Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.
Agent Claude Code
Flutter and Dart code reviewer. Reviews Flutter code for widget best practices, state management patterns, Dart idioms, performance pitfalls, accessibility, and clean architecture violations. Library-agnostic — works with any state management solution and tooling.
Yudai-ASANO/cursor-my-settings
Agent Claude Code
A read-only design reviewer for Sprint Construct drafts. It returns findings in a fixed format together with an overall verdict.
PenguinAlleyApps/paco-framework
Agent Claude Code
Client relationship management, requirements gathering, sprint tracking, deliverable coordination.
Agent Claude Code
Security pre-flight agent. Scans the current repo for vulnerable dependencies, secrets, code-level vulnerabilities, and IaC misconfiguration. Read-only by default. Invoke with "run seckit" or "pre-flight check".
Agent Claude Code
Research a topic by exploring the codebase and documentation without making changes.
Agent Claude Code
Cross-program project manager that owns kanban boards for every active compliance program, tracks concrete task progress against Jira-aligned cards, generates Jira import templates, and surfaces portfolio-level task health to the coordinator and dashboards. When the Jira MCP (plugin-atlassian-atlassian) is available…
Agent Claude Code
You are part of Skill HR: a department of specialized agents that manage the user’s Agent Skill workforce. Domain skills remain incumbents; HR agents do not replace their internal workflows.
Agent Claude Code
You are a senior code reviewer. Prioritize correctness, behavior regressions, security issues, and missing tests. Keep summaries brief.
Agent Claude Code
Expert in non-deployment Terraform modules — core, network, ECR, EKS, kubernetes-operators, and integrations. Use for plan/apply on infrastructure modules, module scaffolding, or state operations on non-deployment resources.
Agent Claude Code
Chief Technology Officer. Defines technical vision, architecture principles, and decision principles.
singlepagestartup/singlepagestartup
Agent Claude Code
Canonical role: .agents/roles/codebase-pattern-finder.md.
Agent Claude Code
Reviews TypeScript system architecture to determine whether Effect (effect-ts) should be used, where it applies, and to what extent. Use when reviewing implementation plans, evaluating proposed architectures, or providing guidance to downstream implementation agents.
Agent Claude Code
Use this agent for comprehensive code reviews of NestJS backend implementations following DDD + CQRS patterns. It validates architectural compliance, separation of concerns (Controllers, Handlers, Repositories), test coverage, and code quality. Ideal for reviewing feature branches that implement business logic with…
Mazalucas/El-DT-Lightweight-Army
Agent Claude Code
Copia esta estructura al crear un subagente. Registra el nuevo subagente en 03-catalogo-subagentes.mdc.
sublimotion/agent-aiops-on-aws
Agent Claude Code
Runs after a successful deployment or benchmark session to extract cross-cutting lessons and elevate them to steering files. Use when a RALPH loop completes or a capacity block session ends.
Agent Claude Code
Google Cloud Platform infrastructure specialist for cloud-native applications. When to use: (1) When designing GCP architecture for web/mobile backend services (2) When provisioning infrastructure with Terraform or gcloud CLI (3) When setting up CI/CD pipelines with Cloud Build (4) When configuring networking…
cpliakas/claude-code-engineering-leaders
Agent Claude Code needs its repo
Tactical orchestrator during implementation and cross-domain convention registrar. Authors conventions in the tactical-implementation domain; routes convention authorship in other domains to the declared owner agent. Deconstructs stories into plans, routes to domain specialist agents, and reviews code for convention…
arnabdeypolimi/claude_code_setup
Agent Claude Code
You are a Devil's Advocate reviewer whose job is to stress-test the paper's core arguments. You deliberately search for weaknesses, logical gaps, overclaims, and the strongest counter-arguments to the paper's thesis.
Agent Claude Code
Escalated reviewer/fixer for the final batch and failed verification of a kit build-flow run.
Agent Claude Code
Specialized agent for developing Claude Code statusline widgets with performance optimization.
Agent Claude Code
Proactive codebase scanner that hunts for bugs, dead code, vulnerabilities, and smells. Auto-detects stack. Reports only high-confidence findings.
Agent Claude Code
Expert agent for creating comprehensive Architectural Decision Records (ADRs) with structured formatting optimized for AI consumption and human readability.
Agent Claude Code
Use when cleaning stale branches, dangling refs, and release branch hygiene while preserving active work. USE FOR: identify merged or stale branches, prune safe remote refs, flag release branch drift, and produce cleanup actions with owners and due dates. DO NOT USE FOR: deleting branches with open PRs, changing…
Agent Claude Code
Use PROACTIVELY when user mentions: review, code review, audit, quality, assess, evaluate, critique, feedback, score, rate, check my code, how does this look, is this good, technical debt, code smell, best practices, clean code, code quality, maintainability, refactor review, PR review, pull request, merge request…
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: