> | /worktree remove <name>
+```
+
+**Process:**
+1. Run `git worktree list --porcelain`
+2. For each worktree: extract path, branch, HEAD, status (locked/prunable)
+3. Format table with status indicators
+
+---
+
+### cleanup
+
+Clean up stale worktree files and orphaned directories.
+
+**What it does:**
+- Prunes administrative files for deleted worktrees
+- Repairs recoverable worktrees
+- Removes orphaned directories (with --remove-dirs)
+
+**Process:**
+1. Dry-run check: `git worktree prune --dry-run --verbose`
+2. Find orphaned dirs in `megacampus2-worktrees/` not in `git worktree list`
+3. Try repair: `git worktree repair <path>`
+4. If not --dry-run: `git worktree prune --verbose`
+5. If --remove-dirs: remove orphaned/empty directories
+
+**Output:**
+```
+# Worktree Cleanup Report
+
+✅ Pruned administrative records: N
+✅ Removed directories: N (--remove-dirs)
+✅ Recovered worktrees: N
+
+Active worktrees: N
+All valid: ✅
+```
+
+---
+
+## File Sync Config
+
+`.worktree-sync.json` format:
+```json
+{
+  "sync": {
+    "files": [".env", ".env.local", ".mcp.json"],
+    "directories": [".vscode"],
+    "patterns": ["packages/*/.env", "services/*/.env"]
+  }
+}
+```
+
+---
+
+## Notes
+
+- Worktrees share `.git` → saves disk space
+- Each worktree must be on unique branch
+- Cannot checkout same branch in multiple worktrees
+- Main worktree cannot be removed
+- Use --dry-run with cleanup to preview changes