Anti-Pattern Detector

Identifies recurring failure patterns in plans and decisions. Anti-patterns look reasonable on the surface but lead to predictable problems. Detecting them early saves months of pain.

Anti-Pattern Categories

1. Architecture Anti-Patterns

2. Timeline Anti-Patterns

3. Team Anti-Patterns

4. Process Anti-Patterns

5. Technology Anti-Patterns

Detection Process

Step 1: Scan for Signals

Look for phrases that indicate anti-patterns:

Timeline signals: "If everything goes well...", "We can do it faster if...", "Just need to hire...", "Should only take..."

Architecture signals: "We'll figure out boundaries later...", "Everything talks to everything...", "It's only temporary...", "We can always refactor..."

Team signals: "Only [person] knows...", "We'll hire for that...", "[Person] will handle all of...", "The team can absorb..."

Process signals: "We don't need docs...", "We'll add tests later...", "Let's discuss in the meeting...", "Requirements are evolving..."

Step 2: Verify Pattern Match

For each suspected anti-pattern:

1. Identify: Which specific pattern?
2. Evidence: What in the plan matches?
3. Severity: How bad? (Critical / High / Medium / Low)
4. Context: Could this be a reasonable exception?

Step 3: Check for Combinations

Certain patterns appear together and compound risk:

Startup Death Spiral: Timeline Fantasy + Understaffed Ambition + Hero Culture

• Result: Burnout, missed deadlines, key person leaves

Enterprise Trap: Analysis Paralysis + Documentation Theater + Meeting Madness

• Result: Nothing ships, team frustrated, competition wins

Tech Debt Avalanche: "Refactor later" + No ownership + Premature optimization

• Result: System unmaintainable, rewrite required

Microservices Mistake: Premature Microservices + Distributed Monolith + Understaffed

• Result: Complexity explosion, slower than monolith

Severity Framework

When to Use This Skill

Use antipattern-detector for recognizing known failure patterns (architecture, timeline, team, process, technology). Use assumption-challenger for surfacing hidden assumptions treated as facts. Both run together in /validate.

Pre-Delivery Checklist

Before presenting an analysis, verify:

• Every detected pattern includes a direct evidence quote from the plan
• Every pattern has a severity rating (Critical/High/Medium/Low)
• Pattern combinations are checked and reported
• "Patterns NOT Detected" section is included for confidence
• Fixes are specific and actionable, not generic advice

Output Format

# Anti-Pattern Analysis: [Plan Name]

## Summary
- **Patterns Detected**: [Count]
- **Critical**: [Count] | **High**: [Count] | **Medium**: [Count] | **Low**: [Count]
- **Overall Risk Level**: Critical / High / Medium / Low
- **Pattern Combinations Found**: [List any compound patterns]

## Critical Issues (Must Address)

### [Pattern Name]
**Category**: [Category] | **Severity**: Critical
**Evidence**: [What triggered detection]
**Risk**: [What will go wrong]
**Fix**: [How to address]

---

## High-Priority Issues (Should Address)
[Same format]

## Medium-Priority Issues (Consider Addressing)
[Same format]

## Patterns NOT Detected
[List patterns checked but not found — builds confidence]

## Recommendations
### Before Proceeding
1. [Critical action]
### During Execution
1. [Mitigation]
### Warning Signs to Monitor
- [Metric or signal to watch]