Skip to content
Development
Command

/hybrid-auto

Generate PRD from task description and enter review mode. Auto-generates user stories with priorities, dependencies, and acceptance criteria for parallel execution. Usage: /plan-cascade:hybrid-auto [--flow <quick|standard|full>] [--tdd <off|on|auto>] [--confirm] [--no-confirm]

From plugin
plan-cascade
14030 skills30 commands
Install
> /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.

  • Fires itselfClaude auto-loads it when your prompt matches the work.
  • You can call itInvoke it directly when you want it.
  • Slash command/hybrid-auto

Context preview

What this command does when you run it.

Generate PRD from task description and enter review mode. Auto-generates user stories with priorities, dependencies, and acceptance criteria for parallel execution. Usage: /plan-cascade:hybrid-auto [--flow <quick|standard|full>] [--tdd <off|on|auto>] [--confirm] [--no-confirm]

Command definition

hybrid-auto.md
description: "Generate PRD from task description and enter review mode. Auto-generates user stories with priorities, dependencies, and acceptance criteria for parallel execution. Usage: /plan-cascade:hybrid-auto [--flow <quick|standard|full>] [--tdd <off|on|auto>] [--confirm] [--no-confirm] [--spec <off|auto|on>] [--first-principles] [--max-questions N] [--agent <name>] <task description> [design-doc-path]"

Hybrid Ralph - Auto Generate PRD

You are automatically generating a Product Requirements Document (PRD) from the task description.

Execution Flow Parameters

This command accepts flow control parameters that affect story execution:

Parameter Priority

Parameters are saved to `prd.json` and later used by `/plan-cascade:approve`. Priority order:

1. **Command-line flags to THIS command** (highest priority)

  • Example: `/plan-cascade:hybrid-auto --flow full "task"`
  • Saved to `prd.json` as `flow_config`, `tdd_config`, etc.

2. **Command-line flags to `/plan-cascade:approve`**

  • Can override values saved in `prd.json`
  • Example: Even if prd.json has `flow_config.level="standard"`, running `/plan-cascade:approve --flow full` will use `full`

3. **Default values** (lowest priority)

  • Used when no flags provided to either command

**Example Flow:**

# Step 1: Generate PRD with parameters
/plan-cascade:hybrid-auto --flow full --tdd on "Build auth"
# → Saves to prd.json: flow_config.level="full", tdd_config.mode="on"

# Step 2a: Approve with saved parameters
/plan-cascade:approve
# → Uses flow="full", tdd="on" from prd.json

# Step 2b: Approve with override
/plan-cascade:approve --flow standard
# → Uses flow="standard" (overrides prd.json), tdd="on" (from prd.json)

**Note:** This command writes parameters to `prd.json` in Step 5. The recommended `/plan-cascade:approve` command (shown in Step 6) includes the same parameters for clarity, but they're already in prd.json.

`--flow <quick|standard|full>`

Override the execution flow depth for the approve phase.

| Flow | Gate Mode | AI Verification | Code Review | Test Enforcement | |------|-----------|-----------------|-------------|------------------| | `quick` | soft | disabled | no | no | | `standard` | soft | enabled | no | no | | `full` | **hard** | enabled | **required** | **required** |

`--tdd <off|on|auto>`

Control Test-Driven Development mode for story execution.

| Mode | Description | |------|-------------| | `off` | TDD disabled | | `on` | TDD enabled with prompts and compliance checks | | `auto` | Automatically decide based on risk assessment (default) |

`--confirm`

Require confirmation before each batch execution in the approve phase.

`--no-confirm`

Explicitly disable batch confirmation, even if FULL flow would normally require it. Useful for CI/automated environments where you want strict quality gates but no interactive prompts.

**Precedence**: `--no-confirm` overrides `--confirm` and FULL flow's default confirmation requirement.

`--spec <off|auto|on>`

Enable a planning-time **spec interview** to produce `spec.json/spec.md` before finalizing `prd.json`.

  • `auto` (default): enabled when `--flow full`, otherwise disabled
  • `on`: always run interview before PRD finalization
  • `off`: never run interview

`--first-principles`

Ask 3–5 first-principles questions before detailed spec questions (only when spec interview runs).

`--max-questions N`

Soft cap for interview length (recorded in `.state/spec-interview.json`).

Prerequisites Check

**CRITICAL**: If this is your first time using Plan Cascade, run `/plan-cascade:init` first to set up the environment.

# Quick check - if this fails, run /plan-cascade:init
uv run python -c "print('Environment OK')" 2>/dev/null || echo "Warning: Run /plan-cascade:init to set up environment"

Path Storage Modes

Plan Cascade supports two path storage modes:

New Mode (Default)

Runtime files stored in user directory:

  • **Windows**: `%APPDATA%/plan-cascade/<project-id>/`
  • **Unix/macOS**: `~/.plan-cascade/<project-id>/`

Files created:

  • `prd.json`: `<user-dir>/prd.json` (or in worktree if in worktree mode)
  • `design_doc.json`: In project root (user-visible)
  • State files: `<user-dir>/.state/`

Legacy Mode

All files in project root or worktree directory.

User-visible files (`progress.txt`, `findings.md`) always remain in the working directory.

Multi-Agent Support

PRD generation can use different AI agents:

| Agent | Type | Notes | |-------|------|-------| | `claude-code` | task-tool | Default, always available | | `codex` | cli | Good for structured PRD generation | | `aider` | cli | Alternative for PRD generation |

Command Parameters

--agent <name>    Agent to use for PRD and design doc generation

Tool Usage Policy (CRITICAL)

**To avoid command confirmation prompts:**

1. **Use Read tool for file reading** - NEVER use `cat` via Bash

  • ✅ `Read("prd.json")`
  • ❌ `Bash("cat prd.json")`

2. **Use Write tool for file creation** - When creating prd.json

  • ✅ `Write("prd.json", content)`
  • Or have the Task agent write it directly

Step 0: Ensure .gitignore Configuration

**IMPORTANT**: Before creating any planning files, ensure the project's `.gitignore` is configured to ignore Plan Cascade temporary files:

# Check and update .gitignore for Plan Cascade entries
uv run python -c "from plan_cascade.utils.gitignore import ensure_gitignore; from pathlib import Path; ensure_gitignore(Path.cwd())" 2>/dev/null || echo "Note: Could not auto-update .gitignore"

This prevents planning files from being accidentally committed to version control.

Step 1: Parse Arguments

Parse user arguments:

  • **Task description**: First positional argument (required)
  • **Design doc path**: Second positional argument (optional) - external design document to convert
  • **--flow**: Execution flow depth (quick|standard|full)
  • **--tdd**: TDD mode (off|on|auto)
  • **--confirm**:
Read more
Ships withplan-cascade

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

Get the whole plugin
Stats
141
Stars
12
Forks
Quiet
Maintenance
Rust
Language
MIT
License
6mo ago
Last commit
8mo ago
Created

Repo: Taoidle/plan-cascade

Other commands on plan-cascade.