/auto

description: "AI auto strategy executor. Analyzes task and automatically selects and executes the best strategy: direct execution, hybrid-auto PRD generation, hybrid-worktree isolated development, or mega-plan multi-feature orchestration."

Plan Cascade - Auto Strategy Executor

AI automatically analyzes the task and executes the optimal strategy without user confirmation.

CRITICAL CONSTRAINTS (READ FIRST)

**NEVER use `EnterPlanMode`.** This command has its own planning and execution flow. Using Claude's native plan mode bypasses Plan Cascade entirely and defeats the purpose of this command. If you feel the urge to "enter plan mode" or "design an implementation approach", STOP — that is exactly what the Skill tool routing in Step 5 handles.

**NEVER use the `Task` tool with `subagent_type=Explore` or `subagent_type=Plan`** during this command's execution. Context gathering in Step 2 must use only Glob, Read, Grep, and Bash (for git commands only). Launching exploration agents delays routing and causes fallthrough to native plan mode.

**After completing Step 3 (strategy analysis), you MUST proceed directly to Step 5 (Skill tool routing).** Do not pause to "think about the approach", "gather more context", or "design a solution". The specialized skill invoked in Step 5 handles all of that.

Command-Line Flags

The auto command supports the following flags to customize execution:

Parameter Priority

When parameters are specified in multiple places, the following priority order applies:

1. **Command-line flags** (highest priority) - Override all other sources 2. **Configuration files** (prd.json, mega-plan.json) - Used when no command-line flag provided 3. **Default values** (lowest priority) - Used when no other source provides the parameter

**Example:**

# If prd.json contains: flow_config.level = "standard"
# And you run: /plan-cascade:auto --flow full "task"
# Result: FLOW = "full" (command-line overrides configuration)

**Note:** Parameters are propagated through the execution chain:

• `auto` → passes parameters to `hybrid-auto`/`hybrid-worktree`/`mega-plan`
• These commands → save parameters to `prd.json`/`mega-plan.json`
• `approve` → reads parameters from configuration files (can be overridden by command-line)

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

Override the execution flow depth (**default: `full`**).

| Flow | Description | Gate Mode | AI Verification | Confirm Required | |------|-------------|-----------|-----------------|------------------| | `quick` | Fastest path, minimal gating | soft | disabled | no | | `standard` | Balanced speed and quality | soft | enabled | no | | `full` | Strict methodology + strict gating (default) | hard | enabled + review | yes |

**Usage:**

/plan-cascade:auto "Implement critical security feature"          # defaults to FULL flow (TDD on + confirm)
/plan-cascade:auto --flow full "Implement critical security feature"
/plan-cascade:auto --flow quick "Fix typo in documentation"

`--explain`

Display detailed analysis results and decision rationale without executing.

This flag shows:

• **Key Factors**: scope, complexity, risk, parallelism assessment
• **Strategy Decision**: selected strategy, flow, confidence score
• **Confirmation Points**: questions for user review (if any)
• **TDD Recommendation**: test-driven development guidance
• **Estimates**: stories, features, duration, worktree usage

**Usage:**

/plan-cascade:auto --explain "Build user authentication system"

The output is human-readable by default. For machine-readable JSON output, combine with `--json`:

/plan-cascade:auto --explain --json "Build user authentication system"

`--confirm`

Display confirmation points before execution and wait for user acknowledgment.

**Default**: enabled in `--flow full` (the default flow for `/plan-cascade:auto`) unless `--no-confirm` is set.

When this flag is set: 1. Analysis is performed and displayed 2. Confirmation points are shown (if any exist) 3. User must acknowledge before execution proceeds

Confirmation points are generated when:

• Low confidence (< 0.7): "Do you want to proceed with this strategy?"
• High risk: "Have you considered rollback procedures?"
• Architecture decisions needed: "Would you like to create a design document first?"

**Usage:**

/plan-cascade:auto --confirm "Major refactoring of payment module"

`--no-confirm`

Explicitly disable batch confirmation during execution, even if FULL flow would normally require it.

This is useful for:

• CI/CD pipelines where interactive confirmation is not possible
• Automated testing environments
• When you want strict quality gates but uninterrupted execution

**Note**: `--no-confirm` only affects batch-level confirmation during story execution. It does NOT disable quality gates (verification, code review, TDD compliance) - those still run and can block on failures in FULL flow.

**Usage:**

# Strict quality gates but no batch confirmation prompts
/plan-cascade:auto --flow full --no-confirm "Implement critical feature"

# CI-friendly: strict gates, no interruptions
/plan-cascade:auto --flow full --tdd on --no-confirm "Security audit fixes"

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

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

Control Test-Driven Development (TDD) mode for story execution.

| Mode | Description | When to Use | |------|-------------|-------------| | `off` | TDD disabled | Simple changes, documentation, non-code tasks | | `on` | TDD enabled with prompts and compliance checks | Critical features, security-related code | | `auto` | Automatically decide based on risk assessment | Mixed-risk tasks, faster iteration |

**Default**: `/plan-cascade:auto` uses `--tdd on` in FULL flow unless explicitly overridden via `--tdd`.

When TDD mode is enabled (on or auto-enabled): 1. **Red Phase**: AI writes failing tests first based on acceptance criteria 2. **Green Ph