review

Review

Orchestrated code review that launches 5 specialized agents in parallel.

Input

• $ARGUMENTS — Review scope (optional)
  • Empty/omitted: unstaged changes (git diff)
  • staged: staged changes (git diff --cached)
  • HEAD: last commit (git show HEAD)
  • <commit>: specific commit
  • <file1> <file2>...: specific files
  • <branch>: changes on branch vs main

Agents

Agent	Focus
orc:code-reviewer	CLAUDE.md compliance, bugs, quality
orc:silent-failure-hunter	Error handling, silent failures
orc:test-analyzer	Test coverage, gaps, quality
orc:type-design-analyzer	Type invariants, encapsulation
orc:frontend-verifier	UI verification via browser automation

Process

Step 1: Enter Plan Mode

Use EnterPlanMode tool to enter planning mode. The review findings will form the plan for fixes.

Step 2: Determine Review Scope

Parse $ARGUMENTS to determine what to review:

if $ARGUMENTS is empty:
  scope = "unstaged changes"
  diff_cmd = "git diff"
elif $ARGUMENTS == "staged":
  scope = "staged changes"
  diff_cmd = "git diff --cached"
elif $ARGUMENTS == "HEAD":
  scope = "last commit"
  diff_cmd = "git show HEAD"
elif $ARGUMENTS matches commit hash:
  scope = "commit $ARGUMENTS"
  diff_cmd = "git show $ARGUMENTS"
else:
  scope = "$ARGUMENTS"
  diff_cmd = "git diff -- $ARGUMENTS" (or read files directly)

Run the diff command to get the changes to review.

Step 3: Launch 5 Parallel Review Agents

Launch ALL agents simultaneously using Task tool with subagent_type="orc:<agent>".

Critical: Send a SINGLE message with 5 Task tool calls to run them in parallel.

<Task subagent_type="orc:code-reviewer" description="Code review: guidelines">
Review scope: $scope

$diff_output

Review these changes against project guidelines (CLAUDE.md).
Focus on: compliance, bugs, code quality.
Report issues with confidence ≥80 only.
</Task>

<Task subagent_type="orc:silent-failure-hunter" description="Code review: error handling">
Review scope: $scope

$diff_output

Audit error handling in these changes.
Focus on: silent failures, empty catches, poor feedback.
Flag CRITICAL/HIGH/MEDIUM severity issues.
</Task>

<Task subagent_type="orc:test-analyzer" description="Code review: test coverage">
Review scope: $scope

$diff_output

Analyze test coverage for these changes.
Focus on: critical gaps, edge cases, test quality.
Rate gaps 1-10 (10 = must have).
</Task>

<Task subagent_type="orc:type-design-analyzer" description="Code review: type design">
Review scope: $scope

$diff_output

Evaluate type designs in these changes.
Focus on: invariants, encapsulation, enforcement.
Rate each dimension 1-10.
</Task>

<Task subagent_type="orc:frontend-verifier" description="Code review: UI verification">
Review scope: $scope

$diff_output

Verify the frontend still works correctly after these changes.
IMPORTANT: Backend API changes can break frontend even if no frontend files changed.

For backend changes: Test that frontends consuming these APIs still work.
For frontend changes: Test rendering, interactions, visual regressions.

Always:
1. Start the relevant services (backend + frontend)
2. Test key user flows end-to-end
3. Capture screenshots at each major step
4. Report any errors, broken flows, or unexpected behavior
</Task>