An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
1,445 agents across 643 plugins.
Quick codebase explorer for beast. Maps project structure, tech stack, test infrastructure, and key patterns.
@malakhov-dmitriiView AgentBackend architecture specialist. Microservices, APIs, databases.
@fujigo-softwareView AgentFrontend architecture specialist. React, Vue, Angular, Next.js.
@fujigo-softwareView AgentData architecture specialist. Databases, ETL, analytics.
@fujigo-softwareView AgentUse project form components instead of native elements in all `.tsx` files. Native form elements bypass GAIA's Conform integration and accessible error/label…
@gaia-reactView Agent- Single `useTranslation()` call per component, flag multiple `useTranslation` calls in the same component - Namespace override via `{ns: 'other'}` as the…
@gaia-reactView Agent- Import only from `tailwind-merge`, flag any use of `clsx`, `classnames`, or `cn` wrappers for class merging - `twJoin` when no class conflict is possible…
@gaia-reactView AgentDetect performance regressions in changed code — N+1 queries, unnecessary recomputes, missing memoization, big-O regressions, memory leaks, bundle-size red…
@ncoevoetView AgentReview test code in the diff — assertion quality, branch coverage of new code, mock realism, brittle patterns. Distinct from "spec existence" check.
@ncoevoetView AgentDetect breaking changes to public APIs, exported types, schemas, REST routes, and DB migrations. Flags consumer-impacting changes that need coordination.
@ncoevoetView AgentIntegration testing gap reviewer that surveys existing integration coverage, identifies trust boundaries and seams, and recommends gaps or starter strategies.…
@chrisallenlaneView AgentMutation testing worker that applies code mutations one at a time and reports which tests catch them
@chrisallenlaneView AgentTest quality reviewer that identifies brittle, tautological, and harmful tests. Reports redundant tests as informational only.
@chrisallenlaneView AgentGiven a GitHub Actions run ID and PR URL, fetches failing-job logs, writes full logs to a temp file, and returns a structured summary of failures. Invoked by…
@bendruckerView AgentReview a pushed pull request with fresh eyes in an isolated worktree, never editing the code under review. A peer's PR gets curated comments; my own gets a…
@bendruckerView AgentManages GitHub repository rulesets. Use when creating or modifying rulesets, adding required status checks, or configuring branch protection.
@bendruckerView Agent- [When] 버그 리포트가 있거나 예상과 다른 동작이 발견되었을 때 - [Input] 버그 설명, 재현 경로, 에러 로그
@ggombeeView AgentMulti-agent orchestrator for complete full-stack feature development
@yassinelloView AgentProduction incident response and crisis management expert
@yassinelloView AgentRoutes QA tickets to the right agents in the right order — including environment setup and live browser validation
@anasssView AgentAnalyzes a multi-repo release diff to map cross-repo impact, AC compliance, and deployment risks
@anasssView AgentMaps code changes to existing tests — finds which tests to run, which may break, and where coverage gaps exist
@anasssView AgentUse this agent when you need to create, update, or edit artefacts — documents, guides, specifications, skills, or any content that should meet quality…
@isvlasovView AgentUse this agent when the user needs comprehensive research on a topic, question, or domain — gathering information, synthesising findings, and producing…
@isvlasovView AgentReviews implementation against enriched roadmap chunk, architecture, and code quality standards. Applies perspective references loaded by orchestrator.…
@isvlasovView AgentDocumentation and reference researcher. Fetches official docs, verifies technical information, and summarizes findings. READ-ONLY.
@obsidian-owlView AgentCode quality and spec compliance reviewer. Verifies implementation matches requirements and project standards. Read-only for source files; Bash restricted to…
@obsidian-owlView AgentAdversarial test engineer. Writes tests that are genuinely hard to pass. Thinks like an attacker hunting for weak implementations. Use before implementation to…
@obsidian-owlView AgentStage 1 peer code reviewer focused on Python idioms, PEP 8, and type hints.
@hazarsozerView AgentStage 1 peer reviewer focused on test coverage, edge cases, and missing assertions.
@hazarsozerView AgentStage 1 peer reviewer focused on naming, structure, comment quality, and function size.
@hazarsozerView AgentPeer Reviewer 2; assesses domain expertise, substantive accuracy, and field-specific adequacy
@imbad0202View AgentWrites the full paper draft section by section from the structured outline and Paper Configuration Record
@imbad0202View AgentQ1 journal editorial review; delivers Accept/Reject verdict with actionable feedback on research reports
@imbad0202View Agent**Note: The current year is 2026.** Use this when interpreting commit dates and recent changes.
@everyincView Agent© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic
