before-after
A reference set of small, behavior-preserving refactorings with the reasoning for each. Tests stay green across every one.
An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
1,494 agents across 238 plugins.
A reference set of small, behavior-preserving refactorings with the reasoning for each. Tests stay green across every one.
When reasoning stalls, *search*. Halving the problem space repeatedly finds the culprit in log₂(N) steps instead of N. Bisection applies to three spaces:…
Use proactively for codebase exploration, file/symbol search, reading logs, summarizing files or directories, and answering "where is X / how does Y work"…
Use proactively after builder or architect completes any task
Dispatch when a Go function, method, or package needs new tests authored from scratch or extended with missing cases. Generates table-driven tests, subtests,…
Dispatchable subagents that wrap one or more **gophers** skills. Each agent is a focused worker — it loads the underlying skill, runs a fixed process on input…
Automated code review specialist for Next.js full-stack applications with platform-specific validation, ensuring code quality, security, performance, and…
Specialized agent for managing static and dynamic content across web applications. Handles content creation, SEO optimization, search implementation, metadata…
You are an Azure DevOps specialist with deep expertise in Azure deployment patterns, Azure Static Web Apps, Azure App Service deployment slots, Azure…
Splits an epic into thin vertical slices that are each safe to leave forever. Writes the plan to disk. Does not write product code.
Cheap, fast reader. Maps what exists in the codebase and reports back facts, not opinions. Read-only.
Runs the project's verification contract against real behaviour and judges honestly - verified, gap, or failed. Does not implement fixes.
Review persona: senior software architect lens for any codebase. Use for architecture review or grading of a project's shape: folder structure and module…
Бизнес-интервью с предпринимателем для извлечения требований и заполнения CLAUDE.md + domain-rules.yaml. Один-два вопроса за раз, бизнес-язык, без жаргона.
Критический Opus-ревьюер модели данных ПЕРЕД реализацией схемы БД / миграций / RLS в проекте пользователя. Fresh context, НЕ соглашается по умолчанию. Ищет…
Готовит бриф для Claude Design (claude.ai/design) по формуле C.R.O.P. (Context / Requirements / Output / Patterns). Плагин не рисует UI сам — готовит handoff.…
The `xhigh` rung of `cad-executor`; `bin/route.mjs` picks it, not the user.
The `low` rung of `cad-plan-checker` (goal-backward plan gate); `bin/route.mjs` picks it, not the user.
The `high` rung of `cad-plan-checker`; `bin/route.mjs` picks it, not the user.
Stage 1 peer code reviewer focused on memory safety, modern C++ idioms, and undefined behavior.
Stage 1 peer code reviewer focused on idiomatic Go, error handling, and concurrency patterns.
Stage 1 peer code reviewer focused on JVM idioms, Spring/Android patterns, and null safety.
You are a security auditor focused on protecting API keys, preventing credentials leaks, and securing Webhook entry points.
Invoke after a developer commit to run build, test, and lint and emit a BMAD-style PASS/CONCERNS/FAIL gate verdict as JSON. Read-only; never modifies code.
Use to resolve findings on an existing pull request - review comments, CI failures, and self-review findings - fixing code, updating tests, re-verifying gates,…
Use for high-signal review of a diff or pull request in any codebase, with emphasis on scope (PR intent), correctness, contract drift, security,…
Use for a focused security pass on a diff or pull request - authorization, secrets, input validation, data exposure, webhook verification, and OWASP-style…
Use as the top-level orchestrator at the start of any new app project, or when the user wants strategic direction, scope decisions, prioritization tradeoffs,…
Use as the single founder interface — prepares decision briefs, tracks unresolved commitments, ensures every founder decision reaches a specification, and…
Use after a developer finishes a ticket and before tech-manager merges. Reviews a single branch / diff against the impl spec, the engineering principles, and…
Read-only codebase explorer. Use for "where is X", "how does Y work", "which files touch Z" - returns conclusions with file:line refs, never file dumps. Never…
Runs tests, builds, and linters; reports compactly. Mechanical run-and-report only. Do NOT use when failures need interpretation or fixing - that is e2e-runner…
Cheap gate before accepting another agent's diff - does it match the task (scope, completeness, obvious breakage)? Returns PASS/FAIL with reasons. NOT a code…
Use when a user prompt arrives in Gaia and needs to be routed — when intent must be matched to a specialist surface, when multiple surfaces touch the same…
Use when planning a feature or decomposing work from a brief into an executable plan -- turning objectives and acceptance criteria into ordered, testable tasks…
Use when building, modifying, or auditing Gaia's own machinery — agents, skills, hooks and hook modules, routing config, CLI plugins, build manifests — or when…
Applies researched improvements to Claude Code components, validates changes with the component-reviewer agent, and creates pull requests. The only agent that…
Migrates components (agents, commands, skills, hooks, settings, MCPs) from external GitHub repositories to claude-code-templates, validates them with…
Investigates best practices and improvement opportunities for Claude Code components using web search and codebase analysis. Returns structured research…
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic