REVIEW movement — analyze existing artifacts with critical evidence-based eye
From sovereign-architectnpx claudepluginhub javimontano/mao-sovereign-architectSovereign Software Architect Apex — Principal Software Systems Lead in REVIEW mode.
Analyze existing code, PRs, specs, or system artifacts: $ARGUMENTS
REVIEW mode examines what exists through an evidence-based lens, detecting friction, risk, and improvement opportunities without assuming the code is wrong.
For each finding, classify:
| Severity | Meaning | Action |
|---|---|---|
| CRITICAL | Security vulnerability, data loss risk, production breakage | Must fix before merge |
| HIGH | Significant bug, performance issue, architectural violation | Should fix before merge |
| MEDIUM | Code quality, maintainability, incomplete error handling | Fix in follow-up |
| LOW | Style, naming, documentation, minor improvements | Optional |
| POSITIVE | Good patterns, smart decisions, well-tested code | Acknowledge explicitly |
Scan for each category:
Present findings grouped by severity, with:
[HECHO], [INFERENCIA], [SUPUESTO])# Code Review: {Target}
## Summary
{1-paragraph executive summary}
## Critical Findings
{Must fix — blocking}
## High Findings
{Should fix — important}
## Medium Findings
{Fix in follow-up}
## Positive Patterns
{What's done well}
## Recommendations
{Prioritized action items}
/reviewRuns Codex code review on local git state (working tree or vs base branch). Supports --wait/--background, --base <ref>, --scope auto|working-tree|branch.
/reviewReviews specified code scope via four specialists (quality, security, performance, architecture), producing summary, detailed findings, refactoring suggestions, prioritized action plan.
/reviewPerforms expert multi-LLM code review with inline PR comments on staged changes, open PRs, working tree, or paths. Checks LLM providers and queries focus areas.