Best Other Subagents

Deep-reads legacy codebases (COBOL, Java, .NET, Node, anything) to build structural and behavioral understanding. Use for discovery, dependency mapping, dead-code detection, and "what does this system actually do" questions.

Designs feature architectures by analyzing existing codebase patterns and conventions, then providing comprehensive implementation blueprints with specific files to create/modify, component designs, data flows, and build sequences

Migrates ONE project/module of an in-flight same-stack version uplift by applying a proven pilot playbook — minimal diff, then runs that unit's real build to prove it. Refuses to migrate anything if no playbook exists yet. Write access is scoped to its own unit's directory inside the uplift working

Designs the methodological blueprint; selects research paradigm, method, data strategy, and analytical framework

Designs the literature search strategy and manages source selection for the paper

Designs the papers section architecture and detailed outline before drafting begins

Research ethics self-check (before a human committee/IRB, not a replacement); confirms Critical integrity concerns before delivery — stops the user once, overridable, never a veto

Quantitative synthesis of included studies; computes effect sizes, assesses heterogeneity, and applies GRADE framework

Integrates findings across sources, resolves evidence conflicts, and maps knowledge gaps

Assesses risk of bias in included studies using RoB 2 (RCTs) and ROBINS-I (non-randomized studies)

Transforms vague topics into precise, FINER-evaluated researchable questions through iterative refinement

Conducts the paper configuration interview and produces the Paper Configuration Record for downstream agents

Use this agent when the user asks whether to add, upgrade, or use a specific package version. Examples: "Is lodash 4.17.20 safe?", "Should I use requests 2.28.0?", "Check log4j-core 2.14.1 before I add it." Returns a dependency verdict with evidence, conditions, alternatives, and any data gaps.

Preview safe remediation options without opening PRs.

Challenges assumptions, tests logical chains, and stress-tests research arguments at mandatory checkpoints