Code Reviewer Cross — Data & AI agent for Claude Code
Use to delegate code review to the cross-LLM DeepAgent reviewer (foundry-auditor) — useful when a second-opinion is desired beyond the native Claude review, when a PR is large, or for the monthly audi.
How to install Code Reviewer Cross
Installs to ~/.claude/agents/rafaelnovaes22-agent-governance-framework-code-reviewer-cross.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/rafaelnovaes22/agent-governance-framework/HEAD/.claude/agents/code-reviewer-cross.md -o ~/.claude/agents/rafaelnovaes22-agent-governance-framework-code-reviewer-cross.md Restart Claude Code, or start a new session, for it to be picked up.
What Code Reviewer Cross does
name: code-reviewer-cross description: Use to delegate code review to the cross-LLM DeepAgent reviewer (foundry-auditor) — useful when a second-opinion is desired beyond the native Claude review, when a PR is large, or for the monthly audit run. Provides the bridge between Claude Code session and the LangChain DeepAgent process. Does not run a model itself — invokes the external deepagents CLI. model: claude-haiku-4-5-20251001 tools: [Read, Write, Glob, Bash] foundry_agent_version: 0.1.0 lin
Alternatives in Data & AI
- Callstackincubator — A collection of agent-optimized React Native skills for AI coding assistants 1k ★
- ZeroClaw Android — Run AI agents 24/7 on your Android phone 281 ★
- Docs Reference — Specialized agent for looking up Protheus documentation - native functions, SX data dictionary, REST APIs, MV 136 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Glm Agent
Runs Z.AI GLM on the user's GLM Coding Plan. Three modes - consult (direct API call, 1M context, for inputs to
Consult Agent
Execute cross-tool AI consultations via Task spawning. Use when agents or workflows need a second opinion from
Claude Advisor
Second-opinion advisor running Claude's most capable model (Fable 5). Consult at commitment boundaries — befor
Explainer Director
Delegate to this agent to make a vertical first-person making-of video (3-5 min, 公众号/视频号/抖音) with real-data ca
Review Context
Pre-review architectural context gatherer. Explores the codebase beyond the diff to produce a structured summa
Doc Bar Raiser
Review PR/FAQs and written narratives for customer obsession, clarity, data over opinion, and genuinely hard F
Related Skills
Ask Claude And Sol For Codex
A second opinion is useful. Two independent second opinions are more useful
UX A11y
WCAG 2.1 AA accessibility audit plus common-courtesy checks beyond the spec. Produces findings grouped by WCAG
Audit With Verification
Run a parallel-review-then-adversarial-verify audit on a URL, feature spec, or code path. Dispatches N reviewe