governor

🏛️ Governor — Portfolio Governance

Enforce tier-appropriate complexity. Prevent over-engineering the #1 waste of time in AI-assisted development.

Activation

When this skill activates, output:

🏛️ Governor — Checking project tier constraints...

Then execute the protocol below.

Context Guard

Anti-Rationalization

If you're thinking any of these, STOP — you're about to let scope creep happen:

Protocol

Step 1: Determine Project Tier

Ask or infer the project tier from context:

If tier is unclear, default to Prototype and escalate only when evidence suggests otherwise.

Step 2: Apply Tier Constraints

Prototype — Move Fast, Break Things

Prototype rule: If it works in a demo, ship it.

MVP — Prove It Works

MVP rule: If the first 10 users can use it reliably, ship it.

Production — Reliability Matters

Production rule: If it breaks at 3 AM, someone gets paged.

Step 3: Report Constraints

Output a brief summary:

🏛️ Project: {name}
   Tier: {Prototype | MVP | Production}
   Allowed: {brief list}
   NOT allowed: {brief list of key restrictions}

Step 4: Flag Violations

When the user proposes work that exceeds the tier, flag it:

🏛️ Governor — Scope check:
   You're proposing {X}, but this is a {Tier} project.
   {X} is a {higher tier} concern. Current tier doesn't require it.
   Want to proceed anyway, or skip it for now?

Always defer to the user if they override. Governor advises, doesn't block.

Anti-Patterns by Tier

Prototype Anti-Patterns — DON'T DO THIS

1. Writing tests for throwaway code — If the prototype proves the idea wrong, those tests are wasted
2. Adding auth to single-user tools — You're the only user. Skip it
3. Setting up CI/CD — You're not deploying to production. git push is your CI
4. Using TypeScript for a quick script — JavaScript is fine for prototypes
5. Adding rate limiting — You have 0 users. Rate limit when you have 10
6. Creating database migrations — SQLite + direct schema changes. Migrate when you scale
7. Building admin dashboards — Database GUI tool (TablePlus, DBeaver) is your admin panel
8. Over-abstracting — 3 similar lines > 1 premature abstraction
9. Adding comprehensive error handling — Crash and read the stack trace. That's debugging
10. Monitoring and alerting — Console output is your monitoring

MVP Anti-Patterns — DON'T DO THIS

1. Integration test suites — Happy-path unit tests are enough at MVP
2. Multi-environment deploys — One environment. Dev IS production
3. Performance optimization — Make it work, make it right, THEN make it fast. You're at step 2
4. Horizontal scaling — Vertical scale (bigger server) until proven insufficient
5. Comprehensive logging — Log errors and key events. Not every function call

Production Anti-Patterns — DON'T DO THIS

1. Skipping tests to "move faster" — You'll move slower when bugs hit production
2. Manual deployments — CI/CD exists for a reason. Set it up
3. No error tracking — If you can't see errors, you can't fix them
4. Ignoring security — Production code faces the internet. Act like it

Inputs

• Project name and context
• Current tier (from user, STATE.md, or project CLAUDE.md)
• Proposed work scope

Outputs

• Tier assignment with constraint summary
• Violation flags when scope exceeds tier
• Anti-pattern warnings

Level History

• Lv.1 — Base: 3-tier governance system with phase constraints, anti-patterns list, and scope violation flagging. Inspired by Intellegix portfolio governance. (Origin: MemStack v3.2, Feb 2026)