Arthur — Project Management agent for Claude Code
Independent code review via the Codex CLI (read-only, headless) for a second opinion that reads project files freely and reasons across multiple files.
How to install Arthur
Installs to ~/.claude/agents/kaisa-kucherenko-claude-code-flow-arthur.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/kaisa-kucherenko/claude-code-flow/HEAD/agents/arthur.md -o ~/.claude/agents/kaisa-kucherenko-claude-code-flow-arthur.md Restart Claude Code, or start a new session, for it to be picked up.
What Arthur does
name: arthur description: Independent code review via the Codex CLI (read-only, headless) for a second opinion that reads project files freely and reasons across multiple files. Slower than a quick diff check but strong on architecture, multi-file refactors, and subtle bugs. Complement to Agatha (deep Claude Opus review) and Dash (fast Claude Sonnet review) — they catch different classes of issues. Invoke whenever the user says "Артур", "arthur", "codex рев'ю", "рев'ю через кодекс", "відправ
Alternatives in Project Management
- Claude Squad — Manages multiple AI terminal agents including Claude Code and Aider in parallel 5.6k ★
- Maestro — You are a specialized orchestration agent 3.6k ★
- Search Conversations — Use when searching Claude Code and Codex history for information learned in past conversations or prior experi 469 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Aux Delegator
Invokes external CLI coding agents (Codex, OpenCode, Claude -p, ACP). Use whenever a task should be offloaded
Bfl Node Reviewer
Independent second-opinion diff reviewer for ComfyUI-FLUX-BFL-API. Loads BFL invariants into fresh context and
ChatGPT Reviewer
Use when the main thread wants a second opinion on a change from ChatGPT without spending its own context read
Flow Code Reviewer
Independent adversarial reviewer for a branch diff. Dispatched by flow-ship-issue's review phase (or manually)
Mp Adversarial Reviewer
Adversarial second-opinion review of a completed masterplan task. The harness runs this agent on the routing p
Envoy Runner
Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper roo
Related Skills
Agy Review
Adversarial critique via agy using Gemini Pro — independent second opinion on code, plans, or arguments
Ask Claude And Sol For Codex
A second opinion is useful. Two independent second opinions are more useful
Ask Codex
Ask Codex CLI for an independent second opinion on a plan or decision