Review Archify issues, pull requests, and code by weighing user value, implementation and maintenance costs, and wider impact. Use evidence to decide whether work is worthwhile, compare alternatives, and identify questions that still affect the decision.
Review Archify issues, PRs, or code through value, cost, and impact to support evidence-based maintenance decisions. Use for issue triage, change reviews, and code quality assessments.
Review the instructions the agent will receive before you install.
Judge whether a problem is worth addressing and an approach is worth maintaining over time.
Consider maintainability, complexity, compatibility, performance, and other relevant concerns within these three dimensions, according to the specific problem.
Ground judgments in evidence: verify the target revision and relevant facts, distinguish direct verification from existing evidence and assumptions, and choose checks that resolve the key uncertainties.
Explain whether the work is worthwhile, the approach's cost and impact, any better alternatives, and unresolved questions that matter to the decision. Give reasons and scale the detail to the importance of each concern.
For repository-specific review and contribution requirements, consult REVIEWING.md and CONTRIBUTING.md as needed.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Turn plain-language descriptions, Mermaid diagrams, or repository evidence into interactive standalone HTML diagrams. Create system maps, workflows, timelines, database relationships, and everyday process diagrams, with automated validation, light and dark themes, and image, SVG, or WebM export.
Evaluate improvements to Archify diagrams using actual outputs and agent work records. Compare accuracy, readability, and total delivery time to investigate layout, connection routing, diagnostics, and authoring guidance, then document what the evidence supports.
Audit a codebase for unnecessary complexity, including dead code, duplicated state, redundant interfaces, and obsolete compatibility paths. Receive evidence-backed simplification candidates, or authorize changes that remove justified targets and validate the behavior that must remain.
Evaluate slow, unreliable, duplicated, or brittle tests by the behavior they protect and their maintenance cost. Use it to choose focused checks, justify additions or removals, and distinguish product bugs from outdated expectations or environment failures.