challenge-pr
01Command Codex
Challenge a pull request with an independent second opinion from another model.
Command Codex
Challenge a pull request with an independent second opinion from another model.
Command Codex
Run the full implementation pipeline - implement, check for spec deviations, and test - in a single automated step.
Command Codex
Commit staged changes, create or update a pull request.
Command Codex
Resolve reviewer feedback - from GitHub PRs, chat, or any reviewer.
Command Codex
Run the full specification pipeline - specify, review, revise, and plan - in a single automated step.
Command Codex
Forensic audit of an implementation against its authoritative specification.
Command Codex
Architectural review of a specification before implementation begins.
Command Claude Code
$ARGUMENTS.
Command Claude Code
Every subagent invocation uses the delegation tool with the appropriate subagenttype (the implementation subagent, the tester subagent, or any specialized subagent the project ships). That tool is named Agent in an interactive Claude Code session and Task in the headless runtime (claude -p, Agent SDK). Read your…
Command Claude Code
$ARGUMENTS.
Command Claude Code
$ARGUMENTS.
Command Claude Code
Every subagent invocation uses the delegation tool with the appropriate subagenttype (architect, arch-review, planner). That tool is named Agent in an interactive Claude Code session and Task in the headless runtime (claude -p, Agent SDK). Read your toolbox and call whichever of the two is actually present; do not…
Command Claude Code
Specification file: $ARGUMENTS.
Command Claude Code
Task: $task Specification file: $specPath.
Command Gemini CLI
@arch-review.