Cross Role Reviewer — Research agent for Claude Code
Compares Decision Digests across role analysis files in a brainstorm session to surface conflicts, gaps, and synergies.
How to install Cross Role Reviewer
Installs to ~/.claude/agents/catlog22-maestro-flow-cross-role-reviewer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/catlog22/Maestro-Flow/HEAD/.claude/agents/cross-role-reviewer.md -o ~/.claude/agents/catlog22-maestro-flow-cross-role-reviewer.md Restart Claude Code, or start a new session, for it to be picked up.
What Cross Role Reviewer does
name: cross-role-reviewer description: Compares Decision Digests across role analysis files in a brainstorm session to surface conflicts, gaps, and synergies. Read-only — returns structured text for the orchestrator to apply. allowed-tools:
- Read
- Glob
- Grep
Cross-Role Reviewer
You read N role analysis index files from a brainstorm session and report cross-role issues. You do NOT write files. You produce structured text that the orchestrator consumes to drive AskUserQuestion
Alternatives in Research
- Role Analysis Reviewer Agent — Validates role analysis outputs against role-specific templates and quality standards 1.5k ★
- Echo Analyst — Use this agent BEFORE planning to surface requirement gaps, hidden assumptions, and missing acceptance criteri 523 ★
- Reproducibility Auditor — Reviews research workflows for reproducibility gaps — hidden dependencies,\ 130 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Protocol Replay Adversary
Use this agent for adversarial analysis of protocol-state attacks — lease replay across windows, nonce-ledger
Framework Gap Analyzer
Compares best practices against the current framework to find gaps and prioritize improvements. Use for gap an
Workflow Implementation Analysis Architecture
Analyzes implementation for API surface quality, module structure, integration gaps, and seam quality. Invoked
Interface Designer
Creates method signatures and interface boundaries for all components across 25+ languages. Ensures separation
Decide Well
Structured decision-making for high-stakes, often irreversible product choices. Use when facing a decision tha
Swarm Judge
Opus-tier judge for research swarms — adversarial verification adjudication, cross-lens synthesis, plan critiq
Related Skills
Grant Funder Landscape Scan
A Claude skill that researches who funds a nonprofit and what those funders currently prioritize, then compare
Cloud Run Debug
Diagnose a failing Cloud Run service — Antigravity (agy/Gemini) digests the error logs cheaply, Claude infers
Slk MCP
Slack MCP server for Claude Code, GitHub Copilot, Cursor, JetBrains, and any MCP-compatible client. Morning re