
Single-agent diagnose and design-compliance review workflow using Codex skills. Replaces investigator/verifier/solver and code-reviewer subagent chains.
Sends commands to another tmux pane. Use when requests include phrases like "run it in another pane," "send via tmux," or "ask Claude Code to execute."
Backend diagnosis workflow for Claude without investigator/verifier/solver subagents. Performs evidence collection, validation, and solution derivation with confidence control.
Document workflow for backend design/plan/reverse-engineer/update-doc commands in Claude without subagent dependency.
Add integration and E2E tests to existing backend code in Claude without subagent delegation. Mirrors add-integration-tests command flow with review and quality gates.
Backend task/build/review execution loop in Claude without subagents. Enforces per-task quality gates and design-compliance checks.
End-to-end lifecycle orchestration with a single Codex agent. Replaces subagent workflow coordination while preserving scale-based phases, stop points, and quality gates.
Unified deterministic entry for workflow requests. Centralizes routing with stop/approval and sandbox controls.
Single-agent execution loop for implementation tasks. Replaces task-executor/quality-fixer subagent cycle with direct Codex skill-driven implementation and quality gates.
Document-centered workflow for design, planning, reverse-engineering, and updates using Codex skills only. Replaces document-focused subagent chains.
End-to-end backend lifecycle execution in Claude without subagent delegation. Preserves scale-based orchestration and approval gates from claude-code-workflows backend.
Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing