Stats
Actions
Tags
From claude-commands
Executes a sequential code review workflow: /cons for bug and correctness checks, /pushl, /reviewdeep, /copilot, and /guidelines.
How this command is triggered — by the user, by Claude, or both
Slash command
/claude-commands:autocommands/The summary Claude sees in its command listing — used to decide when to auto-load this command
## ⚡ EXECUTION INSTRUCTIONS FOR CLAUDE **When this command is invoked, YOU (Claude) must execute these steps immediately:** **This is NOT documentation - these are COMMANDS to execute right now.** **Use TodoWrite to track progress through multi-phase workflows.** ## 🚨 EXECUTION WORKFLOW ### Phase 1: Execute Documented Workflow **Action Steps:** 1. Review the reference documentation below and execute the detailed steps sequentially. ## 📋 REFERENCE DOCUMENTATION # /auto Command Run the following workflow in order, making sure to complete each command fully without skipping any steps: ...
When this command is invoked, YOU (Claude) must execute these steps immediately: This is NOT documentation - these are COMMANDS to execute right now. Use TodoWrite to track progress through multi-phase workflows.
Action Steps:
Run the following workflow in order, making sure to complete each command fully without skipping any steps:
/cons – Carefully review the code for bugs and correctness issues, including logic errors, edge cases, off-by-one errors, and violations of expected behavior. Focus only on correctness, not style or performance. For more details on the /cons command and examples of issues to look for, see the Cons Command Documentation./pushl/reviewdeep/copilot/guidelinesnpx claudepluginhub jleechanorg/claude-commands --plugin claude-commands/codex-reviewOrchestrates a deep code review using Codex jobs for detection, validation, and cross-cutting analysis, producing an artifact.json compatible with the :review workflow.
/reviewAnalyzes and fixes code using parallel subagents in review (changes), audit (path/codebase), or fix modes. Effort scales to input size.
/santa-loopRuns adversarial dual AI code review loop: two independent reviewers (Claude Opus + external model) must both approve changes before commit, with up to 3 fix-review cycles.
/deep-reviewConducts multi-perspective code review with 5 specialized agents, autonomous fix loop, and generates Deep Review Report.
/reviewPerforms multi-agent code review on file-path/scope or unstaged git changes, validating compliance, bugs, security vulnerabilities, and performance issues.