/devteam-bug

name: devteam-bug
description: Fix a bug with structured diagnostic workflow. Uses interview to clarify details and Bug Council for complex issues.
argument-hint: "<description>" [--council] [--severity <level>] [--scope <path>] [--skip-interview] [--eco]
user-invocable: true
allowed-tools: Read, Edit, Write, Glob, Grep, Bash, Task
model: opus

Current session: !`source "${CLAUDE_PLUGIN_ROOT}/scripts/state.sh" && get_current_session 2>/dev/null || echo "No active session"` Active sprint: !`source "${CLAUDE_PLUGIN_ROOT}/scripts/state.sh" && get_kv_state "active_sprint" 2>/dev/null || echo "None"` Failure count: !`source "${CLAUDE_PLUGIN_ROOT}/scripts/state.sh" && get_kv_state "consecutive_failures" 2>/dev/null || echo "0"`

DevTeam Bug Command

**Command:** `/devteam:bug "<description>" [options]`

Fix a bug with structured diagnostic workflow. Uses interview to clarify details and Bug Council for complex issues.

Usage

# Basic bug fix (will trigger interview for missing details)
/devteam:bug "Login fails for guest users"

# Force Bug Council activation
/devteam:bug "Memory leak in image processor" --council

# Specify severity
/devteam:bug "Payment processing timeout" --severity critical
/devteam:bug "Button color wrong" --severity low

# Limit scope
/devteam:bug "API returns 500" --scope "src/api/"

# Skip interview (if you have all details)
/devteam:bug "Null pointer in UserService.getProfile() when user.settings is undefined" --skip-interview

# Cost-optimized
/devteam:bug "Minor typo in error message" --eco

Options

| Option | Description | |--------|-------------| | `--council` | Force Bug Council activation | | `--severity <level>` | Set severity: critical, high, medium, low | | `--scope <path>` | Limit search to specific files/directories | | `--skip-interview` | Skip clarifying questions | | `--eco` | Cost-optimized execution | | `--model <model>` | Force starting model |

Your Process

Phase 0: Initialize Session

source "${CLAUDE_PLUGIN_ROOT}/scripts/state.sh"
source "${CLAUDE_PLUGIN_ROOT}/scripts/events.sh"

SESSION_ID=$(start_session "/devteam:bug \"$1\"" "bug")
log_session_started "/devteam:bug \"$1\"" "bug"
set_phase "interview"

Phase 1: Interview (Clarify Bug Details)

**Always ask if missing from description:**

bug_interview:
  required:
    - key: expected_behavior
      question: "What is the expected behavior?"
      skip_if: description contains "should" or "expected"

    - key: actual_behavior
      question: "What is the actual behavior?"
      skip_if: description contains "but" or "instead" or "actually"

  conditional:
    - key: repro_steps
      condition: description lacks step-by-step
      question: "What steps reproduce this issue?"

    - key: environment
      condition: could be environment-specific
      question: "What environment does this occur in? (browser, OS, version)"

    - key: frequency
      condition: not clear if consistent
      question: "Does this happen every time or intermittently?"

    - key: recent_changes
      condition: could be regression
      question: "Did this start recently? Any recent changes that might be related?"

    - key: error_message
      condition: no error mentioned
      question: "Are there any error messages or stack traces?"

**Interview flow:**

async function runBugInterview(description) {
    log_interview_started('bug')
    const questions = []
    const responses = {}

    // Check what's missing from description
    if (!hasExpectedBehavior(description)) {
        const response = await ask("What is the expected behavior?")
        responses.expected_behavior = response
        questions.push('expected_behavior')
    }

    if (!hasActualBehavior(description)) {
        const response = await ask("What is the actual behavior?")
        responses.actual_behavior = response
        questions.push('actual_behavior')
    }

    // ... more conditional questions

    log_interview_completed(questions.length)
    return responses
}

Phase 2: Classify Bug

**Determine severity:**

severity_indicators:
  critical:
    - "security vulnerability"
    - "data loss"
    - "system down"
    - "production"
    - "payment"
    - "authentication bypass"

  high:
    - "major functionality broken"
    - "affects all users"
    - "no workaround"
    - "blocking"

  medium:
    - "workaround exists"
    - "affects some users"
    - "degraded experience"

  low:
    - "cosmetic"
    - "typo"
    - "minor"
    - "edge case"

**Determine complexity:**

complexity_indicators:
  simple:
    - single file likely
    - clear error message
    - obvious fix
    - similar bug fixed before

  moderate:
    - multiple files
    - requires investigation
    - unclear root cause

  complex:
    - architectural issue
    - race condition
    - intermittent
    - cross-system
    - no reproduction steps

Phase 3: Create Bug Record

INSERT INTO bugs (
    session_id,
    description,
    severity,
    complexity,
    status
) VALUES (
    'session-xxx',
    'Login fails for guest users when settings is null',
    'high',
    'moderate',
    'in_progress'
);

Phase 4: Bug Council (if needed)

**Activate Bug Council if:**

• Complexity is `complex`
• `--council` flag specified
• 2+ failed fix attempts
• Severity is `critical`

if (shouldActivateBugCouncil(bug)) {
    log_bug_council_activated(reason)
    set_phase('bug_council')

    // Spawn 5 diagnostic agents in parallel
    const councilResults = await Promise.all([
        Task({
            subagent_type: "diagnosis:root-cause-analyst",
            model: "opus",
            prompt: `Analyze bug: ${bug.description}

                Expected: ${bug.expected_behavior}
                Actual: ${bug.actual_behavior}
                Repro: ${bug.repro_steps}

                Provide:
                - Root cause hypothesis
                - Evide