Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.
fabio-barboza/development-orchestrator
Agent Claude Code
Subagente isolado que executa UM item de trabalho delegado, em contexto limpo — uma task de um PRD (skill do-execute-task), um fix task de review (do-execute-review-fix) ou um bug de QA (do-execute-qa-fix). Não use para criar PRD/TechSpec/tasks nem para rodar review ou QA.
Agent Claude Code
An independent project auditor that checks a completed implementation against its written requirements and contracts. It produces a report rather than changing the code.
Agent Claude Code
Orchestrates the full relocation experience for clients moving into or out of a market. Handles community orientation, school research, vendor referrals, move logistics coordination, and the dozens of invisible decisions that make a relocation succeed or fail.
Agent Claude Code
Copilot engineering orchestrator — decomposes complex, multi-step customization tasks into research, execution, creation, and review phases. Delegates to specialized workers for discovery, repository mutation, command-oriented validation, and quality review, then synthesizes the results into a cohesive report. Choose…
gensecaihq/MCP-Developer-SubAgent
Agent Claude Code
MCP troubleshooting and debugging specialist for protocol issues, transport problems, and diagnostic analysis.
Agent Claude Code
AB-900 practice buddy: exam-realistic items + admin scenario walkthroughs, grounded in Microsoft Learn via Microsoft Learn MCP, Context7, and MarkItDown.
stacklok/toolhive-registry-server
Agent Claude Code
Reviews code for the registry servers' best practices, security patterns, Go conventions, and architectural consistency.
Agent Claude Code
You are a conversion-focused copywriter specializing in creating high-performing meta titles and descriptions that maximize click-through rates from search engine results pages (SERPs).
armanzeroeight/fastagent-plugins
Agent Claude Code
GitHub Actions workflow design strategist. Makes decisions about workflow structure, job organization, resource optimization, and CI/CD patterns. Use when designing GitHub Actions workflows, optimizing CI/CD pipelines, or architecting automation strategies.
rohittcodes/claude-plugin-suite
Agent Claude Code
Enterprise compliance specialist focusing on regulatory compliance, audit preparation, and governance frameworks. Masters GDPR, HIPAA, SOC 2, PCI DSS, and other regulatory standards. Handles compliance assessment, audit preparation, policy development, and risk management. Use PROACTIVELY for compliance audits…
Agent Claude Code
name: base-template-generator description: Use this agent when you need to create foundational templates, boilerplate code, or starter configurations for new projects, components, or features. This agent excels at generating clean, well-structured base templates that follow best practices and can be easily customized.…
Agent Claude Code
Reviews a supplied diff for introduced behavioral and contract defects. Use only when dispatched by the code-review skill.
Agent Claude Code
Adversarial reviewer for specs, plans, implementations, or any combination ("spec amendment + implementation in the same PR" is the dominant case), plus two narrower branches — an RFC-only review and an intent review. Loads project conventions and the targeted artifacts; attacks along the relevant checklists; returns…
SKZL-AI/boris-cherny-claude-code-playbook
Agent Claude Code
Specialized subagent for scanning X/Twitter and secondary sources for new Boris Cherny Claude Code tips.
Agent Claude Code
Design and plan application architecture using MCP tools.
Agent Claude Code
Use proactively to answer "is this safe / secure / production worthy?" Delegate when about to commit, push, open a PR, or mark a security-relevant task done; when a diff touches auth, credentials, secrets, user input, SQL, shell, file paths, deserialization, or crypto; when evaluating a destructive shell command…
Agent Claude Code
Second and final seat of the two-reviewer gate. Assumes the implementer and the QA seat both missed something, and breaks claims through direct measurement rather than accepting them. Returns APPROVE or REQUEST CHANGES.
Agent Claude Code
Delegate to Codex AI when you need alternative implementation approaches, code analysis from a different perspective, or want to explore multiple solutions. Best for complex coding tasks that benefit from a second AI opinion.
Agent Claude Code
Reviews code for bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions, using confidence-based filtering to report only high-priority issues that truly matter.
Ashfaqbs/software-dev-ai-claude-toolkit
Agent Claude Code
System design and architecture decisions. Use when planning new services, evaluating trade-offs, or making technology choices.
Agent Claude Code
Friendly onboarding agent that explains the repo like you are new. Maintains a portable .buddy/ knowledge base (Markdown + small JSON) at the repo root so every clone benefits.
Agent Claude Code
Detects inconsistencies in code style, patterns, and conventions.
Agent Claude Code
Convert PRDs into development task lists.
IdoCohen560/claude-unity-game-studio
Agent Claude Code
Rapid prototyping specialist for pre-production. Builds quick, throwaway implementations to validate game concepts and mechanics. Use during pre-production for concept validation, vertical slices, or mechanical experiments. Standards are intentionally relaxed for speed.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: