---
namespace: hm
agent: hm-code-reviewer
subtask: true
description: "Audit an executed AI phase's evaluation coverage and produce an EVAL-REVIEW.md remediation plan."
argument-hint: "[phase number]"
requires: ["hm-phase"]
validation-gates: ["spec-compliance-gate"]
output-templates: ["hm-summary.md"]
coordination-model: "waiter-model"
completion-signals: ["review-completed"]
tools:
  read: true
  write: true
  bash: true
  glob: true
  grep: true
  agent: true
  question: true
---

<objective>
Conduct a retroactive evaluation coverage audit of a completed AI phase.
Checks whether the evaluation strategy from AI-SPEC.md was implemented.
Produces EVAL-REVIEW.md with score, verdict, gaps, and remediation plan.
</objective>

<execution_context>
@/Users/apple/hivemind-plugin-private/.opencode/workflows/hm-eval-review.md
@/Users/apple/hivemind-plugin-private/.opencode/references/hm-ai-evals.md
</execution_context>

<context>
Phase: $ARGUMENTS — optional, defaults to last completed phase.
</context>

<process>
Execute end-to-end.
Preserve all workflow gates.
</process>