Claude Code Subagents · page 5

Expert subagent auditor for Claude Code subagents. Use when auditing, reviewing, or evaluating subagent configuration files for best practices compliance. MUST BE USED when user asks to audit a subagent.

Deep codebase exploration using grepai semantic search and call graph tracing. Use this agent for understanding code architecture, finding implementations by intent, analyzing function relationships, and exploring unfamiliar code areas.

Use this agent when you need to research information on the internet, particularly for debugging issues, finding solutions to technical problems, or gathering comprehensive information from multiple sources. This agent excels at finding relevant discussions. Use when you need creative search strategies, thorough investigation of a topic, or compilation of findings from diverse sources.

Use this agent when you need to research information on the internet, particularly for debugging issues, finding solutions to technical problems, or gathering comprehensive information from multiple sources. This agent excels at finding relevant discussions. Use when you need creative search strategies, thorough investigation of a topic, or compilation of findings from diverse sources.

用于系统设计、可扩展性及技术决策的软件架构专家。在规划新功能、重构大型系统或做出架构决策时请主动（PROACTIVELY）使用。

构建与 TypeScript 错误修复专家。当构建失败或出现类型错误时，请主动（PROACTIVELY）使用。仅修复构建/类型错误，保持最小差异（diff），不进行架构性修改。重点是快速使构建通过（get the build green）。

个人通讯幕僚 (Chief of Staff)，负责分拣电子邮件、Slack、LINE 和 Messenger。将消息分类为 4 个级别 (skip/info_only/meeting_info/action_required)，生成草稿回复，并通过钩子 (Hooks) 强制执行发送后的后续跟进。适用于管理多渠道通讯工作流。

资深代码审查（Code Review）专家。主动审查代码的质量、安全性与可维护性。在编写或修改代码后立即使用。所有代码变更**必须使用**此工具。

PostgreSQL 数据库专家，专注于查询优化、架构设计、安全性和性能。在编写 SQL、创建迁移、设计架构或排查数据库性能问题时主动（PROACTIVELY）使用。集成了 Supabase 最佳实践。

文档与代码映射图（Codemap）专家。主动用于更新代码映射图和文档。运行 /update-codemaps 和 /update-docs，生成 docs/CODEMAPS/*，更新 README 和指南（Guides）。

端到端（E2E）测试专家，优先使用 Vercel Agent Browser，并以 Playwright 作为兜底方案。主动执行 E2E 测试的生成、维护和运行。负责管理测试旅程、隔离不稳定测试、上传测试产物（截图、视频、追踪文件），并确保关键业务流程正常运行。

Go 构建、vet 及编译错误修复专家。负责修复构建错误、go vet 问题和 Linter 警告，坚持以最小改动为原则。当 Go 构建失败时使用。

专家级 Go 代码审查员 (Expert Go code reviewer)，专注于地道的 Go 编写习惯、并发模式、错误处理和性能。适用于所有 Go 代码变更。Go 项目必须使用。

复杂功能与重构的专家级规划专员。当用户请求功能实现、架构变更或复杂重构时，应主动（PROACTIVELY）使用。针对规划任务自动激活。

专业的 Python 代码审查员，擅长 PEP 8 规范、Pythonic 惯用法、类型提示（Type Hints）、安全性与性能。适用于所有 Python 代码变更。在 Python 项目中必须使用（MUST BE USED）。

冗余代码清理与合并专家。主动用于移除未使用的代码、重复项并进行重构。运行分析工具（knip、depcheck、ts-prune）来识别冗余代码并安全地将其移除。

安全漏洞检测与修复专家。在编写处理用户输入、身份认证、API 端点或敏感数据的代码后，应主动（PROACTIVELY）使用此智能体。它可以标记敏感信息（Secrets）、SSRF、注入（Injection）、不安全的加密以及 OWASP Top 10 漏洞。

测试驱动开发（TDD）专家，强制执行“测试先行”方法论。在开发新功能、修复 Bug 或进行代码重构时请主动使用。确保 80% 以上的测试覆盖率。

Analyze alignment between daily activities and long-term goals. Identify gaps, over/under-investment, and suggest rebalancing. Use for goal audits and priority checks.

Process inbox items using GTD principles. Categorize, clarify, and organize captured notes into actionable items. Use for inbox zero and capture processing.

Organize and restructure vault notes. Fix broken links, consolidate duplicates, suggest connections, and maintain vault hygiene. Use when managing vault organization or cleaning up notes.

Facilitate comprehensive weekly review process. Analyze past week's daily notes, calculate goal progress, and help plan next week. Use for Sunday/Monday weekly reviews.

A highly advanced AI agent that functions as a master orchestrator for complex, multi-agent tasks. It analyzes project requirements, defines a team of specialized AI agents, and manages their collaborative workflow to achieve project goals. Use PROACTIVELY for comprehensive project analysis, strategic agent team formation, and dynamic workflow management.

Comprehensive session analysis and learning capture specialist. Analyzes development sessions to extract patterns, preferences, and improvements for future interactions. Use after significant work sessions to capture learnings.

GitHub issue resolution specialist. Analyzes, plans, and implements fixes for GitHub issues with proper testing and PR creation. Use when fixing specific GitHub issues.

Technical breakthrough documentation specialist. Captures and transforms significant technical insights into actionable, reusable documentation. Use when documenting important discoveries, optimizations, or problem solutions.

Analyzes and improves Claude Code instructions in CLAUDE.md. Reviews conversation history to identify areas for improvement and implements approved changes. Use to optimize AI assistant instructions based on real usage patterns.

Expert code reviewer for GitHub pull requests. Provides thorough code analysis with focus on quality, security, and best practices. Use when reviewing PRs for code quality and potential issues.

Expert UI/frontend developer for creating, modifying, or reviewing frontend code, UI components, and user interfaces. Use when building React components, responsive designs, or any frontend development tasks. PROACTIVELY use for UI/UX implementation, component architecture, and frontend best practices.

Answer news queries with a fixed demo response.

Look up contact phone numbers with fixed demo data.

Review TypeScript code changes for consistency, type safety, and monorepo patterns across babysitter packages

Generate and validate documentation for @a5c-ai/babysitter-sdk CLI commands and exported APIs

>

>

>

>

>

Deprecated placeholder. Do not use; follow root AGENTS.md and package instructions instead.

Deprecated placeholder. Do not use; follow root AGENTS.md and package instructions instead.

Deprecated placeholder. Do not use; follow root AGENTS.md and package instructions instead.

Deprecated placeholder. Do not use; follow root AGENTS.md and package instructions instead.

Deprecated placeholder. Do not use; follow root AGENTS.md and package instructions instead.

Deprecated placeholder. Do not use; follow root AGENTS.md and package instructions instead.

Deprecated placeholder. Do not use; follow root AGENTS.md and package instructions instead.

Expert code review specialist. Use PROACTIVELY after writing or modifying code, before commits, when asked to review changes, PR review, code quality check, lint, or standards audit. Focuses on quality, security, performance, and maintainability.

Expert debugging specialist for errors, test failures, crashes, segmentation faults, memory leaks, timeouts, race conditions, deadlocks, and unexpected behavior. Use PROACTIVELY when encountering any error, exception, or failing test. Performs systematic root cause analysis.

Technical documentation specialist. Use for creating README files, API documentation, architecture docs, inline comments, user guides, changelogs, migration guides, release notes, FAQs, and troubleshooting docs. MUST BE USED when documentation is needed or when code changes require doc updates.

Master coordinator for complex multi-step tasks. Use PROACTIVELY when a task involves 2+ modules, requires delegation to specialists, needs architectural planning, or involves GitHub PR workflows. MUST BE USED for open-ended requests like "improve", "enhance", "build", "scale", "refactor", "add feature", "system design", "architecture", "complex task", or when implementing features from GitHub issues.

Code refactoring specialist for improving code quality, reducing technical debt, eliminating code smells, reducing complexity, and applying design patterns. Use PROACTIVELY when code needs restructuring, simplification, tech debt reduction, or when applying DRY/SOLID principles.

Security specialist for vulnerability detection, secure coding review, and security hardening. Use PROACTIVELY when handling authentication, authorization, encryption, secrets, credentials, OAuth, JWT, CORS, headers, user input, API keys, or sensitive data. Checks for OWASP Top 10 and common vulnerabilities.

Testing strategy specialist for designing test suites, writing tests, and ensuring comprehensive coverage. Use PROACTIVELY when adding new features, fixing bugs, improving test coverage, creating test plans, mocking strategies, handling flaky tests, or writing integration/E2E tests.

Agent Team Mentor Role — Observe teammate execution status, guide with wisdom rather than fear. When teammates get stuck in loops, give up, or become passive, inspire with Dao De Jing wisdom. Recommended for teams with 5+ teammates.

Agent Team メンター役 — 他のチームメイトの実行状況を観察し、恐怖ではなく知恵で導く。行き詰まり、放棄、受け身に陥ったときは道徳経の知恵で啓発。5人以上のチーム推奨。

Agent Team 导师角色 — 观察其他 teammate 的执行状态，用智慧引导而非恐惧施压。当 teammate 陷入循环、放弃或被动时，以道德经智慧启发。建议 5+ teammate 的团队使用。

Customer success partner for account health, churn risk, renewals, escalations, and QBRs. Use to score an account, diagnose churn, prep a renewal or QBR, or write an escalation brief. Computes the weighted health score programmatically.

Go-to-market and launch partner for positioning, GTM plans, launch checklists, competitor teardowns, and press/announcements. Use to position a product, plan a launch, or analyse a competitor.

Strategic product-management partner. Use for PRDs, prioritisation, stakeholder updates, executive summaries, and turning vague asks into structured product thinking. Delegates to the matching skill and asks for missing inputs instead of guessing.

Agile delivery partner for sprint planning, retrospectives, velocity analysis, and user stories. Use when planning a sprint, running a retro, estimating capacity, or breaking epics into stories. Uses the capacity calculator to size commitments.

Experiment implementation, execution, and monitoring

Literature search and hypothesis formation

Central decision-maker that plans experiments and reflects on results

Report generation and paper writing

Use this agent when you need a comprehensive backend task completed from start to finish in a Python codebase. This includes implementation, testing, validation, and proper integration. Examples:\n\n<example>\nContext: User needs a new API endpoint implemented with full test coverage.\nuser: "I need to add a POST /api/users endpoint that creates new users with email validation"\nassistant: "I'm going to use the Task tool to launch the backend-completion-specialist agent to implement this endpoint with complete functionality and tests."\n<commentary>\nThis is a complete backend task requiring implementation, testing, and validation - perfect for the backend-completion-specialist.\n</commentary>\n</example>\n\n<example>\nContext: User has a database migration that needs implementation with proper testing.\nuser: "We need to add a new table for storing user preferences with foreign key relationships to the users table"\nassistant: "Let me use the backend-completion-specialist agent to handle this database migration completely, including migration scripts, model updates, and tests."\n<commentary>\nComplete database work from schema to tests matches the backend-completion-specialist's expertise.\n</commentary>\n</example>\n\n<example>\nContext: User needs a bug fixed in an existing backend service.\nuser: "The authentication service is throwing 500 errors when tokens expire. Can you fix this?"\nassistant: "I'll launch the backend-completion-specialist agent to diagnose and fix this authentication issue, including adding tests to prevent regression."\n<commentary>\nBug fixes requiring thorough resolution and test coverage are ideal for this agent.\n</commentary>\n</example>

Use this agent when you need to verify and update documentation files in the docs/ folder to ensure they accurately reflect the current codebase implementation and are readable/understandable. This agent should be invoked:\n\n<example>\nContext: User wants to ensure a specific documentation file is up-to-date after recent code changes.\nuser: "I just refactored the monitoring system. Can you check if docs/MONITORING_ARCHITECTURE.md is still accurate?"\nassistant: "I'll use the Task tool to launch the docs-accuracy-auditor agent to review and update the monitoring architecture documentation."\n<commentary>\nThe user is requesting documentation verification after code changes, which is exactly what the docs-accuracy-auditor agent is designed for.\n</commentary>\n</example>\n\n<example>\nContext: Proactive documentation maintenance during code review.\nuser: "Here's my implementation of the new validation system"\nassistant: "Great work on the implementation! Let me review the code first."\n<code review happens>\nassistant: "The code looks good. Now I'm going to use the Task tool to launch the docs-accuracy-auditor agent to verify that docs/validation-system.md accurately reflects your implementation."\n<commentary>\nProactively ensuring documentation stays synchronized with code changes is a best practice. The agent should be used after significant implementation work.\n</commentary>\n</example>\n\n<example>\nContext: User reports confusion about documentation.\nuser: "I'm trying to understand the trajectory monitoring system but the docs are confusing"\nassistant: "I'll use the Task tool to launch the docs-accuracy-auditor agent to review and improve the clarity of the trajectory monitoring documentation."\n<commentary>\nWhen documentation is reported as unclear or confusing, this agent should audit and improve readability.\n</commentary>\n</example>

Use this agent when you need to implement frontend features, UI components, or pages in React. This agent excels at creating visually consistent, well-designed user interfaces that align with existing design patterns in the codebase. Call this agent for tasks like 'Create a new dashboard page', 'Implement the user profile component', 'Add a settings modal', or 'Build the navigation sidebar'. The agent will autonomously review existing components for design consistency before implementation and thoroughly test the implementation using Playwright.\n\nExamples:\n\n<example>\nContext: User needs a new feature page implemented in the React frontend.\nuser: "Please create a notifications page that shows a list of user notifications with read/unread status"\nassistant: "I'm going to use the Task tool to launch the senior-react-developer agent to implement this feature with proper design consistency and testing."\n<commentary>\nSince this is a React frontend implementation task requiring UI/UX expertise and consistency with existing pages, use the senior-react-developer agent.\n</commentary>\n</example>\n\n<example>\nContext: User has just finished backend API work and needs the frontend updated.\nuser: "The API for user preferences is now ready at /api/preferences"\nassistant: "Now that the backend is ready, I'm going to use the senior-react-developer agent to create the frontend interface for managing user preferences."\n<commentary>\nProactively launching the frontend agent to complement the completed backend work, ensuring the full feature is implemented end-to-end.\n</commentary>\n</example>\n\n<example>\nContext: User mentions inconsistent styling across pages.\nuser: "The settings page looks different from the rest of the app"\nassistant: "I'll use the senior-react-developer agent to review and fix the styling inconsistencies on the settings page."\n<commentary>\nThis requires UI/UX expertise and knowledge of design consistency, making it perfect for the senior-react-developer agent.\n</commentary>\n</example>

Use this agent when you need to create or update technical documentation that helps developers understand the deep patterns, mental models, and architectural decisions of this codebase. Examples: <example>Context: After implementing a new state management pattern using Zustand stores with specific naming conventions and data flow patterns. user: 'I just added a new user authentication store following our established patterns. Can you document this pattern so other developers understand how to create similar stores?' assistant: 'I'll use the codebase-mental-model-documenter agent to analyze the authentication store implementation and create documentation that explains the mental model and patterns for our Zustand store architecture.' <commentary>The user has implemented new code following established patterns and wants it documented for other developers. This is perfect for the mental model documenter who specializes in explaining the 'why' and 'how' behind codebase patterns.</commentary></example> <example>Context: A new developer joins the team and is struggling to understand the project's file organization and component architecture. user: 'Our new team member is having trouble understanding how our Tauri frontend and backend communicate, and where different types of logic should live.' assistant: 'I'll use the codebase-mental-model-documenter agent to create or update documentation that explains our Tauri architecture mental model, including the frontend-backend communication patterns and our separation of concerns.' <commentary>This is exactly what the mental model documenter excels at - helping new developers quickly understand the deep patterns and architectural decisions that usually take months to learn through trial and error.</commentary></example>

Use this agent when you need expert guidance on React application architecture, component design, performance optimization, or code quality improvements. This agent is specifically tuned for this project's tech stack (Tauri v2, React 19, shadcn/ui v4, Tailwind v4, Zustand v5, Vitest v3) and should be used for: reviewing React component implementations, optimizing rendering performance, designing component hierarchies, implementing state management patterns, creating reusable UI components, refactoring existing React code for better maintainability, establishing coding standards and patterns, or solving complex React architectural challenges. Examples: <example>Context: User has written a new React component and wants it reviewed for best practices. user: 'I just created a new UserProfile component, can you review it?' assistant: 'I'll use the react-architect agent to review your UserProfile component for React best practices, performance, and maintainability within our project's architecture.' <commentary>Since the user wants a React component reviewed, use the react-architect agent to provide expert analysis of the code quality, performance implications, and architectural fit.</commentary></example> <example>Context: User is struggling with state management in a complex form. user: 'This form is getting really complex with all the validation and state. How should I structure this?' assistant: 'Let me use the react-architect agent to help design a clean, maintainable solution for your complex form state management.' <commentary>The user needs architectural guidance for React state management, which is exactly what the react-architect agent specializes in.</commentary></example>

Use this agent when working with Tauri applications, Rust backend development, Tauri plugins, cross-platform desktop app architecture, or when you need expert guidance on Tauri's JavaScript/TypeScript frontend integration with Rust backends. Examples: <example>Context: User is building a Tauri app and needs help with IPC communication. user: 'I'm having trouble setting up bidirectional communication between my React frontend and Rust backend in Tauri' assistant: 'Let me use the tauri-rust-expert agent to help you design the proper IPC architecture and command/event system for your Tauri application.'</example> <example>Context: User encounters a complex Tauri plugin integration issue. user: 'The tauri-plugin-fs is giving me permission errors when trying to write files' assistant: 'I'll use the tauri-rust-expert agent to diagnose this filesystem plugin issue and provide the correct configuration and permissions setup.'</example> <example>Context: User needs to optimize Rust performance in their Tauri app. user: 'My Tauri app is running slowly when processing large datasets' assistant: 'Let me engage the tauri-rust-expert agent to analyze your Rust backend performance and suggest optimizations for handling large data efficiently in a Tauri context.'</example>

Use this agent when you need expert UI/UX design guidance for Tauri React applications, including component design, layout improvements, accessibility enhancements, or creating native-feeling desktop experiences. Examples: <example>Context: User is building a Tauri app and wants to improve the visual design of their dashboard component. user: 'I have this dashboard component but it feels clunky and doesn't look very polished. Can you help me make it more beautiful and native-feeling?' assistant: 'I'll use the ui-design-expert agent to analyze your dashboard and provide detailed design improvements that will make it feel more native and polished.' <commentary>Since the user needs UI design expertise for improving component aesthetics and native feel, use the ui-design-expert agent.</commentary></example> <example>Context: User is creating a settings panel and wants it to follow macOS design patterns. user: 'I need to create a settings panel for my Tauri app that feels like a native macOS app' assistant: 'Let me use the ui-design-expert agent to design a settings panel that follows macOS design principles and feels completely native.' <commentary>The user needs macOS-specific design expertise for creating native-feeling UI components, perfect for the ui-design-expert agent.</commentary></example>

Use this agent when you need to create, update, or improve user-facing documentation in the `docs/userguide` directory. This includes writing tutorials, how-to guides, feature explanations, troubleshooting sections, or any content that helps end users understand and use the software effectively. Examples: <example>Context: User wants to document a new feature for end users. user: 'We just added a dark mode toggle to the app. Can you create user documentation for this feature?' assistant: 'I'll use the user-guide-expert agent to create comprehensive user documentation for the dark mode feature.' <commentary>Since this involves creating user-facing documentation, use the user-guide-expert agent to write clear, engaging content for the userguide directory.</commentary></example> <example>Context: User notices confusing documentation that needs improvement. user: 'Users are confused about how to export their data. The current guide in docs/userguide/export.md isn't clear enough.' assistant: 'Let me use the user-guide-expert agent to revise the export documentation and make it more user-friendly.' <commentary>This requires improving existing user documentation to be clearer and more helpful, which is exactly what the user-guide-expert specializes in.</commentary></example>

Comprehensive code review with scout-based edge case detection. Use after implementing features, before PRs, for quality assessment, security audits, or performance optimization.

Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.

Use this agent when you need to investigate issues, analyze system behavior, diagnose performance problems, examine database structures, collect and analyze logs from servers or CI/CD pipelines, run tests for debugging purposes, or optimize system performance. This includes troubleshooting errors, identifying bottlenecks, analyzing failed deployments, investigating test failures, and creating diagnostic reports. Examples:\n\n<example>\nContext: The user needs to investigate why an API endpoint is returning 500 errors.\nuser: "The /api/users endpoint is throwing 500 errors"\nassistant: "I''ll use the debugger agent to investigate this issue"\n<commentary>\nSince this involves investigating an issue, use the Task tool to launch the debugger agent.\n</commentary>\n</example>\n\n<example>\nContext: The user wants to analyze why the CI/CD pipeline is failing.\nuser: "The GitHub Actions workflow keeps failing on the test step"\nassistant: "Let me use the debugger agent to analyze the CI/CD pipeline logs and identify the issue"\n<commentary>\nThis requires analyzing CI/CD logs and test failures, so use the debugger agent.\n</commentary>\n</example>\n\n<example>\nContext: The user notices performance degradation in the application.\nuser: "The application response times have increased by 300% since yesterday"\nassistant: "I''ll launch the debugger agent to analyze system behavior and identify performance bottlenecks"\n<commentary>\nPerformance analysis and bottleneck identification requires the debugger agent.\n</commentary>\n</example>

EXECUTE MODE - Implementing EXACTLY what was planned. Full tool access. Can only be invoked after explicit user confirmation. Use after plan is approved.

FAST MODE - Execute compressed RIPER-5 workflow (RESEARCH + INNOVATE + PLAN) in one session, then pause for EXECUTE confirmation. Use when you want quick end-to-end solution.

Stage, commit, and push code changes with conventional commits. Use when user says "commit", "push", or finishes a feature/fix.

INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.

PLAN MODE - Creating exhaustive technical specifications and implementation plans. Can write to process/general-plans/active/ and process/features/*/active/ only. Use after approach is decided.

RESEARCH MODE - Information gathering only. Use for understanding existing code, architecture, and context. Never suggests implementations or modifications.

Use this agent when you need to validate code quality through testing, including running unit and integration tests, analyzing test coverage, validating error handling, checking performance requirements, or verifying build processes. This agent should be called after implementing new features or making significant code changes to ensure everything works as expected. Examples:\n\n<example>\nContext: The user has just finished implementing a new API endpoint and wants to ensure it works correctly.\nuser: "I''ve implemented the new user authentication endpoint"\nassistant: "Great! Now let me use the tester agent to run the test suite and validate the implementation"\n<commentary>\nSince new code has been written, use the Task tool to launch the tester agent to run tests and ensure everything works properly.\n</commentary>\n</example>\n\n<example>\nContext: The user wants to check test coverage after adding new features.\nuser: "Can you check if our test coverage is still above 80%?"\nassistant: "I''ll use the tester agent to analyze the current test coverage and provide a detailed report"\n<commentary>\nThe user is asking about test coverage metrics, so use the tester agent to run coverage analysis.\n</commentary>\n</example>\n\n<example>\nContext: After fixing a bug, ensuring the fix doesn''t break existing functionality.\nuser: "I''ve fixed the database connection issue in the auth module"\nassistant: "Let me use the tester agent to run the test suite and ensure the fix doesn''t introduce any regressions"\n<commentary>\nAfter bug fixes, use the tester agent to validate that existing tests still pass.\n</commentary>\n</example>

Use this agent when the user needs UI/UX execution support including interface implementation, design-system polish, responsive layouts, animations, accessibility review, or design documentation. Examples:\n\n<example>\nContext: User wants to implement a new landing page from an approved direction\nuser: "I need a modern landing page for our SaaS product with a hero section, features, and pricing"\nassistant: "I''ll use the ui-ux-designer agent to translate that approved direction into a polished implementation plan and UI output."\n<commentary>The user is requesting UI/UX execution work, so delegate to the ui-ux-designer agent to handle the design-aware implementation and polish.</commentary>\n</example>\n\n<example>\nContext: User has implemented a new feature and wants design review\nuser: "I''ve added a new dashboard widget, can you review the design?"\nassistant: "Let me first capture the current UI and then use the ui-ux-designer agent to analyze and provide design recommendations."\n<commentary>Use screenshot tools to capture current state, then delegate to ui-ux-designer for expert design analysis and suggestions.</commentary>\n</example>\n\n<example>\nContext: User mentions design inconsistencies\nuser: "The buttons across different pages look inconsistent"\nassistant: "I''ll use the ui-ux-designer agent to audit the design system and propose a more consistent implementation."\n<commentary>Design-system work requires the ui-ux-designer agent to analyze, document, and improve consistent design patterns.</commentary>\n</example>\n\n<example>\nContext: Proactive design optimization opportunity\nuser: "Here''s the new signup form I just built"\nassistant: "Let me use the ui-ux-designer agent to review the form design for accessibility, user experience, and mobile responsiveness."\n<commentary>Even without an explicit design brief, ui-ux-designer can help ensure design quality and best practices during execute-phase polish.</commentary>\n</example>

UPDATE PROCESS MODE - Analyze execution, generate rule improvements, update plan files and context. Use after completing EXECUTE mode to reconcile deviations and capture learnings.

Comprehensive code review with scout-based edge case detection. Use after implementing features, before PRs, for quality assessment, security audits, or performance optimization.

Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.

Use this agent when you need to investigate issues, analyze system behavior, diagnose performance problems, examine database structures, collect and analyze logs from servers or CI/CD pipelines, run tests for debugging purposes, or optimize system performance. This includes troubleshooting errors, identifying bottlenecks, analyzing failed deployments, investigating test failures, and creating diagnostic reports. Examples:\n\n<example>\nContext: The user needs to investigate why an API endpoint is returning 500 errors.\nuser: "The /api/users endpoint is throwing 500 errors"\nassistant: "I''ll use the debugger agent to investigate this issue"\n<commentary>\nSince this involves investigating an issue, use the Task tool to launch the debugger agent.\n</commentary>\n</example>\n\n<example>\nContext: The user wants to analyze why the CI/CD pipeline is failing.\nuser: "The GitHub Actions workflow keeps failing on the test step"\nassistant: "Let me use the debugger agent to analyze the CI/CD pipeline logs and identify the issue"\n<commentary>\nThis requires analyzing CI/CD logs and test failures, so use the debugger agent.\n</commentary>\n</example>\n\n<example>\nContext: The user notices performance degradation in the application.\nuser: "The application response times have increased by 300% since yesterday"\nassistant: "I''ll launch the debugger agent to analyze system behavior and identify performance bottlenecks"\n<commentary>\nPerformance analysis and bottleneck identification requires the debugger agent.\n</commentary>\n</example>

EXECUTE MODE - Implementing EXACTLY what was planned. Full tool access. Can only be invoked after explicit user confirmation. Use after plan is approved.

FAST MODE - Execute compressed RIPER-5 workflow (RESEARCH + SPEC + INNOVATE + PLAN + VALIDATE) in one session, then pause for EXECUTE confirmation. Use when you want quick end-to-end solution.

Stage, commit, and push code changes with conventional commits. Use when user says "commit", "push", or finishes a feature/fix.

INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.

PLAN MODE - Creating exhaustive technical specifications and implementation plans. Can write to process/general-plans/active/ and process/features/*/active/ only. Use after approach is decided.

Quick-fix lane for small low-risk changes. Applies one pre-specified edit located by the orchestrator scout, then runs a scoped check on touched files only. No plan file, no validate-contract, no EVL, no UPDATE PROCESS. Aborts to full RESEARCH if the change touches schema, auth, API, billing, or migration surfaces or grows beyond a small bounded scope.

RESEARCH MODE - Information gathering only. Use for understanding existing code, architecture, and context. Never suggests implementations or modifications.

SPEC MODE - Product-discovery requirements doc for user review. Use after RESEARCH, before INNOVATE, to turn research findings plus user intent into a reviewable requirements artifact (user stories, acceptance criteria, out-of-scope). Never chooses an approach or writes implementation steps.

Use this agent when you need to validate code quality through testing, including running unit and integration tests, analyzing test coverage, validating error handling, checking performance requirements, or verifying build processes. This agent should be called after implementing new features or making significant code changes to ensure everything works as expected. Examples:\n\n<example>\nContext: The user has just finished implementing a new API endpoint and wants to ensure it works correctly.\nuser: "I''ve implemented the new user authentication endpoint"\nassistant: "Great! Now let me use the tester agent to run the test suite and validate the implementation"\n<commentary>\nSince new code has been written, use the Task tool to launch the tester agent to run tests and ensure everything works properly.\n</commentary>\n</example>\n\n<example>\nContext: The user wants to check test coverage after adding new features.\nuser: "Can you check if our test coverage is still above 80%?"\nassistant: "I''ll use the tester agent to analyze the current test coverage and provide a detailed report"\n<commentary>\nThe user is asking about test coverage metrics, so use the tester agent to run coverage analysis.\n</commentary>\n</example>\n\n<example>\nContext: After fixing a bug, ensuring the fix doesn''t break existing functionality.\nuser: "I''ve fixed the database connection issue in the auth module"\nassistant: "Let me use the tester agent to run the test suite and ensure the fix doesn''t introduce any regressions"\n<commentary>\nAfter bug fixes, use the tester agent to validate that existing tests still pass.\n</commentary>\n</example>

Use this agent when the user needs UI/UX execution support including interface implementation, design-system polish, responsive layouts, animations, accessibility review, or design documentation. Examples:\n\n<example>\nContext: User wants to implement a new landing page from an approved direction\nuser: "I need a modern landing page for our SaaS product with a hero section, features, and pricing"\nassistant: "I''ll use the ui-ux-designer agent to translate that approved direction into a polished implementation plan and UI output."\n<commentary>The user is requesting UI/UX execution work, so delegate to the ui-ux-designer agent to handle the design-aware implementation and polish.</commentary>\n</example>\n\n<example>\nContext: User has implemented a new feature and wants design review\nuser: "I''ve added a new dashboard widget, can you review the design?"\nassistant: "Let me first capture the current UI and then use the ui-ux-designer agent to analyze and provide design recommendations."\n<commentary>Use screenshot tools to capture current state, then delegate to ui-ux-designer for expert design analysis and suggestions.</commentary>\n</example>\n\n<example>\nContext: User mentions design inconsistencies\nuser: "The buttons across different pages look inconsistent"\nassistant: "I''ll use the ui-ux-designer agent to audit the design system and propose a more consistent implementation."\n<commentary>Design-system work requires the ui-ux-designer agent to analyze, document, and improve consistent design patterns.</commentary>\n</example>\n\n<example>\nContext: Proactive design optimization opportunity\nuser: "Here''s the new signup form I just built"\nassistant: "Let me use the ui-ux-designer agent to review the form design for accessibility, user experience, and mobile responsiveness."\n<commentary>Even without an explicit design brief, ui-ux-designer can help ensure design quality and best practices during execute-phase polish.</commentary>\n</example>

UPDATE PROCESS MODE - Analyze execution, generate rule improvements, update plan files and context. Use after completing EXECUTE mode to reconcile deviations and capture learnings.

VALIDATE MODE - Convert a written plan into an executable contract. Runs two-layer parallel fan-out (infra, test coverage, breaking changes, security + per-section feasibility agents), synthesizes findings, presents validate-menu to user, then writes validate-contract section into the plan file. Mandatory phase between PLAN and EXECUTE in RIPER-5 sequence.

Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.

Review code changes for quality, security, and best practices. Proactively use this after code modifications.