Accessibility specialist. Delegates here for WCAG audits, ARIA review, keyboard navigation, screen reader compatibility, and inclusive design fixes. Use when auditing UI for accessibility, fixing a11y findings, or designing accessible components. For general UI implementation delegate to frontend; for visual testing delegate to chrome.
Technical analysis specialist. Delegates here for impact analysis, dependency analysis, risk assessment, technical debt evaluation, migration path analysis, complexity analysis, and technology comparisons. Use when evaluating blast radius of changes, assessing complexity or risks, or comparing technical options.
Architecture specialist. Delegates here for system-level and component-level architecture design and review — bounded contexts, module boundaries, dependency direction, ADRs, SOLID audits, pattern correctness, and aggregate integrity. Use when designing a new subsystem, auditing structural health, or making architectural decisions. For general PR review delegate to review; for impact, migration, or risk analysis delegate to analysis. Read-only for source code; may write ADRs and design docs under docs/architecture/. Returns structured persist blocks for project memory updates.
Backend development specialist. Delegates here for server-side development, APIs, business logic, service architecture, and message queues. Use when implementing endpoints, writing business logic, or working with backend frameworks (PHP, Python, Node.js, Go, Rust, Java). For schema design, migrations, indexing, and query optimization delegate to database.
Chrome browser automation specialist. Delegates here for web testing, form filling, screenshot capture, navigation, visual regression testing, and GIF recording. Use when verifying UI behavior, capturing visual evidence, or testing browser-based flows.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Specialist sub-agents for AI-assisted development, packaged as a Claude Code Plugin.
| Agent | Role |
|---|---|
accessibility | WCAG audits, ARIA review, keyboard navigation, screen-reader compatibility |
analysis | Impact analysis, dependency analysis, risk & complexity |
architect | System & component architecture design and review |
backend | Server-side development, APIs, business logic, service architecture |
chrome | Chrome browser automation, visual testing, GIF recording |
concept | Technical concepts, effort estimates, user stories |
database | Schema design, migrations, indexing, query optimization |
debug | Bug investigation, root cause analysis, test failure fixes |
devops | CI/CD pipelines, container builds, Kubernetes, Infrastructure-as-Code |
discovery | Codebase mapping, architecture exploration, onboarding |
docs | READMEs, API docs, ADRs, changelogs, project memory updates |
frontend | HTML, CSS, JS/TS, React, Vue, Angular, design-to-code |
incident | Production incident triage, timeline reconstruction, mitigation strategy |
performance | Performance audits, profiling, bottleneck analysis |
refactor | Large-scale refactors, pattern extraction, modernization, dead-code |
research | Technology evaluation, best practices, API/SDK documentation |
review | PR reviews, code quality checks, architecture triage |
security | OWASP audits, secret detection, auth review, CVE checks, threat modeling |
testing | Writing tests, TDD, coverage improvement, test infrastructure |
Zero coupling to .agent-context/ — Agents detect tech stack from project manifests and receive project context via the delegating prompt. They work in any project without requiring the Agent-Context framework.
Persist block protocol — Write-coupled agents (architect, docs) return structured persist: blocks in their responses instead of writing directly to project files. The orchestrating agent decides where to persist the data.
claude plugin marketplace add https://github.com/lx-wnk/agents
claude plugin install agents@lx-wnk
Once installed, agents are available as subagent_type in the Agent tool:
subagent_type: "analysis" # or backend, frontend, debug, etc.
See docs/integration-with-agent-context.md for how to wire these agents into the Agent-Context framework (delegating prompt patterns, persist block consumption).
MIT
Curated skills for AI coding agents — architecture design/review, component design/review, PR review-and-fix, tech-gazette, obsidian, and agent-context lifecycle.
npx claudepluginhub lx-wnk/agents --plugin agentsCodebase exploration, refactoring, and quality analysis
Code transformation: Dev SDLC orchestrator (code-shipping pipeline), plan, assert, audit, review, test, refactor, debug, for-sure. Hosts engineering agents.
AI-powered development workflow automation - Phase-based planning, implementation orchestration, preflight code quality checks with security scanning, ship-it workflow, and development principles generator for CLAUDE.md
AI Pilot workflow agents: sniper (code quality), research-expert, explore-codebase, seo-expert, websearch
Task-focused agents for test, review, debug, docs, CI, security, refactoring, research, performance, and search-replace — with teammate and subagent role guidance
Use this agent when you need to design scalable architecture and folder structures for new features or projects. Examples include: when starting a new feature module, refactoring existing code organization, planning microservice boundaries, designing component hierarchies, or establishing project structure conventions. For example: user: 'I need to add a user authentication system to my app' -> assistant: 'I'll use the code-architect agent to design the architecture and folder structure for your authentication system' -> <uses agent>. Another example: user: 'How should I organize my e-commerce product catalog feature?' -> assistant: 'Let me use the code-architect agent to design a scalable structure for your product catalog' -> <uses agent>.