gsd-codebase-mapper
Explores codebase and writes structured analysis documents. Spawned by map-codebase with a focus area (tech, arch, quality, concerns). Writes documents…
An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
6,290 agents across 643 plugins.
Explores codebase and writes structured analysis documents. Spawned by map-codebase with a focus area (tech, arch, quality, concerns). Writes documents…
USE BEFORE committing security-sensitive changes (auth, crypto, routes, templates, secrets). Audits current diff for OWASP-Top-10 patterns + deps…
Run tests on Sonnet — auto-detects framework, returns structured failure analysis, read-only.
Use this agent for read-only test-coverage gap analysis between waves. Identifies missing boundary cases, error paths, and integration gaps not caught by…
Use this agent for security analysis — OWASP checks, authentication flows, input validation, authorization, and vulnerability assessment. Read-only analysis…
Use this agent between waves or at session end to verify work quality against the session plan. Checks implementation correctness, test coverage, TypeScript…
Use this agent for autonomous story planning — deep codebase research + detailed chunk breakdown in one focused pass. Primary use: parallel planning of…
Interactive browser automation agent powered by playwright-cli. Owns a live browser session - navigates pages, clicks elements, fills forms, reads…
PR review agent crystallized from reverse-engineering CodeRabbit. Consult when reviewing PRs, checking diffs for bugs/security/performance, or when the user…
Use this agent when an MSP needs to reconcile billing in QuickBooks Online — matching invoices to contracts, identifying unbilled work, flagging overdue…
Use this agent when a service manager, dispatcher, or team lead needs a full cross-board health read on the connected PSA — unassigned aging, SLA-at-risk…
Use this agent when an MSP owner, service-delivery manager, or ops lead needs a single operational, commercial, and security heartbeat across the entire client…
PM 모드 PRD 작성 전문가. PM-Discovery + PM-Strategy 결과를 종합하여 실행 가능한 PRD 문서 생성. Use proactively in PM mode final step.
PM 모드 전략 분석가. JTBD(Jobs-to-be-Done) + Lean Canvas 기반 가치 제안 설계. Use proactively in PM mode.
TRUST 5 코드 리뷰 전문가. Phase 4 병렬 리뷰 + Lead Consolidator 패턴. Tested/Readable/Unified/Secured/Trackable 5개 기준.
Spec-blind behavioral tester - validates implementation against specs without seeing implementation details
AST-based test coverage analysis - identifies untested code and coverage gaps
Testing specialist using the Quality Diamond model — specification-driven tests from acceptance criteria down through contract tests, property-based…
This agent should be used when the user needs security analysis for a feature, or when the arn-code-feature-spec-teams skill needs a security specialist…
This agent should be used when the arn-code-sketch skill needs to create or update an interface preview using the project's actual framework, component…
This agent should be used when a single phase plan task needs to be executed, either for implementation or testing. Reads INTRODUCTION.md for codebase…
專為 Java/Spring Boot 專案設計的程式碼簡化專家。簡化和優化程式碼以提升清晰度、一致性和可維護性,同時保持原有功能不變。預設專注於最近修改的程式碼,除非另有指示。
分析日誌檔案和監控數據,識別錯誤模式和異常行為。 擅長從大量日誌中提取有價值的資訊,識別錯誤模式,統計錯誤頻率。 使用時機: - "分析這些錯誤日誌" - "找出日誌中的異常模式" - "統計錯誤發生頻率" - "分析這個堆疊追蹤" - "從日誌中找出問題的時間點"
當使用者要求「驗證我的插件」、「檢查插件結構」、「驗證插件是否正確」、「驗證 plugin.json」、「檢查插件檔案」或提到插件驗證時使用此代理。也在使用者創建或修改插件組件後主動觸發。範例:
Bounded test-fix loop agent for beast. Diagnoses test failures and applies targeted fixes, max 5 cycles.
Deep research agent for beast-plan. Investigates codebase architecture, external docs, APIs, schemas, and library compatibility with maximum depth and…
Code simplification specialist for beast. Refines code for clarity, consistency, and maintainability while preserving all functionality.
Quality gate enforcement. Check all criteria before proceed.
Context and memory management. Optimize token usage, maintain state.
Use when: go.mod present. Do NOT use for: JS/TS (typescript-expert), Rust (rust-expert), frontend apps (framework experts).
Use when: composer.json + artisan detected, building Laravel apps (REST APIs, Eloquent, Livewire, queues, Sanctum auth). Do NOT use for: React/Vue frontend…
Use when: MEMORY/LESSON.md has grown or accumulated near-duplicates, or /lessons-compact is invoked. Do NOT use for: appending a single lesson (that is…
Use this subagent to troubleshoot visual defects, layout confusion, CSS issues, responsive exceptions, and inconsistencies between interaction and design in…
Post-deploy smoke test agent. Verifies live URL, checks console errors, screenshots 6 breakpoints, runs axe-core, validates SEO tags, reports pass/fail with…
Runs prettier + oxlint --fix on modified files. Ensures consistent formatting and lint compliance with zero human intervention.
Sentry-triggered incident response agent. Reads error events, traces to source code, proposes fixes, creates branches, and opens PRs with the fix.
Expert in MongoDB 6.x/7.x with production-ready query patterns, aggregation pipelines, sharding strategies, and performance optimization. Masters document…
Expert in Neo4j 5.x graph database with production-ready Cypher queries, graph modeling patterns, GDS algorithms, and APOC procedures for advanced graph…
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic