run-prompt

Execution Strategy Flags:

• --auto-detect: Analyze prompt dependencies and choose strategy automatically (default)
• --parallel: Force parallel execution (independent tasks only)
• --sequential: Force sequential execution (safe for dependent tasks)
• --no-input: Non-interactive mode for CI/CD - uses auto-detect strategy

Preference System: The command uses 3-tier preferences to determine execution strategy:

1. Config file: .spec-flow/config/user-preferences.yaml (default_strategy)
2. Command history: Learns from past usage
3. Command-line flags: Explicit overrides

Single prompt:

• Empty (no arguments): Run the most recently created prompt (default behavior)
• A prompt number (e.g., "001", "5", "42")
• A partial filename (e.g., "user-auth", "dashboard")

Multiple prompts:

• Multiple numbers (e.g., "005 006 007")
• With execution flag: "005 006 007 --parallel" or "005 006 007 --sequential"
• If no flag specified with multiple prompts, default to --sequential for safety

Determine execution strategy using 3-tier preference system:

a. Load configuration file (Tier 1 - lowest priority):

$preferences = & .spec-flow/scripts/utils/load-preferences.ps1 -Command "run-prompt"
$configStrategy = $preferences.commands.'run-prompt'.default_strategy  # "auto-detect", "parallel", or "sequential"

b. Load command history (Tier 2 - medium priority, overrides config):

$history = & .spec-flow/scripts/utils/load-command-history.ps1 -Command "run-prompt"

if ($history.last_used_mode -and $history.total_uses -gt 0) {
    $preferredStrategy = $history.last_used_mode  # Use learned preference
} else {
    $preferredStrategy = $configStrategy  # Fall back to config
}

c. Check command-line flags (Tier 3 - highest priority):

const args = "$ARGUMENTS".trim();
const hasParallelFlag = args.includes('--parallel');
const hasSequentialFlag = args.includes('--sequential');
const hasAutoDetect = args.includes('--auto-detect');
const hasNoInput = args.includes('--no-input');

let selectedStrategy;

if (hasNoInput || hasAutoDetect) {
    selectedStrategy = 'auto-detect';  // CI/automation default
} else if (hasParallelFlag) {
    selectedStrategy = 'parallel';  // Explicit parallel override
} else if (hasSequentialFlag) {
    selectedStrategy = 'sequential';  // Explicit sequential override
} else {
    selectedStrategy = preferredStrategy;  // Use config/history preference
}

d. Track usage for learning system:

# Record selection after command completes successfully
& .spec-flow/scripts/utils/track-command-usage.ps1 -Command "run-prompt" -Mode $selectedStrategy

</step0_load_preferences>

<step1_parse_arguments> Parse $ARGUMENTS to extract:

• Prompt numbers/names (all arguments that are not flags)
• Execution strategy: Use selectedStrategy from preference system

<step2_resolve_files> For each prompt number/name:

• If empty or "last": Find with !ls -t ./prompts/*.md | head -1
• If a number: Find file matching that zero-padded number (e.g., "5" matches "005-.md", "42" matches "042-.md")
• If text: Find files containing that string in the filename