t1k:predict
| Field | Value |
|---|---|
| Module | t1k-extended |
| Version | 2.14.3 |
| Effort | medium |
| Tools | — |
Keywords: debate, expert, pre-implementation, predict, review, risky, tradeoffs
How to invoke
Section titled “How to invoke”/t1k:predict<proposed change description>TheOneKit Predict — Expert Debate
Section titled “TheOneKit Predict — Expert Debate”5 expert personas review a proposed change and debate its merits, risks, and alternatives.
/t1k:predict "Add caching layer to API responses"Personas
Section titled “Personas”| # | Persona | Focus | Looks For |
|---|---|---|---|
| 1 | Architect | System design, scalability, coupling | Over-engineering, tight coupling, wrong abstractions, missing extensibility |
| 2 | Security | Attack surface, data flow, trust boundaries | Auth bypass, injection, data exposure, insufficient logging |
| 3 | Performance | Bottlenecks, memory, latency | N+1 queries, unnecessary allocations, cache invalidation issues |
| 4 | UX/DX | User/developer impact, edge cases | Breaking changes, poor error messages, confusing APIs |
| 5 | Devil’s Advocate | Assumptions, alternatives, hidden costs | ”What if this is the wrong approach entirely?” |
Process
Section titled “Process”- Read the proposed change description
- Each persona reviews independently:
- State their concerns (1-3 bullet points)
- Rate risk for their domain (1-5 scale)
- Suggest mitigations
- Synthesize:
- Consensus risk score (average of 5 ratings)
- Prioritized concern list (highest risk first)
- Go/No-Go recommendation with conditions
Output Format
Section titled “Output Format”## Prediction: {change description}
### Architect (Risk: 3/5)- Concern: ...- Mitigation: ...
### Security (Risk: 2/5)- Concern: ...- Mitigation: ...
### Performance (Risk: 4/5)- Concern: ...- Mitigation: ...
### UX/DX (Risk: 1/5)- Concern: ...- Mitigation: ...
### Devil's Advocate (Risk: 3/5)- Alternative: ...- Hidden cost: ...
### Consensus- **Overall Risk: 2.6/5**- **Recommendation: GO with conditions**- **Top 3 concerns to address:** 1. ... 2. ... 3. ...Anti-Rationalization Guards
Section titled “Anti-Rationalization Guards”| Trap | Reality |
|---|---|
| ”This change is too simple for a debate” | Simple changes with hidden complexity cause the worst incidents. |
| ”We already discussed this” | Discussion ≠ structured risk assessment. |
| ”The user wants to start coding” | 5 minutes of prediction saves 5 hours of debugging. |
When to Use
Section titled “When to Use”- Before any change affecting >3 files
- Before any security-sensitive change
- Before any architectural decision
- When the team disagrees on approach
- When risk feels “medium” or higher
Sub-Agent Fork Hygiene
Section titled “Sub-Agent Fork Hygiene”Sub-agent forking: see skills/t1k-architecture/references/fork-hygiene.md.