decision-tree

name	decision-tree
description	Build a decision tree with probabilities and payoffs, roll back expected values, and report EV and variance per option. Produces a 0-100 score.

Decision Tree / Expected Value

Single-framework analysis. Use when the user wants this lens specifically, or when called as a building block by /decision:analyze.

Inputs

• A decision file path (markdown). If the user describes a decision verbally instead, run /decision:new-decision first.

Procedure

1. Locate the framework guide at the plugin install dir's frameworks/decision-tree.md. Read it fully.

2. Read the decision file fully.

3. Apply the framework exactly as the guide specifies. Don't invent additional structure. Don't merge in other frameworks — that's the orchestrator's job.

4. Output destination:

   • If the user invoked this standalone, write the analysis inline as the response (and offer to save it to a path).
   • If invoked as a subagent by /decision:analyze, write to the fragment path the orchestrator provides (fragments/decision-tree.md).

5. End with the score line ## Score: <0-100> per the guide's scoring rubric.

Notes

• Stay inside the framework. If you notice that a different framework would have surfaced something this one missed, note it briefly at the end (## Cross-framework note) but don't switch lenses.