Start a time-boxed technical investigation
Conducts time-boxed technical investigations to answer feasibility questions and make GO/NO-GO decisions.
/plugin marketplace add srstomp/pokayokay/plugin install srstomp-pokayokay@srstomp/pokayokay<spike-question>Investigate: $ARGUMENTS
For deep investigations (>1 hour), delegate to the yokay-spike-runner agent for isolated execution. This keeps investigation context separate and allows the agent to write spike reports to .claude/spikes/.
Use the yokay-spike-runner agent to investigate: $ARGUMENTS
Time box: [specify hours]
Return the decision (GO/NO-GO/PIVOT/MORE-INFO) and summary to this conversation.
For quick feasibility checks (<1 hour), run inline without delegation.
Spikes answer questions, they don't build features.
Good spike questions:
Bad spike questions:
Reframe $ARGUMENTS as a specific, answerable question.
If vague, ask:
| Duration | Use Case |
|---|---|
| 1h | Quick feasibility check |
| 2h | Standard investigation (default) |
| 4h | Complex evaluation |
| 8h | Deep dive (requires justification) |
npx @stevestomp/ohno-cli create "Spike: $QUESTION" -t spike
npx @stevestomp/ohno-cli start <task-id>
Before starting, document:
## Spike: [Question]
**Time Box**: [hours]
**Started**: [timestamp]
**Must Conclude By**: [timestamp + time-box]
### Success Criteria
- [ ] [Specific criterion 1]
- [ ] [Specific criterion 2]
Focus on answering the question:
At half time, assess:
## Spike Checkpoint (50%)
**Progress**: [summary of findings so far]
**On Track?**: Yes / No / Pivoting
**Remaining Time**: [hours]
If off track:
Even if time runs out, produce decision:
| Decision | Meaning | Next Step |
|---|---|---|
| GO | Feasible, proceed | Create implementation tasks |
| NO-GO | Not feasible | Document why, close spike |
| PIVOT | New question | Create new spike task |
| MORE-INFO | Insufficient data | One follow-up spike max |
Create .claude/spikes/[date]-[slug].md:
# Spike: [Question]
**Date**: [date]
**Time spent**: [hours]
**Decision**: [GO/NO-GO/PIVOT/MORE-INFO]
## Question
[The specific question investigated]
## Answer
[Clear answer with rationale]
## Findings
[Key discoveries]
## Evidence
[Code samples, links, screenshots]
## Recommendation
[What to do next]
## Follow-up
- [ ] [Action item 1]
- [ ] [Action item 2]
If decision is GO:
npx @stevestomp/ohno-cli create "[implementation task]" -t feature
npx @stevestomp/ohno-cli done <task-id> --notes "Decision: X. See .claude/spikes/[file]"
## Spike Complete
**Question**: [question]
**Answer**: [GO/NO-GO/PIVOT/MORE-INFO]
**Time**: [actual] / [budgeted]
**Report**: .claude/spikes/[file].md
### Summary
[2-3 sentence summary]
### Next Steps
[Follow-up tasks created, or "No action needed"]
/pokayokay:research - Longer multi-day research/pokayokay:work - Implement spike findings/pokayokay:quick - Non-investigative quick work/pokayokay:spike Can we use Clerk for authentication?
/pokayokay:spike What's the best state management for our React app?
/pokayokay:spike Is our current architecture suitable for real-time features?