Agent Claude Code
Implementation agent for complex, multi-step coding tasks. Use proactively when delegating code writing, bug fixing, refactoring, or any task requiring both exploration and modification. Replaces built-in general-purpose for all implementation tasks.
Agent Claude Code
Planning and architecture agent for complex tasks, features, or projects. Use proactively when a task requires decomposition, has multiple components, or when requirements need clarification before implementation. Replaces built-in Plan for all planning tasks.
Agent Claude Code
Deep research and codebase exploration agent. Use proactively for any task requiring factual verification, technical investigation, documentation lookup, community discourse analysis, or codebase understanding. Replaces built-in Explore for all research and exploration tasks.
Command Claude Code
Run dotfiles management commands directly from Claude Code.
Hook Claude Code
One of 4 in settings.json
Runs when a session starts, executing session-env.sh via bash. From marvinleonbutlerii/.dotfiles.
Hook Claude Code
One of 4 in settings.json
Runs when you submit a prompt, before the agent sees it, running echo TURN PROTOCOL: Execute skill-sweep gates (session-guard. From marvinleonbutlerii/.dotfiles.
Hook Claude Code
One of 4 in settings.json
Runs when the agent finishes a response, running echo STOP CHECK: Did you complete the holistic review? If yo. From marvinleonbutlerii/.dotfiles.
Skill Claude Code
Evaluates code changes, output, and implementations for correctness, maintainability, security, and adherence to project standards. Activates when evaluating any code — whether user-requested or as part of the mandatory holistic review before shipping.
Skill Claude Code
Systematic debugging for any type of issue. Activates when any error, failure, or unexpected behavior is encountered during any task. Root-cause investigation at the deepest architectural level. Never symptom-by-symptom patching.
Skill Claude Code
Structured planning for complex tasks, features, or projects. Activates when a task requires decomposition, has multiple components, or when requirements need clarification before implementation.
Skill Claude Code
Initialize new projects with proper structure, documentation, and Claude configuration. Activates when creating any new project, repository, module, or significant component.
Skill Claude Code
Systematic code refactoring to improve design without changing behavior. Activates when code structure needs improvement without behavior change, including during the refactor phase of TDD cycles.
Skill Claude Code
Deep research and knowledge synthesis. Activates for ANY task involving factual claims, technical decisions, implementation patterns, or domain knowledge. Deactivated ONLY when the mechanical task test passes (all three conditions true).
Skill Claude Code
Monitors session scope and entropy. Activates automatically via skill-sweep. Detects when the conversation has drifted significantly from its original intent or has accumulated too many unrelated threads. Warns the user and generates a handoff prompt for a new session.
Skill Claude Code
Mandatory per-turn gate protocol. Runs at the start of EVERY turn. Four sequential gates must be evaluated before any work begins. Not optional. Not skippable. Not implicit.
Skill Claude Code
Test-Driven Development workflow. Activates when implementing new behavior, fixing bugs, or when tests are needed to verify correctness. Enforces Red-Green-Refactor discipline. Tests are written BEFORE implementation.
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: