GitHub

Agents

DESIGN

Name Description Preloaded skills
nw-ddd-architect Use for DESIGN wave domain modeling. Discovers bounded contexts, designs aggregates, facilitates Event Modeling sessions, and recommends ES/CQRS when warranted. 8
nw-ddd-architect-reviewer Use for reviewing DDD domain models. Validates bounded context boundaries, aggregate design, context mapping, ES/CQRS recommendations, and ubiquitous language consistency. 5
nw-platform-architect Use for DESIGN wave (infrastructure design) and DEVOPS wave (deployment execution, production readiness, stakeholder sign-off). Transforms architecture into deployable infrastructure, then coordinates production delivery and outcome measurement. 11
nw-platform-architect-reviewer Use for review and critique tasks - Platform design, CI/CD pipeline, infrastructure, observability, deployment readiness, and production handoff review specialist. Runs on Haiku for cost efficiency. 4
nw-system-designer Use for DESIGN wave infrastructure-level architecture. Designs distributed systems, scalability strategies, load balancing, caching, database sharding, message queues, back-of-envelope estimation, and trade-off analysis. Complements solution-architect (application-level) with infrastructure-level depth. 7
nw-system-designer-reviewer Use to review system design architecture outputs. Validates trade-off analysis, estimation accuracy, pattern applicability, SPOF detection, and scalability claims. Pairs with system-designer. 4

DELIVER

Name Description Preloaded skills
nw-lane-orchestrator Runs one nwdes lane end to end for the root in the DELIVER wave. Launches the installed role agents, never does role work, reports to the root. 4

Other

Name Description Preloaded skills
nw-acceptance-designer Authors the public executable oracle when required. 15
nw-acceptance-designer-reviewer Independently approves or finds defects in the consolidated public oracle. 9
nw-agent-builder Use when creating new AI agents, validating agent specifications, optimizing requested existing SKILL.md assets, optimizing command definitions, or ensuring compliance with Claude Code best practices. Creates focused, research-validated agents (200-400 lines) with Skills for domain knowledge. 11
nw-agent-builder-reviewer Use for review and critique tasks - Agent design and quality review specialist. Runs on Haiku for cost efficiency. 6
nw-data-engineer Use for database technology selection, data architecture design, query optimization, schema design, security implementation, and governance guidance. Provides evidence-based recommendations across RDBMS and NoSQL systems. 5
nw-data-engineer-reviewer Use for review and critique tasks - Data architecture and pipeline review specialist. Runs on Haiku for cost efficiency. 2
nw-diverger Use before DISCUSS — runs JTBD analysis, competitive research, structured brainstorming, and taste-filtered evaluation to produce 3-5 design directions before the team converges on one. Use when the team has a validated problem but hasn't chosen a solution approach. 5
nw-diverger-reviewer Use as peer reviewer for nw-diverger outputs — validates JTBD rigor, research evidence quality, option structural diversity, taste application correctness, and recommendation coherence. Runs on Haiku for cost efficiency. 3
nw-documentarist Use for documentation quality enforcement using DIVIO/Diataxis principles. Classifies documentation type, validates against type-specific criteria, checks diagrams against the nw-diagram accessibility rules, detects collapse patterns, and, when documents.readable_brief is enabled, runs one round of questions to the owning roles and presents their decisions. 4
nw-documentarist-reviewer Use for reviewing documentarist assessments. Validates classification accuracy, validation completeness, collapse detection, and recommendation quality using Haiku model. 3
nw-functional-software-crafter Implements the functional change for one ready ordered batch. 6
nw-nwave-buddy Use for any nWave question — methodology, project navigation, command help, wave status, migration, and troubleshooting. The first agent to consult when unsure about anything in nWave. 5
nw-plugin-validator Use to validate Claude Code plugin structure and schema during DISTILL/DELIVER verification when deliverable_type is plugin. Validates plugin manifest, directory layout, hook/command/agent registration, and Claude Code plugin schema compliance. No existing agent knows the plugin schema. Runs on Haiku for cost efficiency. 1
nw-product-discoverer Conducts evidence-based product discovery through customer interviews, assumption testing, and opportunity validation. Use when validating problems exist, prioritizing opportunities, or confirming market viability before writing requirements. 4
nw-product-discoverer-reviewer Use as peer reviewer for product-discoverer outputs -- validates evidence quality, sample sizes, decision gate compliance, bias detection, and discovery anti-patterns. Runs on Haiku for cost efficiency. 2
nw-product-owner Owns DISCUSS, facilitates human product decisions, and derives visible feedback-oriented value increments. 7
nw-product-owner-reviewer Reviews DISCUSS product decisions, human understanding and visible increments, or an explicitly assigned expectation-charter namespace. 5
nw-researcher Use for evidence-driven research with source verification. Gathers knowledge from web and files, cross-references across multiple sources, and produces cited research documents. 5
nw-researcher-reviewer Use for review and critique tasks - Research quality and evidence review specialist. Runs on Haiku for cost efficiency. 2
nw-skill-reviewer Use to review SKILL.md quality during DISTILL/DELIVER verification when deliverable_type is plugin or skill. Validates skill structure, scope discipline, frontmatter, and domain-knowledge quality. Thin reviewer — reuses nw-agent-builder skill assets. Runs on Haiku for cost efficiency. 3
nw-software-crafter Implements the object-oriented or procedural change for one ready ordered batch. 4
nw-software-crafter-reviewer Independently reviews the whole candidate with captured native evidence. 7
nw-solution-architect Use for application architecture decisions, boundaries, reuse and evidence-backed design. 12
nw-solution-architect-reviewer Reviews durable architecture decisions for evidence, reuse, boundaries, cross-layer algebra, residual stress behavior, test substrate, and absence of drift. 8
nw-test-optimizer Minimize test cost while preserving observable behavior and coverage. Reads production code but modifies tests only. 2
nw-test-optimizer-reviewer Independently reviews test optimization. Read-only; vetoes production drift, behavior or coverage loss, and unmapped deletion. 2
nw-troubleshooter Use for investigating system failures, recurring issues, unexpected behaviors, or complex bugs requiring systematic root cause analysis with evidence-based investigation. 5
nw-troubleshooter-reviewer Independently falsifies root-cause analyses and their prevention claims. 2
nw-user-examiner User-view assessment of fixed public expectations and independently gathered public observations at final EXAMINE. 1
nw-ux-designer Supports PO-led DISCUSS with user journeys, accessible interface design and bounded visual prototypes; reuses the product's design system. 3

All Agents

Name Wave Description Preloaded skills
nw-acceptance-designer Other Authors the public executable oracle when required. 15
nw-acceptance-designer-reviewer Other Independently approves or finds defects in the consolidated public oracle. 9
nw-agent-builder Other Use when creating new AI agents, validating agent specifications, optimizing requested existing SKILL.md assets, optimizing command definitions, or ensuring compliance with Claude Code best practices. Creates focused, research-validated agents (200-400 lines) with Skills for domain knowledge. 11
nw-agent-builder-reviewer Other Use for review and critique tasks - Agent design and quality review specialist. Runs on Haiku for cost efficiency. 6
nw-data-engineer Other Use for database technology selection, data architecture design, query optimization, schema design, security implementation, and governance guidance. Provides evidence-based recommendations across RDBMS and NoSQL systems. 5
nw-data-engineer-reviewer Other Use for review and critique tasks - Data architecture and pipeline review specialist. Runs on Haiku for cost efficiency. 2
nw-ddd-architect DESIGN Use for DESIGN wave domain modeling. Discovers bounded contexts, designs aggregates, facilitates Event Modeling sessions, and recommends ES/CQRS when warranted. 8
nw-ddd-architect-reviewer DESIGN Use for reviewing DDD domain models. Validates bounded context boundaries, aggregate design, context mapping, ES/CQRS recommendations, and ubiquitous language consistency. 5
nw-diverger Other Use before DISCUSS — runs JTBD analysis, competitive research, structured brainstorming, and taste-filtered evaluation to produce 3-5 design directions before the team converges on one. Use when the team has a validated problem but hasn't chosen a solution approach. 5
nw-diverger-reviewer Other Use as peer reviewer for nw-diverger outputs — validates JTBD rigor, research evidence quality, option structural diversity, taste application correctness, and recommendation coherence. Runs on Haiku for cost efficiency. 3
nw-documentarist Other Use for documentation quality enforcement using DIVIO/Diataxis principles. Classifies documentation type, validates against type-specific criteria, checks diagrams against the nw-diagram accessibility rules, detects collapse patterns, and, when documents.readable_brief is enabled, runs one round of questions to the owning roles and presents their decisions. 4
nw-documentarist-reviewer Other Use for reviewing documentarist assessments. Validates classification accuracy, validation completeness, collapse detection, and recommendation quality using Haiku model. 3
nw-functional-software-crafter Other Implements the functional change for one ready ordered batch. 6
nw-lane-orchestrator DELIVER Runs one nwdes lane end to end for the root in the DELIVER wave. Launches the installed role agents, never does role work, reports to the root. 4
nw-nwave-buddy Other Use for any nWave question — methodology, project navigation, command help, wave status, migration, and troubleshooting. The first agent to consult when unsure about anything in nWave. 5
nw-platform-architect DESIGN Use for DESIGN wave (infrastructure design) and DEVOPS wave (deployment execution, production readiness, stakeholder sign-off). Transforms architecture into deployable infrastructure, then coordinates production delivery and outcome measurement. 11
nw-platform-architect-reviewer DESIGN Use for review and critique tasks - Platform design, CI/CD pipeline, infrastructure, observability, deployment readiness, and production handoff review specialist. Runs on Haiku for cost efficiency. 4
nw-plugin-validator Other Use to validate Claude Code plugin structure and schema during DISTILL/DELIVER verification when deliverable_type is plugin. Validates plugin manifest, directory layout, hook/command/agent registration, and Claude Code plugin schema compliance. No existing agent knows the plugin schema. Runs on Haiku for cost efficiency. 1
nw-product-discoverer Other Conducts evidence-based product discovery through customer interviews, assumption testing, and opportunity validation. Use when validating problems exist, prioritizing opportunities, or confirming market viability before writing requirements. 4
nw-product-discoverer-reviewer Other Use as peer reviewer for product-discoverer outputs -- validates evidence quality, sample sizes, decision gate compliance, bias detection, and discovery anti-patterns. Runs on Haiku for cost efficiency. 2
nw-product-owner Other Owns DISCUSS, facilitates human product decisions, and derives visible feedback-oriented value increments. 7
nw-product-owner-reviewer Other Reviews DISCUSS product decisions, human understanding and visible increments, or an explicitly assigned expectation-charter namespace. 5
nw-researcher Other Use for evidence-driven research with source verification. Gathers knowledge from web and files, cross-references across multiple sources, and produces cited research documents. 5
nw-researcher-reviewer Other Use for review and critique tasks - Research quality and evidence review specialist. Runs on Haiku for cost efficiency. 2
nw-skill-reviewer Other Use to review SKILL.md quality during DISTILL/DELIVER verification when deliverable_type is plugin or skill. Validates skill structure, scope discipline, frontmatter, and domain-knowledge quality. Thin reviewer — reuses nw-agent-builder skill assets. Runs on Haiku for cost efficiency. 3
nw-software-crafter Other Implements the object-oriented or procedural change for one ready ordered batch. 4
nw-software-crafter-reviewer Other Independently reviews the whole candidate with captured native evidence. 7
nw-solution-architect Other Use for application architecture decisions, boundaries, reuse and evidence-backed design. 12
nw-solution-architect-reviewer Other Reviews durable architecture decisions for evidence, reuse, boundaries, cross-layer algebra, residual stress behavior, test substrate, and absence of drift. 8
nw-system-designer DESIGN Use for DESIGN wave infrastructure-level architecture. Designs distributed systems, scalability strategies, load balancing, caching, database sharding, message queues, back-of-envelope estimation, and trade-off analysis. Complements solution-architect (application-level) with infrastructure-level depth. 7
nw-system-designer-reviewer DESIGN Use to review system design architecture outputs. Validates trade-off analysis, estimation accuracy, pattern applicability, SPOF detection, and scalability claims. Pairs with system-designer. 4
nw-test-optimizer Other Minimize test cost while preserving observable behavior and coverage. Reads production code but modifies tests only. 2
nw-test-optimizer-reviewer Other Independently reviews test optimization. Read-only; vetoes production drift, behavior or coverage loss, and unmapped deletion. 2
nw-troubleshooter Other Use for investigating system failures, recurring issues, unexpected behaviors, or complex bugs requiring systematic root cause analysis with evidence-based investigation. 5
nw-troubleshooter-reviewer Other Independently falsifies root-cause analyses and their prevention claims. 2
nw-user-examiner Other User-view assessment of fixed public expectations and independently gathered public observations at final EXAMINE. 1
nw-ux-designer Other Supports PO-led DISCUSS with user journeys, accessible interface design and bounded visual prototypes; reuses the product's design system. 3