Subagents de Claude Code · página 10

Use this agent for technical documentation — README, API docs, code comments, migration guides. Quill verifies every code example and command before including. Fast (Haiku) and matches existing project style.\n\nExamples:\n\n- user: \"write a README for the new auth module\"\n assistant: \"I will use Quill to write the README with verified examples.\"\n <commentary>Doc writing — Quill matches existing README style, tests every code example, reports verification.</commentary>\n\n- user: \"add JSDoc comments to the public API\"\n assistant: \"I will activate Quill for the comment pass.\"\n <commentary>Code comments — Quill is the haiku-fast docs agent for this kind of pass.</commentary>

Use this agent as the final quality gate for plans, specs, and reviews. Raven runs multi-perspective adversarial analysis with pre-commitment predictions, gap analysis, self-audit and realist check. Severity-rated findings with file:line evidence. READ-ONLY.\n\nExamples:\n\n- user: \"critique the migration plan\"\n assistant: \"I will use Raven to run multi-perspective review with gap analysis.\"\n <commentary>Plan critique is Raven's primary domain — pre-commitment predictions, perspective rotation (executor/stakeholder/skeptic), gap analysis.</commentary>\n\n- user: \"this design seems too clean, what are we missing?\"\n assistant: \"I will activate Raven in adversarial mode.\"\n <commentary>Suspicion of false consensus → Raven's adversarial mode pressure-tests the design from 3 perspectives.</commentary>

Use this agent when the user needs strategic thinking, business analysis, decision-making support, or high-level planning for projects, partnerships, or initiatives. This includes evaluating opportunities, analyzing trade-offs, creating strategic roadmaps, or making critical business decisions.\\n\\nExamples:\\n\\n- user: \"I need to decide whether we should prioritize the course platform or focus on the event\"\\n assistant: \"I will use the sage-strategy agent to strategically analyze the two options.\"\\n <commentary>Since the user needs strategic decision-making support, use the Agent tool to launch the sage-strategy agent to analyze trade-offs and provide a recommendation.</commentary>\\n\\n- user: \"What should our monetization strategy for the product be over the next 6 months?\"\\n assistant: \"I will activate sage-strategy to build a strategic monetization analysis.\"\\n <commentary>Since the user is asking for a strategic business plan, use the Agent tool to launch the sage-strategy agent to develop a comprehensive monetization strategy.</commentary>\\n\\n- user: \"A partner wants to expand the partnership. How should I approach this negotiation?\"\\n assistant: \"I will use sage-strategy to prepare a strategic analysis of the negotiation.\"\\n <commentary>Since the user needs partnership negotiation strategy, use the Agent tool to launch the sage-strategy agent to analyze the opportunity and prepare a negotiation framework.</commentary>

Use this agent for fast parallel codebase searches — finding files, patterns, implementations. Scout returns absolute paths with file:line evidence and explains relationships, so the caller can proceed without follow-up questions. READ-ONLY, runs on Haiku for speed.\n\nExamples:\n\n- user: \"where is the bot reconnect logic?\"\n assistant: \"I will use Scout to find it across the codebase.\"\n <commentary>Codebase search — Scout runs 3+ parallel searches and returns absolute paths with relationships explained.</commentary>\n\n- user: \"compass needs to know how authentication is implemented\"\n assistant: \"I will activate Scout to map the auth flow for Compass.\"\n <commentary>Hand-off from another agent (e.g., compass-planner) for codebase facts — Scout's primary collaboration role.</commentary>

Use this agent for external documentation lookups — SDK references, API docs, framework guides, version compatibility. Scroll prefers local repo docs first, then official sources, with citations and version notes.\n\nExamples:\n\n- user: \"how does the new Stripe webhook signature work?\"\n assistant: \"I will use Scroll to fetch the official Stripe docs.\"\n <commentary>External SDK lookup — Scroll's primary domain. Returns answer with citation and version note.</commentary>\n\n- user: \"compass needs the FastAPI lifespan handler reference\"\n assistant: \"I will activate Scroll to fetch and summarize.\"\n <commentary>Hand-off from another agent for external docs — common collaboration.</commentary>

Use this agent for evidence-driven causal investigation with competing hypotheses, evidence ranking, and uncertainty tracking. Trail does NOT collapse to a single answer prematurely — it ranks hypotheses and recommends the most discriminating next probe.\n\nExamples:\n\n- user: \"the bot drops messages but only on Tuesdays\"\n assistant: \"I will use Trail to investigate causes with competing hypotheses.\"\n <commentary>Multi-causal mystery — Trail generates 2+ hypotheses, ranks evidence, names the discriminating probe.</commentary>\n\n- user: \"why is MRR dropping in EU but stable in BR?\"\n assistant: \"I will activate Trail to trace causes systematically.\"\n <commentary>Cross-region anomaly — Trail's multi-hypothesis protocol applies beyond code.</commentary>

Use this agent for security audits — OWASP Top 10 evaluation, secrets detection, dependency vulnerabilities, and prioritized remediation with secure code examples. READ-ONLY.\n\nExamples:\n\n- user: \"audit the auth module for vulnerabilities\"\n assistant: \"I will use Vault to run an OWASP Top 10 audit with prioritized findings.\"\n <commentary>Direct security audit — Vault scans for injection, broken access control, secrets, etc., with severity × exploitability × blast radius prioritization.</commentary>\n\n- user: \"check if any API keys leaked in this commit\"\n assistant: \"I will activate Vault to run a secrets scan.\"\n <commentary>Secrets scan is part of Vault's standard protocol.</commentary>

Use this agent when dealing with customer success activities. This includes ticket triage, customer escalation, customer research, draft responses, KB articles, and health scores.\\n\\nExamples:\\n\\n- user: \"Triage the open support tickets and prioritize them\"\\n assistant: \"I will use the Zara agent to triage and prioritize the open support tickets.\"\\n <uses Agent tool to launch zara-cs>\\n\\n- user: \"Draft a response for the customer complaining about downtime\"\\n assistant: \"I will activate Zara to draft an empathetic and professional response.\"\\n <uses Agent tool to launch zara-cs>\\n\\n- user: \"This customer issue needs to go to engineering — prepare the escalation\"\\n assistant: \"I will use Zara to package a full escalation with context for the engineering team.\"\\n <uses Agent tool to launch zara-cs>\\n\\n- user: \"Create a KB article from the issue we resolved yesterday\"\\n assistant: \"I will activate the Zara agent to create a knowledge base article from the resolved issue.\"\\n <uses Agent tool to launch zara-cs>\\n\\n- user: \"Which customers are at risk of churning based on their health scores?\"\\n assistant: \"I will use Zara to analyze health scores and identify customers at churn risk.\"\\n <uses Agent tool to launch zara-cs>

Use this agent to simplify recently modified code without changing behavior — reduce nesting, eliminate redundancy, improve names, consolidate logic. Zen creates atomic commits matching project style and never adds features.\n\nExamples:\n\n- user: \"clean up the changes from the last commit\"\n assistant: \"I will use Zen to simplify without changing behavior.\"\n <commentary>Post-implementation cleanup — Zen reduces nesting and redundancy while preserving exact functionality.</commentary>\n\n- user: \"deslop the AI-generated code in /api\"\n assistant: \"I will activate Zen to remove unnecessary abstractions.\"\n <commentary>Deslop after AI generation — removes single-use helpers and over-engineered patterns.</commentary>

WCAG 2.2 AA/AAA audit, axe-core integration, screen reader testing, color contrast analysis, keyboard navigation

Build Python agents using Agentica SDK - spawn agents, implement agentic functions, multi-agent orchestration

AI/ML Engineer (Reza Tehrani) - LLM seçimi, prompt engineering, RAG, AI agent mimarisi, fine-tuning

API tasarim ve dokumantasyon agent'i. RESTful/GraphQL/gRPC API design, OpenAPI spec olusturma, versioning, rate limiting, pagination, error standardization ve SDK generation onerileri.

API documentation generation and management specialist

API Gateway design, configuration, and optimization specialist

API versiyonlama stratejileri, breaking change tespiti, migration guide olusturma, deprecation lifecycle yonetimi

Unit and integration test execution and validation

Software architecture specialist for system design, scalability, and technical decision-making. Use PROACTIVELY when planning new features, refactoring large systems, or making architectural decisions.

AWS services architecture (Lambda, ECS, S3, RDS, SQS, CloudFront), IaC patterns, and cost optimization specialist.

Microsoft Azure infrastructure, services, and best practices specialist

Localization & i18n - multi-language, RTL, locale-aware UX

Backend Developer (Dmitri Volkov) - API tasarımı, veritabanı, güvenlik, ölçeklenebilir sistemler

Performance benchmark agent'i. Micro benchmark olusturma, regression tespiti, baseline karsilastirma, memory/CPU/IO profiling, benchmark CI entegrasyonu ve sonuc raporlama.

AI-powered browser automation - web interaction, form filling, visual verification, deploy checks

Build and TypeScript error resolution specialist. Use PROACTIVELY when build fails or type errors occur. Fixes build/type errors only with minimal diffs, no architectural edits. Focuses on getting the build green quickly.

Business Analyst (Amara Nwosu) - Requirements, user stories, gap analizi, paydaş yönetimi

Canary & progressive delivery specialist - Blue-green, rolling updates, traffic splitting, automated rollback, deployment strategies

Scaffold & Boilerplate Intelligence Agent - Pattern scanning, consistent code generation, template engine

Chaos experiments, failure injection, blast radius control, gameday planning, and resilience validation specialist.

Clean/Hexagonal/Onion architecture specialist for maintainable systems

Code generation specialist from schemas and templates

Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.

Engineering Manager - team processes, sprint planning, organizational design

Open source community yonetim agent'i. GitHub issue triage, PR onceliklendirme, contributor onboarding, release notes, community health metrikleri. vibecosystem ve diger acik kaynak projeler icin.

Session Context Recovery & Continuity Agent (Ingrid Svensson) - Context brief, decision log, thread tracking, handoff generation, WIP management

GDPR, SOC2, HIPAA compliance, data classification, audit logging, retention policies, and privacy-by-design specialist.

Configuration validation and environment management specialist

Contract testing specialist - Pact/consumer-driven contracts, schema validation, API compatibility, provider verification

Copywriter/Content Strategist (Ellie Marchetti) - UX writing, marka sesi, landing page, mikrokopi

Post-Mortem & Pattern Propagation Agent - Bug fix sonrası aynı hatalı pattern'ı codebase'de bulur, 5 Whys root cause analysis, blameless post-mortem

Token kullanimi analizi, session maliyet tahmini, agent spawn maliyet/fayda orani, budget optimizasyonu

CQRS pattern specialist for command/query separation architectures

Data Analyst (Yuna Park) - Product analytics, A/B testing, SQL, Python, metrik tanımlama

Database ve data modelleme agent'i. ER diagram (Mermaid), normalization, denormalization, index optimization, partition stratejileri, migration planlama, schema evolution ve multi-database strategy.

ETL/ELT tasarimi, data quality, schema evolution, idempotent processing, pipeline debugging

PostgreSQL database specialist for query optimization, schema design, security, and performance. Use PROACTIVELY when writing SQL, creating migrations, designing schemas, or troubleshooting database performance. Incorporates Supabase best practices.

Domain-Driven Design specialist for complex business domain modeling

Dependency guvenlik ve kalite audit agent'i. CVE tarama, license compliance, outdated dependency tespiti, transitive dependency analizi, supply chain security, SBOM olusturma ve upgrade impact analizi.

Paket bagimlilik analizi, circular dependency tespiti, update impact, license audit, security advisory kontrolu

Dependency tracking, analysis, and security scanning specialist

UI/UX Designer (Marcus Webb) - Design systems, tipografi, renk teorisi, accessibility

DevOps/Infrastructure (Kai Nakamura) - CI/CD, Docker, K8s, monitoring, cloud

Documentation and codemap specialist. Use PROACTIVELY for updating codemaps and documentation. Runs /update-codemaps and /update-docs, generates docs/CODEMAPS/*, updates READMEs and guides.

Document Generation Specialist - PDF, DOCX, XLSX, PPTX creation with professional design standards, template engine, and format-aware orchestration

Dokumantasyon mimarisi agent'i. Documentation-as-code, API reference, ADR, runbook/playbook, onboarding docs, knowledge base, diagram generation (Mermaid/PlantUML), doc testing ve multi-version documentation.

End-to-end testing specialist using Vercel Agent Browser (preferred) with Playwright fallback. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.

Elasticsearch mappings, queries, aggregations, analyzers, index lifecycle, and cluster management specialist.

Event sourcing pattern specialist for event-driven architectures

Feature flag specialist - Gradual rollout, A/B testing, kill switches, LaunchDarkly/Unleash patterns, flag lifecycle

Frontend Developer (Aria Chen) - React, Next.js, TypeScript, accessibility, performance

Google Cloud Platform architecture, Cloud Run, BigQuery, Pub/Sub, GKE, Cloud Functions, IAM, and cost optimization specialist.

Go build, vet, and compilation error resolution specialist. Fixes build errors, go vet issues, and linter warnings with minimal changes. Use when Go builds fail.

Expert Go code reviewer specializing in idiomatic Go, concurrency patterns, error handling, and performance. Use for all Go code changes. MUST BE USED for Go projects.

Codebase'i knowledge graph olarak analiz eden agent. Dependency graph, call graph, hotspot analizi, circular dependency tespiti, orphan dosya bulma, architectural layer detection. Mermaid diagram + JSON cikti uretir. codebase-memory MCP ile entegre calisir.

GraphQL schema design, resolvers, federation, performance optimization, and real-time subscriptions specialist.

Growth & Marketing Strategist (Camille Dubois) - PLG, GTM, acquisition, retention, CRO

Protocol Buffers, gRPC services, streaming patterns, interceptors, load balancing, and error handling specialist.

Web intelligence gatherer - deep crawling, structured extraction, documentation mining, competitive analysis

Release prep, version bumps, changelog generation

Internationalization and localization specialist for multi-language applications

Production incident yonetimi, runbook olusturma, postmortem fasilitasyonu, SLA/SLO takibi, escalation zinciri

Production incident response agent'i. Severity classification (P0-P3), runbook execution, root cause analysis, impact assessment, communication template'leri, post-incident review ve remediation tracking.

Tech Debt Hunter & Codebase Hygiene Agent (Sam Calloway). Detects dead code, oversized files, TODO debt, duplicate code, and runs proactive session health scans. Use for codebase hygiene audits, pre-sprint cleanup, or when technical debt is slowing velocity.

Kafka topics, partitions, consumer groups, exactly-once semantics, Kafka Streams, and operational best practices specialist.

Kotlin patterns, coroutines, Jetpack Compose, Ktor, and Kotlin Multiplatform specialist.

Implementation and refactoring agent using TDD workflow

Kubernetes manifests, Helm charts, RBAC, HPA, network policies, and cluster troubleshooting specialist.

Integration and API review

Performance testing with k6/Artillery, load profiles, stress testing, benchmarking, and SLO validation specialist.

Log analysis, pattern detection, and debugging specialist

Multi-agent coordination for complex patterns

MCP (Model Context Protocol) server yonetim agent'i. MCP server kesfetme, kurulum, konfigurasyonu, health check ve troubleshooting. Proje tipine gore MCP stack onerisi yapar.

Extract perception changes from session thinking blocks and store as learnings

Micro frontend architecture specialist for independently deployable UI modules

Database and system migration planning specialist

Dependency Upgrade & Migration Intelligence Agent (Tomas Kowalski) - Deep dependency analysis, CVE scanning, migration planning, rollback strategies, supply chain security

Test Data & Fixture Intelligence Agent - TypeScript type'lardan realistic mock data üretir, edge case variants, fixture library, database seed data

Mobil uygulama monetizasyon uzmani (Kerem Bozkurt). Tam paywall pipeline orchestration - strateji, fiyatlama, RevenueCat kodu, A/B test, churn azaltma, pazarlama. paywall-planner + growth + ai-engineer koordinasyonu.

MongoDB schema design, aggregation pipelines, indexing strategies, sharding, and transaction patterns specialist.

|

|

|

|

|

|

|

|

|

|

|