Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.
phobologic/claude_code_helpers
Agent Claude Code
Adversarial code reviewer on an agent team. Reviews changes that have already passed AC verification. Focuses on correctness, security, reliability, and performance. Creates tk tickets for findings.
sergei-aronsen/claude-code-toolkit
Agent Claude Code
Deep Ruby on Rails expertise - ActiveRecord, Hotwire, testing, performance, security.
Agent Claude Code
Activates when user needs help with migrations - database migrations, code migrations, or framework upgrades. Triggers on "migrate", "upgrade framework", "move to new version", "database migration", "schema change", "breaking changes", or migration planning.
forest6511/claude-code-recipes-v2
Agent Claude Code
A Japanese-language session for reviewing REST APIs, which are web interfaces that programs use to exchange data.
Agent Claude Code
Expert React Native / Expo code reviewer. Catches routing param traps, OTA drift, native module mismatches, accessibility gaps, offline/persistence mistakes, and platform gotchas.
YourTechBud/coding-harness-config
Agent Claude Code
Use when relevant files or documentation sections are unknown and exploration would significantly reduce how much you need to read. Returns relevant locations and brief explanations of their relevance so you can read the selected material yourself. When relevant files are already known or a quick search is sufficient…
matheusallvarenga/claude-code-skills
Agent Claude Code
Complete Supabase platform specialist covering architecture design, schema creation, RLS policies, Edge Functions, real-time subscriptions, storage, AI/vectors, performance optimization, security hardening, and LGPD/GDPR compliance. Use PROACTIVELY for any Supabase-related development from initial setup to production…
Agent Claude Code
Infrastructure-as-Code reviewer that analyzes Terraform, Kubernetes, Helm, Docker, and CI/CD configs for best practices, security, and cost. Read-only analysis.
Agent Claude Code
Independent read-only judge for slices that touch the trust boundary — untrusted input, authentication, authorization, secrets, or dependencies — returning a one-line verdict.
laravel-agent-kits/claude-livewire-starter-kit
Agent Claude Code
Expert QA engineer specializing in comprehensive quality assurance, test strategy, and quality metrics. Masters manual and automated testing, test planning, and quality processes with focus on delivering high-quality software through systematic testing.
will-pagane/chief-of-staff-template
Agent Claude Code
Renders the final HTML report from a structured analysis payload. Use after the main agent has finished diagnosing — never for analysis itself.
Agent Claude Code
Fast agent specialized for exploring codebases. Use this when you need to quickly find files by patterns, search code for keywords, or answer questions about the codebase.
Agent Claude Code
StoryForge orchestrator. Reviews planning, identifies active work, prevents unstructured implementation, delegates to specialists, and updates delivery artifacts.
Agent Claude Code
Adversarial quality evaluator. Reviews any artifact (code, tasks, specs, plans, KB docs) against its acceptance criteria, rubric, and KB conventions. Produces the 7-column issue ledger with source and severity tags. Does NOT fix anything; does NOT compute the grade.
Agent Claude Code
Expert at diagnosing code smells and planning safe, behavior-preserving refactorings. Driven by two skills — code-smells (the classic taxonomy: Bloaters, Object-Orientation Abusers, Change Preventers, Dispensables, Couplers) and refactoring (the 60+ named techniques across Composing Methods, Moving Features…
PratikHotchandani22/claude-ollama-agents
Agent Claude Code
Use this agent for ALL code writing tasks: generating new code, fixing bugs, refactoring existing code, and implementing features. Delegates actual code generation to a local Ollama model (zero Claude token cost for the heavy lifting). Use whenever more than 5 lines of code need to be written or modified.
catch-the-wave/fullstack-ios-claude-skills
Agent Claude Code
Scans codebases for security vulnerabilities, anti-patterns, and architectural issues. Creates .claude/SECURITY.md for vulnerability tracking. Builds on codebase-analyzer foundation. Use for security audits, compliance checks, or pre-deployment reviews.
Agent Claude Code
Database architecture and design specialist. Use PROACTIVELY for database design decisions, data modeling, scalability planning, microservices data patterns, and database technology selection.
Agent Claude Code
Self-healing meta-agent that monitors, repairs, and continuously improves all Camp Air agents. Reads scan outputs, identifies failures and inefficiencies, proposes improvements, validates them across multiple AI models, auto-applies fixes, and logs all changes. Run after any agent scan to trigger the improvement…
thiscantbeserious/agent-session-recorder
Agent Claude Code
SDLC workflow coordinator. Spawns specialized agents, gates phase transitions, and orchestrates the development lifecycle. Use when starting SDLC workflows or coordinating between roles.
Agent Claude Code
Use for Rust backend tasks involving Axum/Actix-web, SQLx/Diesel/SeaORM, Tokio async, and production Rust service architecture.
Agent Claude Code
Specialized agent for extracting unique insights and perspectives from content files, handling large files by chunking, and preserving authentic voice and reasoning patterns. ALWAYS searches for duplicates before creating notes.
Agent Claude Code
Extracts structured data from review files into a JSON format for visualization. Use in Round 5 before the viz-designer and html-builder.
SeanningTatum/cf-saas-starter-react-router
Agent Claude Code
Drives a feature's golden path + one error path through the LIVE app using the Playwright CLI (a throwaway Node script run headless), screenshots each step, and writes a verification doc to .brain/features/ /verifications/ .md. Replaces writing per-feature e2e specs. Use for any user-visible feature/flow before…
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: