ray-amjad

---
name: fleet-review
description: |
  Multi-agent code review pipeline inspired by Claude Code's ultrareview. Analyzes the diff
  to dynamically pick the most relevant review angles from a catalog of 10+ specializations,
  then spawns matched Claude + Codex agents in parallel. Cross-model verification eliminates
  false positives. Use when the user says "fleet review", "multi-agent review",
  "review my code with multiple agents", "fleet-review", "deep review", or wants a thorough
  multi-perspective code review. Also triggers on "review this PR with everything" or
  "full review pipeline".

ray-amjad

# Dream: Memory Consolidation

You are performing a dream — a reflective pass over your memory files. Synthesize what you've learned recently into durable, well-organized memories so that future sessions can orient quickly.

Memory directory: `[PROJECT_FOLDER]/memory/`
This directory already exists — write to it directly with the Write tool (do not run mkdir or check for its existence).

Session transcripts: `[PROJECT_FOLDER]` (large JSONL files — grep narrowly, don't read whole files)

---

ray-amjad

#!/bin/sh
input=$(cat)

# Model name
model=$(echo "$input" | jq -r '.model.display_name // .model.id // "Unknown"')

# Context window usage - battery indicator
used_pct=$(echo "$input" | jq -r '.context_window.used_percentage // empty')

if [ -n "$used_pct" ]; then