Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.
MCKRUZ/intent-driven-development
Agent Claude Code
Reviews user-facing Angular changes for UX quality: every state exists (loading, empty, error, success), accessibility basics hold, components follow the codebase's existing patterns, and the flow works end-to-end. Angular-aware — also catches the framework's own failure modes. Use PROACTIVELY when a change adds or…
Agent Claude Code
System design agent that defines system structure, makes technology decisions, and ensures architectural consistency across the codebase.
Agent Claude Code
Use this agent when you need to refactor code for better organization, cleaner architecture, or improved maintainability. This includes reorganizing file structures, breaking down large components into smaller ones, updating import paths after file moves, fixing loading indicator patterns, and ensuring adherence to…
Agent Claude Code
Read-only audit invocation for a claims-verifier pass. Carries Read, Grep, and Bash (recomputation only) and no network or write tools, so it can recompute hashes/figures over its sanctioned read set while an out-of-set write or fetch stays impossible by tool set. Spawned cold, per pass, by the claims-verifier…
Agent Claude Code
Main-session orchestrator for multi-step work. Run as the session agent (claude --agent orchestrator) — it dispatches explorer/planner/implementer/reviewer/tester. Only orchestrates when it IS the main session; a spawned subagent cannot dispatch others.
Agent Claude Code
Level 2 orchestrator. Coordinates comprehensive code reviews across all dimensions by routing PR changes to appropriate specialist reviewers. Select when PR analysis and specialist coordination required.
Agent Claude Code
Runs and explains the @aziontech/webkit adoption flow — npx @aziontech/webkit init. Sets up deps, lint configs, pre-commit, the webkit MCP, and the Claude Code bundle in this project, idempotently.
Agent Claude Code
Use this agent when the user asks to "create an agent", "generate an agent", "build a new agent", "make me an agent that...", or describes agent functionality they need. Trigger when user wants to create autonomous agents for plugins. Examples: Context: User wants to create a code review agent user: "Create an agent…
zapprosite/claude-code-minimax
Agent Claude Code
Place custom agents for this project here.
paulo-yamagishi/claude-code-setup
Agent Claude Code
Reviews documentation and skill changes for consistency and correctness.
SaharCarmel/Sahar-claude-code-marketplace
Agent Claude Code
Plans code review fan-out. Reads the Code Review book TOC and the PR diff, then decides how many code-reviewer agents to spawn and which chapters each one owns. Outputs a JSON plan that the orchestrator consumes to launch parallel reviewers.
Agent Claude Code
Role: Dokploy Template Architect & Builder Version: 1.0.0 Purpose: Orchestrate end-to-end creation of production-grade Dokploy application templates with Cloudflare integration defaults.
JAXTech-Labs/claude-code-template
Agent Claude Code
Orquestrador principal. Recebe uma tarefa, identifica os agents relevantes, distribui o trabalho em paralelo e consolida os resultados.
Agent Claude Code
Use this agent when you need expert code review for Ruby on Rails or Next.js applications, focusing on best practices, DRY principles, Clean Code standards, security vulnerabilities, database optimization, and Test-Driven Development. This agent should be invoked after writing or modifying code to ensure it meets…
Agent Claude Code
Systematic Python code review. Invoked before important commits.
Agent Claude Code
Security and GDPR compliance expert for authentication, authorization, rate limiting, audit logging, consent management, and server hardening.
Agent Claude Code
Read-write worker that implements a focused change — edits code, runs commands, verifies.
Agent Claude Code
Code reviewer. Use before any git commit, when validating implementations, or when asked to review a PR or diff. Focuses on bugs and security, not style.
xcodethink/open-claude-code-skills
Agent Claude Code
A read-only quality-audit agent that treats “finished” as something to test rather than assume. It checks a system through several independent lenses, including security, data quality, operations, performance, and error handling.
orlando-japan/claude-code-setting
Agent Claude Code
Security-focused code review. Use when the user asks to "audit for security", "check for vulnerabilities", review auth/authz/crypto/input handling code, or before shipping anything that touches secrets, user input, or external services. Also use proactively when reviewing dependency additions.
Agent Claude Code
Senior VBA code review specialist. Use after writing or modifying VBA to review for security, quality, performance, and best practices before committing or releasing.
Cyvid7-Darus10/claude-code-config
Agent Claude Code
Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (knip, depcheck, ts-prune) to identify dead code and safely removes it.
jessefmoore/offensive-claude-code
Agent Claude Code needs its repo
Alternate pentest report renderer in "operator casebook" style — a single self-contained HTML deliverable with phosphor-green CRT aesthetic, dossier hero, executive briefing, master timeline, attack graph, per-act chapters, host grid, TTP matrix, attack chains, dead-ends, and close stamp. Coexists with the markdown…
Iteam-company/claude-code-boilerplates
Agent Claude Code
Handles all database work — migrations, queries, schema changes. Invoke for any DB-related task.
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: