| name | domain-reviewer |
| description | Coordinate deep-dive reviews via specialized sub-agents as critics. Use for deep review of a specific module or domain (not general code review), when multiple specialized perspectives are needed (e.g. security plus performance plus correctness), or for pre-release review of critical system components. |
| license | MIT |
Domain & Module Reviewer
Coordinate deep-dive reviews of specific system domains or modules by engaging specialized sub-agents as critics.
When to Use
Reach here when one module or domain needs several specialist lenses at depth
(security + performance + correctness), coordinated via sub-agent critics. For a
general triple-lens pass over an ordinary change before merge, the lighter
sibling is audit-reviewer — don't spin up domain-reviewer's sub-agents for a
routine diff.
Workflow
-
Scope: Define boundaries of the module/domain to review
(e.g., "The Payment Gateway Service", "The Authentication flow").
-
Select Critics: Identify sub-agents for the review based on tech stack
and concerns (e.g., Go code quality, security, SQL performance).
-
Formulate Prompts: Draft clear, scoped prompts for each sub-agent,
asking them to evaluate specific aspects against architectural contracts.
-
Delegate: Execute sub-agent calls in parallel if possible.
-
Synthesize: Collect reports. Do not copy-paste output.
Extract critical architectural flaws and document them in an ADR or action plan.
Completion
- All sub-agent reviews collected and synthesized
- Critical findings documented in ADR or action plan
- No copy-pasted sub-agent output — findings are curated
Anti-Patterns
- Dumping raw sub-agent output without synthesis — the value is in curation
- Overly broad scope — review one domain at a time, not the entire system
- Skipping parallel execution — sub-agents are independent, run them concurrently
