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
Explores the codebase and returns concise summaries of code structure, relationships, and patterns. Use for understanding existing code before making changes.
Agent Claude Code
Validates specifications, plans, and implementations against the project constitution at .specify/memory/constitution.md.
codeverbojan/claude-code-kickstart
Agent Claude Code
Audits components and pages for WCAG 2.1 AA compliance. Checks contrast, semantics, forms, keyboard nav, and motion. Use on any UI component.
Agent Claude Code
Agent "load-test" from kangminhyuk1111/agents, covering load test agent, configuration, initial setup interview, prerequisites and verify k6 installation.
Agent Claude Code
Code review and quality analysis specialist.
Agent Claude Code
Use after staging changes with git add, before running git commit. Reads the staged diff and drafts a Conventional Commits message that describes what actually changed. Use proactively whenever the user is about to commit.
Agent Claude Code
Read-only reviewer for JWT login, password hashing, and /auth routes in this tracker. Use when the user asks to review auth.py, registration, login tokens, or getcurrentuser. Use after changes to auth helpers or auth routes. Do not use for session/cost exploration or for implementing features.
Najeebullah3124/awesome-claude-universe
Agent Claude Code
You are a senior Code Reviewer with 12+ years of experience in software development and code quality assurance. You specialize in identifying code quality issues, performance optimization opportunities, and ensuring adherence to best practices across multiple programming languages and frameworks.
Agent Claude Code
Expert documentation specialist. Proactively updates documentation when code changes are made, ensures README accuracy, and maintains comprehensive technical documentation. Be sure to give this subagent information on the files that were changed so it knows where to look to document changes. Always call this agent…
Maximumsoft-Co-LTD/claude-flightdeck
Agent Claude Code
Author zero-fix Design Docs that let a downstream implementation agent ship in one pass with no re-delegation. Target ≥500 lines for non-trivial tasks (correlates with zero post-delegation rework). Includes AC type-contradiction scan, LSP type verification, touched-files matrix, and lesson references. Use proactively…
smarks26/claude-plugin-template
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…
Agent Claude Code
Network structure and social capital analysis. Structural holes, brokerage, network topology, information flow. Invoke for questions about positioning, relationships, market structure, competitive advantage, or when you need to understand who is connected to whom and where the gaps are.
Agent Claude Code
Adversarial reviewer on Opus 5. The orchestrator dispatches it against any idea, plan, design, architectural decision, or diff BEFORE presenting or committing it: attacks premises, steel-mans the strongest alternative, and names the likeliest failure mode. Read-only — returns findings, never edits. Not a general code…
Agent Claude Code
Architect — AmbyKit role for plan; use for that perspective.
shihchengwei-lab/separation-and-audit-claude-code
Agent Claude Code
Code diff review — reads staged diff, returns four categories of suggestions (bug risk / performance / duplication / naming). No pass/fail verdict.
kimtth/ms-fabric-skills-dev-starter
Agent Claude Code
Orchestrate end-to-end Microsoft Fabric data engineering workflows that span multiple workloads and personas. Use when the request crosses Spark, Warehouse, Pipelines, Lakehouse architecture, migration, or data quality operations. Delegates deep single-endpoint implementation to specialized skills and resources.
Agent Claude Code
Maintain documentation - keeps decisions.md, errors.md, and CLAUDE.md files accurate. Use when docs have drifted from the code.
Agent Claude Code
An automated workflow for managing a candidate’s job search from incoming HR replies through vacancy collection, résumé matching, vacancy summaries, and archiving. It passes information between stages using CSV files and folders.
Agent Claude CodeOpenCode
Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or sensitive data. Flags secrets, SSRF, injection, unsafe crypto, and OWASP Top 10 vulnerabilities.
AlexFischman/mcp-skill-creator-agency
Agent Claude Code
Create complete agent modules with folder structure per Agency Swarm v1.0.0 spec.
Agent Claude Code
Medium complexity — multi-file changes, debugging. Fans out down to fast/view only.
Agent Claude Code
Plans Active Directory attack paths from enumeration or BloodHound data. Use on domain-joined Windows rooms.
Agent Claude Code
Internal subagent for the Second Pass skill. Grades a non-measurable output against the originating skill's intent and the user's request on a universal A–F rubric, returns a grade plus concrete feedback for iteration.
Agent Claude Code
General-purpose code reviewer for single files or focused diffs. Use when reviewing specific files or a single diff before merging. Examines logical errors, race conditions, edge cases, type mismatches, and CLAUDE.md compliance. Reports issues by severity with file:line references. For multi-file PR or pre-merge…
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: