debug

<quick_start> Debug an error (interactive):

/debug login page crashes on submit

Auto mode (fully automatic, use recommended solutions):

/debug -a API returning 500 on POST

What it does:

1. Analyze: Reproduce error, identify root cause → ask if you have more context
2. Find Solutions: Research 2-3+ potential fixes with pros/cons
3. Propose: Present options → you choose which solution
4. Fix: Implement solution with strategic logging
5. Verify: Multi-layer verification (Static → Build → Runtime)

Key principle: Tests passing ≠ fix working. Always execute the actual code path.

Note: Only 2 questions in the entire workflow:

1. After analysis: "Do you have additional info?"
2. After finding solutions: "Which solution to implement?" </quick_start>

1. Reproduce Before Anything Else - If you can't reproduce it, you can't verify the fix
2. Hypothesis-Driven Analysis - List 3-5 causes ranked by likelihood, test systematically
3. Multi-Layer Verification - Tests alone give false confidence (20-40% still fail in production) </core_principles>

<verification_pyramid> Verification Pyramid:

        ┌─────────────┐
        │   Manual    │  ← User confirms
        └──────┬──────┘
     ┌─────────┴─────────┐
     │ Runtime Execution │  ← CRITICAL: Real execution
     └─────────┬─────────┘
   ┌───────────┴───────────┐
   │   Automated Checks    │  ← Build, Types, Lint, Tests
   └───────────┬───────────┘
 ┌─────────────┴─────────────┐
 │     Static Analysis       │  ← Syntax, Imports
 └───────────────────────────┘

Key Insight: Tests passing ≠ fix working. ALWAYS execute the actual code path. </verification_pyramid>

Arguments:

• Everything after flags = {error_context} - Description of the error or context about what's failing

<state_variables> Persist throughout all steps:

</state_variables>

<entry_point> Load steps/step-00-init.md </entry_point>

<step_files>

<success_criteria>

• Error successfully reproduced
• Root cause identified through hypothesis testing
• 2-3+ potential solutions researched with pros/cons
• Solution selected (by user or auto mode)
• Fix implemented with strategic logging
• Static analysis passes (syntax, imports)
• Build completes successfully
• Tests pass (if tests exist)
• Runtime execution verified (actual code path executed)
• User confirms fix resolves the original issue
• No regressions introduced </success_criteria>