| name | anti-pattern-audit |
| description | Monthly self-deception audit — 25 anti-patterns from CEO Bible Section M |
| user-invocable | true |
Anti-Pattern Audit
Monthly self-deception check. Based on CEO Bible Section M.
Process
- Read daily logs and weekly reviews for the past month
- Read MEMORY.md — current state
- Check each block of anti-patterns
- Score: 0 (not observed), 1 (mild risk), 2 (active problem)
- Total score > 8 = serious conversation needed
Block 1: General Founder-CEO Mistakes
- Too many wedges at once — is there diluted signal?
- Confusing early revenue with repeatability — a few sales != PMF
- Letting early customers dictate roadmap — building a services company?
- Scaling GTM before retention/onboarding stable — water into leaky bucket?
- Treating fundraising as validation — investor interest != customer truth
Block 2: Ex-Engineer Founder Mistakes
- Hiding in product — what % of time does the founder spend in code vs with customers?
- "Product should speak for itself" — markets don't decode architecture
- Leading with features, not pain — buyers buy changed outcomes
- Building platform before earning wedge — breadth is tax on learning
- Delegating sales/positioning too early — losing best signal stream
Block 3: Metric Interpretation Mistakes
- Aggregate dashboards vs cohort/segment cuts
- Calling pilots "ARR"
- Signed contracts = retention proof when engagement dead
- Optimizing traffic before activation/TTFV
- Counting shipped experiments vs changed beliefs
Block 4: Growth Mistakes Before PMF
- Many channels before one message lands
- Paid acquisition to compensate poor positioning
- Outbound with no proof, no content, no trust
- B2C DAU as success when B2B conversion weak
- Hiring marketer to find PMF
Block 5: AI-Era Specific Mistakes
- Demo excitement != durable value
- Selling "AI" instead of measurable business result
- Ignoring trust/evals/data handling until procurement
- Pricing ignoring compute/HITL costs -> negative-margin growth
- AI summaries replacing direct founder contact -> synthetic certainty
Output Format
Anti-Pattern Audit — [Month YYYY]
Score: X/50
Critical (score 2):
- #N: [description] — [evidence from this month]
Watch (score 1):
- #N: [description] — [early signs]
Clean:
- [list of areas with no issues]
Recommendation:
[Top 3 actions to address critical patterns]
Follow output preferences from USER.md (language, format, platform constraints).
Rules
- Be honest. If the founder is hiding in code — say it directly.
- Use concrete data: "this week 2 conversations out of 8-12 target"
- Don't sugar-coat or soften
- Log the result to
memory/YYYY-MM-DD.md