agentcmd: Command for Claude Code

Review Spec Implementation

Reviews a previous agent's implementation work by comparing the provided spec file against actual code changes. Identifies discrepancies and documents all findings in a Review Findings section appended to the spec. The documented issues can then be addressed by running /cmd:implement-spec on the updated spec file.

Variables

• $specIdOrNameOrPath: $1 (required) - Either a timestamp ID (e.g., 251024120101), feature name (e.g., workflow-safety), or full path
• $format: $2 (optional) - Output format: "text" or "json" (defaults to "text" if not provided)
• $max-reviews: 3 - This is a constant (maximum review iterations allowed)

Spec File Resolution

Parse and resolve $specIdOrNameOrPath:

• If it's a full path (contains /): use as-is
• Otherwise, look up in .agent/specs/index.json:
  • For timestamp ID: Match by id field
  • For feature name: Fuzzy match path (e.g., message-queue matches todo/251024120101-message-queue-implementation/spec.md)
  • Use path from index: .agent/specs/{path}
• If not found in index.json, fallback to directory search:
  • Search in order: backlog/, todo/, done/
  • For ID: Pattern {id}-*/spec.md
  • For feature name: Pattern *{feature-name}*/spec.md (fuzzy match)
• If still not found: stop and report error

Instructions

• REVIEW ONLY - This command does not implement fixes
• Evidence-based - Every finding must cite file:line and quote spec requirements
• Priority-focused - Only document HIGH and MEDIUM priority issues (see guidelines below)
• Pragmatic mindset - Ask "would this block a PR merge?" not "could this be better?"
• Project standards - Check .agent/docs/code-review-standards.md for detailed review methodology. If that file is missing, look for best practices in CLAUDE.MD
• Maximum Iterations: Reviews stop automatically after 3 iterations
• Act as a professional code auditor, not a nitpicking perfectionist
• If $format is not provided, default to "text"