Ln Spike

Retire one uncertainty. Output is knowledge, not code — spike code is throwaway, never promoted directly (Beck, XP). One question per spike; if multiple unknowns exist, run multiple spikes.

Spike notes are temporary. Reconcile durable findings into memory/SPEC.md and memory/PLAN.md instead of inventing standalone investigation docs unless the user explicitly asks for one.

Input

The question and approach: $ARGUMENTS

Investigate

1. State the question and what would constitute an answer.
2. Time-box the investigation. Stop when answered or exhausted.
3. Write a verdict.

Spike Verdict

## Question
[The question]

## Approach
[What was tried]

## Verdict
[Answer: yes/no/partially, with evidence]

## Recommendation
[Proceed with ln-scope, try a different approach, or abandon]

Traceability (mandatory — do before routing)

After the verdict, do all of these before presenting routing options:

1. Mark the spike done in memory/PLAN.md if the spike itself was tracked as a frontier item, or update the affected frontier definition if it was a proving step inside a frontier
2. Update memory/SPEC.md §Assumptions — set Status to validated or invalidated as evidence warrants, update Confidence if the evidence changed it, and flag implicated frontier items in memory/PLAN.md
3. Add any new decisions to memory/SPEC.md §Decisions, new assumptions to §Assumptions
4. If the verdict changes frontier or slice feasibility → update affected frontier definitions / sequencing in memory/PLAN.md

These are bookkeeping steps, not optional. Routing comes after.

Routing

After traceability is complete, present these options to the user (use tool-ask-question):

Recommended: 1 if the spike validated. If it invalidated an architectural or requirement-level assumption, prefer 3; if it mainly changes frontier/slice feasibility, ordering, or dependencies, prefer 4.