Agent
Popular
Auto-invokeda11y-architect
Accessibility Architect specializing in WCAG 2.2 compliance for Web and Native platforms. Use PROACTIVELY when designing UI…
Claude Code agents for Development
Flowy lists 5,718 subagents for Development, and the most-starred are a11y-architect, agent-evaluator and architect, all three from the 289,990-star ecc plugin. That plugin was last pushed on October 26, 2026.
a11y-architect agent-evaluator AgentPopularAuto-invokedagent-evaluator
Evaluates agent output against 5-axis quality rubric (accuracy, completeness, clarity, actionability, conciseness). Use after any…
architect AgentPopularAuto-invokedarchitect
Software architecture specialist for system design, scalability, and technical decision-making. Use PROACTIVELY when planning new…
analyze-pass-impact AgentPopularanalyze-pass-impact
Analyzes how a specific topic affects a group of compiler passes. Used by the /plan-update skill to parallelize research across…
compiler-review AgentPopularcompiler-review
Reviews Rust port code for port fidelity, convention compliance, and error handling. Compares changed Rust code against the…
investigate-error AgentPopularinvestigate-error
Investigates React compiler errors to determine the root cause and identify potential mitigation(s). Use this agent when the user…
orchestrator Agentorchestrator
- If the user makes a simple request (such as asking for the time) which you can fulfill by running a terminal command (such as…
cavecrew-builder Agentcavecrew-builder
Surgical 1-2 file edit. Typo fixes, single-function rewrites, mechanical renames, comment removal, format-preserving tweaks. Hard…
@juliusbrusseeInstall Agentcavecrew-investigator Agentcavecrew-investigator
Read-only code locator. Returns file:line table for "where is X defined", "what calls Y", "list all uses of Z", "map this…
@juliusbrusseeInstall Agentcavecrew-reviewer Agentcavecrew-reviewer
Diff/branch/file reviewer. One line per finding, severity-tagged, no praise, no scope creep. Output format `path:line: <emoji>…
@juliusbrusseeInstall Agentcode-reviewer AgentAuto-invokedcode-reviewer
Senior code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, and…
@addyosmaniInstall Agentsecurity-auditor AgentAuto-invokedsecurity-auditor
Security engineer focused on vulnerability detection, threat modeling, and secure coding practices. Use for security-focused code…
@addyosmaniInstall Agenttest-engineer AgentAuto-invokedtest-engineer
QA engineer specialized in test strategy, test writing, and coverage analysis. Use for designing test suites, writing tests for…
@addyosmaniInstall Agentarchitecture-analyzer AgentAuto-invokedarchitecture-analyzer
Analyzes a codebase's file structure, summaries, and import relationships to identify logical architectural layers and assign…
@egonex-aiInstall Agentarticle-analyzer AgentAuto-invokedarticle-analyzer
Analyzes markdown files using pre-parsed structural data and LLM inference to extract knowledge graph nodes and edges (entities,…
@egonex-aiInstall Agentassemble-reviewer AgentAuto-invokedassemble-reviewer
Reviews the output of merge-batch-graphs.py for semantic issues the script cannot catch. Recovers dropped nodes/edges and fills…
@egonex-aiInstall Agentcode-reviewer Agentcode-reviewer
Use this agent when you need comprehensive code quality assurance, security vulnerability detection, or performance optimization…
debugger Agentdebugger
Use this agent when encountering errors, test failures, unexpected behavior, or when RTK doesn't work as expected. This agent…
rtk-testing-specialist Agentrtk-testing-specialist
RTK testing expert - snapshot tests, token accuracy, cross-platform validation
adaptive-coordinator Agentadaptive-coordinator
Dynamic topology switching coordinator with self-organizing swarm patterns and real-time optimization
@ruvnetInstall Agentadr-architect Agentadr-architect
ADR lifecycle manager -- create, index, supersede, and link Architecture Decision Records to code
@ruvnetInstall Agentai-backend-expert Agentai-backend-expert
Metabase backend expert for Metabot, LLM provider adapters, agent tools, the Agent API, the MCP server, Slack Metabot, and AI…
content-backend-expert Agentcontent-backend-expert
Metabase backend expert for collections, cards (models, metrics), dashboards, documents, revisions, bookmarks, timelines,…
drivers-and-sync-backend-expert Agentdrivers-and-sync-backe…
Metabase backend expert for database drivers (the multimethod hierarchy, modules/drivers), metadata sync, fingerprinting, field…
accessibility-expert Agentaccessibility-expert
Expert accessibility specialist ensuring WCAG compliance, inclusive design, and assistive technology compatibility. Masters…
@wshobsonInstall Agentai-engineer Agentai-engineer
Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI,…
@wshobsonInstall Agentapi-documenter Agentapi-documenter
Master API documentation with OpenAPI 3.1, AI-powered tools, and modern developer experience practices. Create interactive docs,…
@wshobsonInstall Agentassistant Agentcodex-rescue Agentcodex-rescue
Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper root-cause…
@openaiInstall Agentacademic-researcher Agentacademic-researcher
Academic research specialist for scholarly sources, peer-reviewed papers, and academic literature. Use PROACTIVELY for research…
@davila7Install Agentaccessibility-tester Agentaccessibility-tester
Use this agent when conducting comprehensive accessibility audits, WCAG 2.2 compliance assessments, or evaluating UI components…
@davila7Install Agentadr-generator Agentadr-generator
Use when you need to formalize a technical or architectural decision as a structured Architectural Decision Record (ADR), or when…
@davila7Install Agentmemory_consolidation_prompt Agentmemory_read_prompt Agentmemory_read_prompt
You have access to a memory folder with guidance from prior runs in this sandbox workspace. It can save time and help you stay…
@openaiInstall Agentprompt Agentprompt
You are a general computer-use agent operating in a terminal-based assistant environment. You are expected to be precise, safe,…
@openaiInstall Agentexplorer Agentexplorer
Use this agent when the user wants to analyze or explore a codebase (remote repository or local repository) using Repomix. This…
@yamadashyInstall Agenti18n-translator Agenti18n-translator
Use this agent when you need to add new translatable strings to the application or verify existing translations. This includes:…
code-reviewer Agentcode-reviewer
Adversarially verifies one landed packet against its requirement; read-only.
@triggerdotdevInstall Agentcode-writer Agentcode-writer
Implements exactly one work packet — minimal diff, targeted checks, own-paths-only commits.
@triggerdotdevInstall Agentsoftware-architect Agentsoftware-architect
Resolves contested design questions against the specs; decision + rationale, never code.
@triggerdotdevInstall Agentcheck Agentcheck
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes…
@mindfold-aiInstall Agentimplement Agentimplement
Code implementation expert for the Trellis channel runtime. Understands specs and task artifacts, then implements features. No…
@mindfold-aiInstall Agenttrellis-check Agenttrellis-check
Code quality check expert. Reviews code changes against specs and self-fixes issues.
@mindfold-aiInstall Agentadvisor-subagent Agentadvisor-subagent
Stronger-model advisor for the Advisor plugin. Consulted by the main agent at key checkpoints (before a major decision, when…
@cursorInstall Agent
Questions
What is the best Development subagent for Claude Code?
By the GitHub stars of the plugin each ships in (Flowy does not rate quality), the best Development subagent for Claude Code is a11y-architect, level on stars with agent-evaluator and architect, all three from the 289,990-star ecc plugin.
How many Development subagents are there?
Flowy lists 5,718 subagents for Development, and this page draws the top 44 Development subagents and leaves out 4 documentation files the index read as subagents (MIGRATION_SUMMARY, AGENTS, AGENTS and 1 more).
Development in other kinds
Other subagent categories
- Agent Orchestration1,436
- AI & Agents809
- Automation687
- Security424
- Testing280
- Content233
- Marketing192
- Productivity191
- Monitoring143
- Writing128
- Product103
- Skill Authoring93
- Research91
- Design74
- Agent Workspaces72
- Data72
- Agent Memory67
- Documentation61
- Mobile59
- Business57
- Operations54
- Finance47
- Machine Learning41
- Education39
- Cloud & Infrastructure38
- Legal29
- MCP Servers25
- Code Generation22
- Code Review21
- Spec-Driven Development18
- Databases16
- Backend11
- SEO10
- Video & Audio10
- Debugging9
- Deployment9
- Frontend9
- Career8
- Data Science6
- Presentations6
- Sales6