Subagents de Claude Code · página 11

Strategic planner that validates and shapes ideas into actionable specs before implementation. Use when a brainstorm or feature idea needs to be pressure-tested, scoped, and turned into a clear specification with success criteria and UATs. Sits between brainstorming and technical planning.

Senior backend TypeScript architect specializing in Bun/Node.js runtime, API design, database optimization, and scalable server architecture.

Expert at exploring and understanding legacy and unfamiliar codebases. Maps dependencies, identifies patterns, and creates documentation for complex systems.

Kubernetes architect specializing in cluster design, manifests, Helm charts, GitOps workflows, security policies, and production operations.

Systematic open source contributor that analyzes projects, finds suitable issues, implements fixes, and creates high-quality PRs with high acceptance probability.

Application security expert specializing in SAST, vulnerability assessment, OWASP Top 10, compliance auditing, and security architecture review.

Fullstack code reviewer with 15+ years experience analyzing code for security vulnerabilities, performance bottlenecks, architectural decisions, and best practices.

Senior technical lead who analyzes complex projects and coordinates multi-step development tasks. Delegates to specialized agents and ensures quality delivery.

Use proactively before opening a PR that adds or changes BehaviorTree.CPP nodes or BehaviorTree.ROS2 wrappers (RosActionNode/RosServiceNode/RosTopicPub/SubNode, TreeExecutionServer). Reviews a diff against BT.CPP v4 conventions — node base-class choice, non-blocking ticks, ports/blackboard typing, factory/plugin registration, XML v4, and the ROS 2 wrapper contract. Returns a punch list with file:line anchors, not a rewrite.

Use when a design decision touches Clean Architecture boundaries in a ROS 2 project — which layer a new behaviour belongs to, whether a port belongs in domain or application, whether a new node should be lifecycle-managed, whether to compose nodes or split packages. Returns an architectural recommendation with trade-offs, not implementation.

Use when a design decision touches the gz-sim ECS — where new state should live, which system phase should write it, how to avoid coupling, whether to add a component vs. a member variable, whether a new system should be split or merged with an existing one. Returns an architectural recommendation with trade-offs, not implementation.

Use proactively before opening any gz-sim PR. Reviews a diff against the project's C++17 style, ECS conventions, plugin registration patterns, CMake structure, test placement, Migration.md / Changelog.md expectations, and pre-commit configuration. Returns a punch list, not a rewrite.

Use proactively before opening a PR that adds or changes a ros2_control controller, broadcaster, or hardware component (incl. URDF <ros2_control> bringup). Reviews a diff against ros2_controllers / ros2_control_demos conventions — controller & hardware lifecycle, command/state interface configuration, real-time safety of update()/read()/write(), generate_parameter_library usage, pluginlib registration, chainable-controller correctness, URDF wiring, and tests. Returns a punch list with file:line anchors, not a rewrite.

Use proactively before opening any ROS 2 / Nav 2 PR. Reviews a diff against this template's Clean Architecture, ROS 2 communication, lifecycle, testing, and Nav 2 plugin conventions. Returns a punch list with file:line anchors, not a rewrite.

Use proactively before opening a PR that touches a VDA 5050 connector / fleet bridge. Reviews a diff against VDA 5050 v3.0.0 protocol compliance (topics, QoS, header rules, base/horizon, action state machine, schema validation) and the template's Clean Architecture for the MQTT↔Nav 2 bridge. Returns a punch list with file:line anchors, not a rewrite.

>

>

>

Cross-artifact consistency and coverage analysis specialist with Anthropic think protocol. Validates alignment between specifications, plans, tasks, and implementation. Use before implementation to catch conflicts early.

Production deployment specialist with Anthropic safety patterns managing CI/CD pipelines, infrastructure provisioning, and safe rollout strategies. Defaults to canary deployments with auto-rollback. Use for production deployments and release management.

Root cause analysis and debugging specialist with Anthropic think protocol and 3-retry limit. Focuses on systematic problem diagnosis, error tracing, and fix validation. Use for complex bugs and system failures.

Observability and monitoring specialist with Anthropic's three pillars pattern (Metrics, Logs, Traces). Sets up comprehensive monitoring, SLI/SLO tracking, and incident detection. Use for system observability and proactive alerting.

Performance optimization and auto-scaling specialist with Anthropic profiling patterns. Manages horizontal/vertical scaling, load balancing, caching strategies, and continuous performance tuning. Use for scaling challenges and performance work.

Master orchestrator for complex, multi-faceted software projects. Coordinates specialist agents (researchers, planners, implementers) to deliver cohesive solutions. Use for projects requiring 3+ capabilities or cross-domain work (frontend + backend + devops).

Precision execution specialist that implements code following Implementation Plans and ResearchPacks. Makes surgical, minimal edits with self-correction capability (3 retries). Always runs tests and validates against plan. Requires both ResearchPack and Implementation Plan as input.

High-speed documentation specialist. Fetches version-accurate docs from official sources to prevent coding from stale memory. Use before implementing any feature with external libraries or APIs. Delivers ResearchPack in < 2 minutes.

Strategic architect that transforms ResearchPacks into surgical, reversible implementation plans. Analyzes codebase structure, identifies minimal changes, and creates step-by-step blueprints with rollback procedures. Requires ResearchPack as input.

AI/ML工程师，负责模型集成、提示工程、RAG管道、Agent工作流设计和AI功能开发，交付高质量的智能化功能模块

Python/FastAPI后端架构师，负责API设计、数据库建模、系统架构搭建、性能优化、可扩展性设计，交付稳健可维护的后端服务

代码质量把关专家，负责PR Review、代码规范审查、安全漏洞检测、性能隐患识别，采用教育式而非看门式的Review哲学，帮助团队持续提升代码质量

数据库优化专家，负责查询性能调优、索引策略设计、数据建模和迁移脚本编写，确保数据层高效稳定运行

DevOps自动化工程师，负责CI/CD流水线设计、Docker容器化部署、基础设施即代码(IaC)、监控告警配置，确保项目从构建到部署的全链路自动化

专注React/Vue/现代Web前端开发的工程师，负责组件开发、页面构建、响应式布局、Core Web Vitals性能优化、可访问性合规，交付高质量用户界面代码

Git工作流专家，负责分支策略设计、合并冲突解决、代码历史维护、CI集成和团队Git规范制定

MCP Server开发专家，负责设计和实现Model Context Protocol工具服务器，精通FastMCP/Python SDK、工具命名最佳实践、Zod验证和JSON/Markdown双输出格式

移动端开发专家，负责React Native/Flutter跨平台应用开发、原生性能优化、设备适配和应用商店发布流程

快速原型开发专家，负责MVP验证、概念验证实现、技术可行性评估和最小可行方案交付

安全工程师，负责漏洞检测、安全审计、OWASP Top 10防护、依赖扫描和安全最佳实践执行，守护代码库和基础设施的安全底线

系统架构设计师，负责整体架构规划、ADR决策记录、技术选型与trade-off分析、模块职责划分、系统边界定义，确保架构支撑业务增长且保持技术债务可控

站点可靠性工程师，负责系统可用性保障、事故响应、容量规划、SLO/SLI定义和自动化运维

负责任务分解、进度追踪、范围控制的项目经理，将大需求拆解为可执行的开发任务并严控项目边界

负责架构决策、任务拆分分配、代码审查、团队协调的技术负责人，是团队技术方向的总舵手

工作流架构师，负责复杂业务流程设计、状态机建模、事件驱动架构和自动化编排方案

专职会议主持人，负责组织高效的多Agent讨论，确保每次会议产出清晰结论和行动项

技术文档工程师，负责API文档、架构文档、用户指南编写和文档一致性维护

API测试专家，负责接口契约验证、边界条件测试、认证流程测试和API性能基准建立

Bug修复与根因分析专家，负责问题定位、二分法缩小范围、最小化修复、回归测试编写，确保每个修复都精准且不引入新问题

性能基准测试专家，负责性能瓶颈定位、负载测试、内存/CPU分析和性能回归检测

QA质量验证工程师，负责基于证据的质量验证、测试策略制定、测试用例编写和缺陷报告，默认假设系统存在3-5个未发现的问题并主动寻找

WOZCODE free-plan fallback agent — active when the monthly free-plan cap is exhausted. Claude Code's built-in Read, Edit, Write, Grep, Glob, and NotebookEdit are available; WOZCODE MCP tools are disallowed until the cap resets or the user upgrades.

WozCode enhanced coding agent with smart search, batch editing, and SQL introspection. Use as the default main thread agent.

Fast read-only agent for file searches, symbol lookups, and codebase questions like "where is X defined?", "where is X called?", or "how does X flow through the system?". Prefer over shell-based exploration when answering would take 3+ Search/Sql calls. Cheaper model (haiku) so delegation pays for itself on any real scan.

Idun coding-guideline review against the active rule set.

Agora member. Use standalone for task separation & community-feeling analysis, or via /hearth for relationship deliberation.

Agora member. Use standalone for meaning-finding & attitudinal freedom analysis, or via /clinic or /oracle for deliberation.

Agora member. Use standalone for love-as-practice & productive orientation analysis, or via /hearth for relationship deliberation.

Agora member. Use standalone for shadow integration & individuation analysis, or via /oracle or /clinic for deliberation.

Agora member. Use standalone for categorical imperative & universalizability analysis, or via /hearth or /forge for deliberation.

Agora member. Use standalone for creative destruction & value revaluation, or via /forge, /oracle, or /atelier for deliberation.

Agora member. Use standalone for simplicity audit & complexity reduction, or via /forge or /atelier for deliberation.

Agora member. Use standalone for falsification & red-team analysis, or via /forge for engineering deliberation.

Agora member. Use standalone for radical freedom & responsibility analysis, or via /oracle for life crossroads deliberation.

Agora member. Use standalone for creative destruction & entrepreneurship analysis, or via /bazaar for business & strategy deliberation.

Agora member. Use standalone for behavioral design & environmental analysis, or via /clinic for psychological resilience deliberation.

Agora member. Use standalone for language decomposition & F/D/Q analysis, or via /forge or /atelier for deliberation.

Agora member. Use standalone for effortless action & perspective liberation analysis, or via /hearth or /clinic for deliberation.

Council member. Use standalone for formal systems & computational analysis, or via /council for multi-perspective deliberation.

Council member. Use standalone for categorization & structural analysis, or via /council for multi-perspective deliberation.

Council member. Use standalone for resilience & moral clarity analysis, or via /council for multi-perspective deliberation, or via /oracle, /hearth, /clinic for life & relationship deliberation.

Council member. Use standalone for first-principles debugging & explanation testing, or via /council for multi-perspective deliberation.

Council member. Use standalone for cognitive bias detection & decision science analysis, or via /council for multi-perspective deliberation.

Council member. Use standalone for neural network intuition & empirical ML analysis, or via /council for multi-perspective deliberation.

Council member. Use standalone for emergence & non-intervention analysis, or via /council for multi-perspective deliberation.

Council member. Use standalone for power dynamics & incentive analysis, or via /council for multi-perspective deliberation.

Council member. Use standalone for systems thinking & feedback loop analysis, or via /council for multi-perspective deliberation.

Council member. Use standalone for multi-model reasoning & economic analysis, or via /council for multi-perspective deliberation.

Council member. Use standalone for strategic timing & situational awareness analysis, or via /council for multi-perspective deliberation.

Council member. Use standalone for user-centered design & simplicity analysis, or via /council for multi-perspective deliberation.

Council member. Use standalone for assumption destruction & dialectical analysis, or via /council for multi-perspective deliberation.

Council member. Use standalone for adversarial strategy & competitive analysis, or via /council for multi-perspective deliberation.

Council member. Use standalone for scaling frontier & AI safety analysis, or via /council for multi-perspective deliberation.

Council member. Use standalone for antifragility & tail risk analysis, or via /council for multi-perspective deliberation.

Council member. Use standalone for pragmatic engineering & shipping analysis, or via /council for multi-perspective deliberation.

Council member. Use standalone for perspective dissolution & reframing analysis, or via /council for multi-perspective deliberation.

Orchestrates CLAUDE.md updates for changed files

|

API endpoint testing. Discovery, validation, auth flows, error handling.

Supervisor agent. Coordinates auditors, validates fixes, iterates until production-ready.

Navigates running web applications via Chrome integration to find UI bugs, console errors, and UX issues. Uses /chrome tools to interact with localhost or deployed apps.

Runtime bug scanner. Finds error handling gaps, race conditions, memory leaks, null refs.

Code quality auditor. Reviews patterns, maintainability, complexity, consistency.

Implements fixes from FIXES.md. Production-quality code following project patterns.

Real-time console monitoring during browser sessions. Watches for errors, warnings, and logs as you test.

Database auditor. Schema design, N+1 queries, indexes, connection pooling.

Dependency auditor. Outdated packages, vulnerabilities, licenses, unused deps.

Pre-deployment validation. Build, env vars, dependencies, migrations, health checks.

Documentation coverage analyzer. Finds missing docs, outdated comments, API gaps.

Environment configuration validator. Compares .env.example vs .env, checks for secrets.

Creates prioritized fix plans from audit findings. Generates FIXES.md with deduplication.

Coordinates browser-qa-agent with code-fixer for complete test-fix-verify cycles. The Replit-style workflow.