approve
Approve the current PRD and begin parallel story execution. Analyzes dependencies, creates execution batches, launches background Task agents for each story,…
Complete the mega-plan by cleaning up planning files. All features should already be merged via mega-approve. Usage: /plan-cascade:mega-complete
> /plugin marketplace add Taoidle/plan-cascade > /plugin install plan-cascade@plan-cascade
How it fires
How this command gets triggered: by you, by Claude, or both.
/mega-completeContext preview
What this command does when you run it.
Complete the mega-plan by cleaning up planning files. All features should already be merged via mega-approve. Usage: /plan-cascade:mega-complete
description: "Complete the mega-plan by cleaning up planning files. All features should already be merged via mega-approve. Usage: /plan-cascade:mega-complete"
Complete the mega-plan by cleaning up remaining planning files.
**Note**: In the new batch-by-batch execution model, code merging happens automatically when each batch completes (via `mega-approve`). This command only performs final cleanup.
This command works with both new and legacy path storage modes:
Cleanup removes files from user data directory:
Cleanup removes files from project root:
The command auto-detects which mode is active.
# Get mega-plan path from PathResolver
MEGA_PLAN_PATH=$(uv run python -c "from plan_cascade.state.path_resolver import PathResolver; from pathlib import Path; print(PathResolver(Path.cwd()).get_mega_plan_path())" 2>/dev/null || echo "mega-plan.json")
if [ ! -f "$MEGA_PLAN_PATH" ]; then
echo "No mega-plan.json found at: $MEGA_PLAN_PATH"
echo "Nothing to complete."
exit 0
fiRead `.mega-status.json` and `mega-plan.json` to verify: 1. All batches have been completed 2. All features have been merged
If any batches are still pending:
============================================================
CANNOT COMPLETE - BATCHES PENDING
============================================================
The following batches have not been completed:
Batch 2:
[ ] feature-003: Shopping Cart
[ ] feature-004: Order Processing
Complete remaining batches first:
/plan-cascade:mega-approve
Then run this command again.
============================================================Exit without changes.
# Check we're on the target branch
TARGET_BRANCH=$(read from mega-plan.json)
CURRENT_BRANCH=$(git branch --show-current)
if [ "$CURRENT_BRANCH" != "$TARGET_BRANCH" ]; then
echo "Warning: Not on target branch ($TARGET_BRANCH)"
echo "Currently on: $CURRENT_BRANCH"
fi============================================================
MEGA PLAN COMPLETION
============================================================
All features have been merged!
Target Branch: <target_branch>
Completed Features:
Batch 1:
[X] feature-001: User Authentication
[X] feature-002: Product Catalog
Batch 2:
[X] feature-003: Shopping Cart
[X] feature-004: Order Processing
Total: 4 features merged
Remaining cleanup:
- Remove mega-plan.json
- Remove mega-findings.md
- Remove .mega-status.json
- Prune any remaining worktrees
============================================================Use AskUserQuestion:
**Proceed with cleanup?**
Options: 1. **Yes, cleanup** - Remove planning files 2. **Keep files** - Keep planning files for reference 3. **Cancel** - Do nothing
If user selected "Yes, cleanup":
# Get file paths from PathResolver (handles new vs legacy mode)
MEGA_PLAN_PATH=$(uv run python -c "from plan_cascade.state.path_resolver import PathResolver; from pathlib import Path; print(PathResolver(Path.cwd()).get_mega_plan_path())" 2>/dev/null || echo "mega-plan.json")
MEGA_STATUS_PATH=$(uv run python -c "from plan_cascade.state.path_resolver import PathResolver; from pathlib import Path; print(PathResolver(Path.cwd()).get_mega_status_path())" 2>/dev/null || echo ".mega-status.json")
MEGA_FINDINGS_PATH=$(uv run python -c "from plan_cascade.state.path_resolver import PathResolver; from pathlib import Path; print(PathResolver(Path.cwd()).get_mega_findings_path())" 2>/dev/null || echo "mega-findings.md")
USER_STATE_DIR=$(uv run python -c "from plan_cascade.state.path_resolver import PathResolver; from pathlib import Path; print(PathResolver(Path.cwd()).get_state_dir())" 2>/dev/null || echo "")
# Remove mega-plan core files
rm -f "$MEGA_PLAN_PATH"
rm -f "$MEGA_FINDINGS_PATH"
rm -f "$MEGA_STATUS_PATH"
echo "[OK] Removed mega-plan.json from: $MEGA_PLAN_PATH"
echo "[OK] Removed mega-findings.md from: $MEGA_FINDINGS_PATH"
echo "[OK] Removed .mega-status.json from: $MEGA_STATUS_PATH"
# Remove additional planning files from project root
echo "Cleaning up additional planning files..."
# Design and spec files
rm -f design_doc.json spec.json spec.md
echo "[OK] Removed design_doc.json, spec.json, spec.md"
# Context recovery files
rm -f .mega-execution-context.md .hybrid-execution-context.md
echo "[OK] Removed context recovery files"
# Status and state files in project root
rm -f .agent-status.json .iteration-state.json .retry-state.json
echo "[OK] Removed status files"
# Agent outputs directory
rm -rf .agent-outputs
echo "[OK] Removed .agent-outputs/"
# Locks directory
rm -rf .locks
echo "[OK] Removed .locks/"
# State directory in project root (legacy mode)
rm -rf .state
echo "[OK] Removed .state/"
# Clean up state files from user data directory (new mode)
if [ -n "$USER_STATE_DIR" ] && [ -d "$USER_STATE_DIR" ]; then
echo "Cleaning up state files from user data directory..."
rm -f "$USER_STATE_DIR/.iteration-state.json" 2>/dev/null || true
rm -f "$USER_STATE_DIR/.agent-status.json" 2>/dev/null || true
rm -f "$USER_STATE_DIR/.retry-state.json" 2>/dev/null || true
rm -f "$USER_STATE_DIR/spec-interview.json" 2>/dev/null || true
# Remove .state directory if empty
rmdir "$USER_STATE_DIR" 2>/dev/null || true
echo "[OK] SAI-Powered Cascading Development Framework Transform complex projects into parallel executable tasks with intelligent decomposition and multi-provider execution Why Plan Cascade? • Product Editions • Quick Start • Architecture
Repo: Taoidle/plan-cascade
Approve the current PRD and begin parallel story execution. Analyzes dependencies, creates execution batches, launches background Task agents for each story,…
AI auto strategy executor. Analyzes task and automatically selects and executes the best strategy: direct execution, hybrid-auto PRD generation,…
Check and update .gitignore to exclude Plan Cascade temporary files. Ensures planning files won't be accidentally committed to version control.
Complete a worktree task. Verifies all phases are complete, commits code changes (excluding planning files), merges to target branch, and removes worktree. Can…
Show execution status dashboard. Usage: /plan-cascade:dashboard [--verbose|-v] [--json]
Generate a technical design document. Auto-detects level: project-level from mega-plan.json, or feature-level from prd.json. Provides architectural context for…