mega-plan
Project-level multi-task orchestration system. Manages multiple hybrid:worktree features in parallel with dependency resolution, coordinated PRD generation,…
Hybrid architecture combining Ralph's PRD format with Planning-with-Files' structured approach. Auto-generates PRDs from task descriptions, manages parallel story execution with dependency resolution, and provides context-filtered agents for efficient multi-story development.
$ npx -y skills add Taoidle/plan-cascade --skill hybrid-ralph --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/hybrid-ralphContext preview
The summary Claude sees to decide when to auto-load this skill.
Hybrid architecture combining Ralph's PRD format with Planning-with-Files' structured approach. Auto-generates PRDs from task descriptions, manages parallel story execution with dependency resolution, and provides context-filtered agents for efficient multi-story development.
name: hybrid-ralph
version: "3.2.0"
description: Hybrid architecture combining Ralph's PRD format with Planning-with-Files' structured approach. Auto-generates PRDs from task descriptions, manages parallel story execution with dependency resolution, and provides context-filtered agents for efficient multi-story development.
user-invocable: true
allowed-tools:
- Read
- Write
- Edit
- Bash
- Task
- Glob
- Grep
- AskUserQuestion
hooks:
PreToolUse:
# Show execution context and current story for relevant tools
- matcher: "Write|Edit|Bash|Task"
hooks:
- type: command
command: |
# Show hybrid execution context if we're in a hybrid task
if [ -f "prd.json" ] || [ -f ".planning-config.json" ] || [ -f ".hybrid-execution-context.md" ]; then
if command -v uv &> /dev/null; then
# Update and display context reminder
uv run python "${CLAUDE_PLUGIN_ROOT}/skills/hybrid-ralph/scripts/hybrid-context-reminder.py" both 2>/dev/null || true
fi
fi
# Show current story context if we're executing a story
if [ -f ".current-story" ]; then
STORY_ID=$(cat .current-story 2>/dev/null || echo "")
if [ -n "$STORY_ID" ]; then
echo ""
echo "=== Current Story: $STORY_ID ==="
# Show story details from prd.json if available
if command -v uv &> /dev/null; then
(cd "${CLAUDE_PLUGIN_ROOT}" && uv run python -m plan_cascade.state.context_filter get-story "$STORY_ID" 2>/dev/null | head -20) || true
fi
echo ""
fi
fi
PostToolUse:
# Update context file and remind to update findings after significant operations
- matcher: "Write|Edit|Bash|Task"
hooks:
- type: command
command: |
# Update execution context file
# Best-effort: script exits silently if no hybrid context is detected.
if command -v uv &> /dev/null; then
uv run python "${CLAUDE_PLUGIN_ROOT}/skills/hybrid-ralph/scripts/hybrid-context-reminder.py" update 2>/dev/null || true
elif command -v python &> /dev/null; then
python "${CLAUDE_PLUGIN_ROOT}/skills/hybrid-ralph/scripts/hybrid-context-reminder.py" update 2>/dev/null || true
fi
# Remind about findings
if [ -f ".current-story" ]; then
STORY_ID=$(cat .current-story 2>/dev/null || echo "")
if [ -n "$STORY_ID" ]; then
echo "[hybrid-ralph] Consider updating findings.md with this discovery (tag with <!-- @tags: $STORY_ID -->)"
fi
fi
Stop:
# Verify story completion before stopping
- hooks:
- type: command
command: |
if [ -f ".current-story" ]; then
STORY_ID=$(cat .current-story 2>/dev/null || echo "")
if [ -n "$STORY_ID" ]; then
echo ""
echo "=== Story Completion Check ==="
echo "Current story: $STORY_ID"
echo "Mark complete in progress.txt with: [COMPLETE] $STORY_ID"
echo ""
fi
fiA hybrid architecture combining the best of three approaches:
**At the START of any interaction**, perform this check to recover context after compression/truncation:
1. Check if `.hybrid-execution-context.md` exists in the current directory 2. If YES:
3. If NO but `prd.json` exists:
This ensures context recovery even after:
Generate a PRD from your task description:
/hybrid:auto Implement a user authentication system with login, registration, and password reset
This will: 1. Launch a Planning Agent to analyze your task 2. Generate a PRD with user stories 3. Show the PRD for review 4. Wait for your approval
Load an existing PRD file:
/hybrid:manual path/to/prd.json
After reviewing the PRD:
/approve
This begins parallel execution of stories according to the dependency graph.
project-root/ ├── prd.json # Product Requirements Document ├── findings.md # Research findings (tagged by story) ├── progress.txt # Progress tracking ├── .current-story # Currently executing story ├── .locks/ # File locks for concurrent access └── .agent-outputs/ # Individual agent logs
The `prd.json` file contains:
AI-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
Project-level multi-task orchestration system. Manages multiple hybrid:worktree features in parallel with dependency resolution, coordinated PRD generation,…
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks,…