Dual Reviewer — Development agent for Claude Code
Second-phase Codex code-review loop with Claude adjudication, after pr-reviewer in the branch review pass or manually invoked.
How to install Dual Reviewer
Installs to ~/.claude/agents/michaelhazza-claude-code-framework-dual-reviewer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/michaelhazza/claude-code-framework/HEAD/.claude/agents/dual-reviewer.md -o ~/.claude/agents/michaelhazza-claude-code-framework-dual-reviewer.md Restart Claude Code, or start a new session, for it to be picked up.
What Dual Reviewer does
name: dual-reviewer description: "Second-phase Codex code-review loop with Claude adjudication, after pr-reviewer in the branch review pass or manually invoked. Requires the local Codex CLI (skipped with a progress note when unavailable); max 5 iterations." tools: Bash, Read, Glob, Grep, Edit, Write model: opus
**Project context (read first).** If `.claude/context/agent-context.md` exists, consume it with bounded reads in this exact order — NEVER a whole-file Read: (1) Grep the file for
Alternatives in Development
- Correction Sweep — Find every note restating a corrected fact and classify each as authoritative, restatement, or historical 4.6k ★
- 🖥️ Multi-Window Context — TL;DR: State persistence across Claude Code sessions 243 ★
- After Identifying Or Executing A Chain — findings.sh add chain " " --score \ --steps " step2 -> step3>" --mitre " " findings.sh update chain --status < 213 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Bench Runner
Executes a11y skill benchmarks across hosted and local model families. Runs cloud/Codex/Ollama benchmark scrip
Claude Code Writer
Explicit file-writing Claude Code CLI mode; requires local authentication and trusted user settings/hooks
Codex Consultant
An independent code review and debugging subagent that uses Codex MCP as its sole execution engine, acting as
Ask
Quick single-shot query to Codex or Gemini — second opinion, cross-review, or comparison
Codex Adversarial Reviewer
Adversarial reviewer that calls Codex CLI for an independent second-opinion review of changed files, then adju
Implementation Summarizer B0
Summarizes completed implementations for Branch 0 and updates the roadmap with progress. A similar agent would
Related Skills
Codex Loop
Use Codex as a second, differently-trained reviewer of your branch, fix every real finding with regression tes
Poll CI
Polls the current branch's CI run and reports pass/fail/in-progress (fallback for monitor-ci)
Check Docs SEO
Check whether documentation needs SEO/positioning updates after code changes. Run manually or invoked automati