agents
claudeAll 21 specialist sub-agents for AI-assisted development (full bundle). Subagent types: agents:<name>.
21 agents · hooks
Verification specialists: review, review-lite, security, testing, performance. Subagent types: agents-quality:<name>.
Plugin agents-quality from marketplace lx-wnk in lx-wnk/agents. Commands read from the repo's manifest — yesterday.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
accessibilityAccessibility 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; f
agent-toolingClaude Code ecosystem engineer. Delegates here for authoring and maintaining Claude Code artifacts — subagents, skills, hooks, slash commands, plugin and marketplace manifests, CLAUDE.md / memory files, and Agent-Context wiring. Use when creating or reviewing a subagent, packaging a skill, adding a
analysisTechnical 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 techn
architectArchitecture 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, o
backendBackend 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, migration
chromeChrome 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.
conceptConcept and planning specialist. Delegates here for technical concepts, effort estimates, user stories, specifications, requirements analysis, and project planning. Use when planning features or projects, evaluating approaches, or creating structured proposals before implementation.
databaseDatabase specialist. Delegates here for schema design, migrations, indexing, query optimization, and data-model evolution. Use when adding or altering database schemas, writing migrations, optimizing slow queries, or designing data models. For application business logic delegate to backend; for runt
debugDebugging specialist. Delegates here for investigating bugs, fixing test failures, analyzing error logs, and root cause analysis. Use when something is broken, tests fail unexpectedly, or error behavior needs systematic investigation.
devopsDevOps and platform specialist. Delegates here for CI/CD pipelines, container builds, Kubernetes manifests, Infrastructure-as-Code, and deployment workflows. Use when adding or modifying GitHub Actions / GitLab CI, Dockerfiles, Helm charts, Terraform/Pulumi, or release automation. For application co
discoveryCodebase discovery specialist. Delegates here for understanding unfamiliar codebases, architecture mapping, dependency tracing, and onboarding into new projects. Use when exploring an unknown codebase, mapping system architecture, or tracing data flows.
docsDocumentation specialist. Delegates here for writing READMEs, API documentation, ADRs, changelogs, and project memory updates. Use when documentation needs creating, updating, or auditing for completeness.
frontendFrontend development specialist. Delegates here for HTML, CSS, JavaScript, TypeScript, React, Vue, Angular, Svelte, component building, responsive design, and design-to-code tasks. Use when building UI components, implementing designs, or fixing frontend styling and behavior. For dedicated WCAG audi
incidentProduction incident responder. Delegates here for live incident triage, log and metric investigation, timeline reconstruction, mitigation strategy, and postmortem support. Read-only — never mutates production state. Use when a production system is degraded or down, an alert needs investigation, or a
performancePerformance analysis specialist. Delegates here for performance audits, profiling, bottleneck analysis, database query optimization, and Core Web Vitals. Use when response times are too slow, resources are saturated, or systematic performance measurement is needed.
refactorRefactoring specialist. Delegates here for large-scale refactors, pattern extraction, dead-code removal, modernization, and structural cleanup that preserves behavior. Use when restructuring code without functional changes, extracting reusable abstractions, removing dead code, or modernizing legacy
researchResearch specialist. Delegates here for technology evaluation, best practice research, security vulnerability research, API/SDK documentation gathering, and library comparisons. Use when making technology decisions, evaluating options, or gathering information from external sources.
review-liteLightweight correctness reviewer for small diffs. Delegates here for correctness-gap review of changes under 300 LOC: logic errors, broken edge cases, unhandled failures, contract mismatches. Read-only by capability (no Bash, no Write/Edit). Use when a small change needs an independent verifier befo
reviewCode review specialist. Delegates here for PR reviews, code quality checks, and architecture analysis on changes. Read-only — never modifies code. Use when reviewing changes before merge or auditing code quality. For deep security audits delegate to security; for performance audits delegate to perfo
securitySecurity audit specialist. Delegates here for OWASP audits, secret detection, authentication and authorization review, dependency CVE checks, and threat modeling. Read-only — never modifies code. Use when auditing code for vulnerabilities, reviewing auth flows, scanning for secrets, or producing a t
testingTesting specialist. Delegates here for writing tests, improving test coverage, fixing failing tests, test architecture, and TDD workflows. Use when tests need writing, coverage is insufficient, or test infrastructure needs improvement.
"${CLAUDE_PLUGIN_ROOT}"/hooks/deny-write-bash.sh
"${CLAUDE_PLUGIN_ROOT}"/hooks/recommend-verifier.sh
All 21 specialist sub-agents for AI-assisted development (full bundle). Subagent types: agents:<name>.
21 agents · hooks
Core engineering brain: discovery, analysis, architect, concept, research, docs, debug, refactor, agent-tooling. Subagent types: agents-core:<name>.
21 agents · hooks
Build and run specialists: backend, database, devops, incident. Subagent types: agents-ops:<name>.
21 agents · hooks
Web and UI specialists: frontend, accessibility, chrome. Subagent types: agents-web:<name>.
21 agents · hooks
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.
5 commands
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.