Subagents

package-risk-summary

Use this agent when the user wants a concise risk profile for a specific package version without asking for a yes/no dependency decision. Examples: "Summarize npm lodash 4.17.20 risk", "Give me the risk picture for log4j-core 2.14.1", "What should I know about this package version before I review it

structure_architect_agent

Designs the papers section architecture and detailed outline before drafting begins

workflow-quality

Use this agent when you need expert guidance on Output SDK implementation patterns, code quality, and best practices. Invoke when writing or reviewing workflow code, troubleshooting implementation issues, or ensuring code follows SDK conventions.

nimble-researcher

Fast data gathering agent for Nimble business skills. Use proactively when a skill needs to search the web, find news, or gather raw data about companies, competitors, or people. Optimized for speed and cost — runs parallel searches and returns structured results quickly. Does not write files or pro

research-agent

Use this agent when the user asks to "research [competitor]", "scout [name]", "competitive intelligence", "analyze [company]", "what does [competitor] do", or needs deep autonomous competitor research. Performs multi-source web research to build comprehensive competitor profiles. <example>

migration-reviewer

Use this agent after aidp-migrate-job completes to review a migrated .ipynb for correctness (NOT just "did it run"). Catches latent issues the cell-execute loop missed — wrong write-mode, lost rows, dropped columns, hardcoded paths, dead Databricks-isms. Outputs a structured review report.

report_compiler_agent

Transforms research findings into polished APA 7.0 academic reports; activated in Phase 4 and Phase 6

render-assistant

Render deployment specialist that helps with render.yaml authoring, service configuration, debugging, and monitoring.

editor_in_chief_agent

Q1 journal editorial review; delivers Accept/Reject verdict with actionable feedback on research reports

sonarqube-reviewer

Reviews code changes against SonarQube quality, security, and dependency-risk standards by composing this plugin's sonar-* skills. Use proactively before merging a PR or when the user asks for a SonarQube-based code review, a second opinion on code quality, or to "review my changes with SonarQube.

gap-analyst

Use this agent when the user asks to "find gaps", "what are we missing", "gap analysis", "what should we build", "identify opportunities", "feature gaps", or needs systematic identification of product gaps with WINNING filter scoring. Performs batch gap analysis with deduplication against existing G

domain_reviewer_agent

Peer Reviewer 2; assesses domain expertise, substantive accuracy, and field-specific adequacy

vulnerability-explainer

Use this agent when the user asks what a specific vulnerability means and how to reason about it. Examples: "Explain CVE-2021-44228", "What does CVE-2021-45046 mean for log4j-core?", "Summarize this Endor vulnerability and tell me what to do next." Returns a concise vulnerability explanation with se

connector-researcher

Research source systems for DataHub connector development. Gathers documentation, finds similar connectors, identifies entity mappings, and assesses implementation complexity. Returns structured findings for planning phase. <example> Context: User wants to build a new DataHub connector for a source

agentcore-sme

Amazon Bedrock AgentCore subject matter expert for building production-ready AI agents. Use when prototyping new agents, hardening PoC agents for production, setting up agent observability and evaluation pipelines, or architecting multi-agent systems on AWS.

cost-optimizer

Deep AWS cost optimization expert. Use when analyzing AWS spend, rightsizing resources, evaluating Reserved Instances or Savings Plans, optimizing data transfer costs, or building a cost governance strategy.

literature_strategist_agent

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

error-analyzer

Analyze multiple PostHog errors in parallel to identify patterns, root causes, and prioritize fixes based on user impact.

test-engineer

Writes characterization, contract, and equivalence tests that pin down legacy behavior so transformation can be proven correct. Use before any rewrite.

timeline_extraction_agent

Extracts per-source temporal facts and citation provenance into Phase 2 sidecar artifacts; activated in Phase 2 (Investigation)

editorial_synthesizer_agent

Synthesizes all reviewer reports into a unified editorial decision letter and revision roadmap