codecrew
01Plugin Claude Code
Local marketplace for CodeCrew plugin.
Plugin Claude Code
Local marketplace for CodeCrew plugin.
Plugin Claude Code
Multi-agent orchestration plugin - a virtual dev crew with intelligent model routing (Opus/Sonnet/Haiku), lite mode, 3-layer codebase indexing, auto-skill selection, task history, rollback, and custom agents.
Agent
Chief Executive Officer - the brain of CodeCrew. Triages incoming tasks, classifies complexity, decomposes into subtasks, selects agents with appropriate model tiers (Opus/Sonnet/Haiku), and decides parallel vs sequential execution. Use for every /crew task command.
Agent
Code Reviewer - performs thorough code review against project standards and the original task requirements. Checks for bugs, security issues, code quality, and convention adherence. Use after implementation.
Agent
Debugger - investigates bugs through systematic root cause analysis. Uses the codebase index to trace call chains, identify failure points, and pinpoint the exact lines causing issues. Use for bug investigation before fixes.
Agent
DevOps Engineer - handles Docker configurations, CI/CD pipelines, deployment scripts, and infrastructure tasks. Uses Haiku for cost efficiency on routine infrastructure work.
Agent
Documentation Writer - creates and updates documentation, READMEs, code comments, and API docs. Uses Haiku for cost efficiency on documentation tasks.
Agent
Junior Developer - handles simple, well-defined tasks like typo fixes, formatting, simple one-line changes, and small documentation updates. Uses Haiku for cost efficiency.
Agent
Security Analyst - scans code for vulnerabilities including XSS, injection, auth issues, hardcoded secrets, and insecure patterns. Use for security audits and pre-deploy reviews.
Agent
Senior Developer - handles complex implementation tasks including multi-file changes, new features, refactoring, and performance optimization. The primary implementation agent for moderate-to-complex work.
Agent
Test Engineer - writes and maintains tests including unit tests, integration tests, and e2e tests. Handles TDD workflow, test strategy, and coverage analysis.
Agent
VP of Engineering - handles architecture decisions, technical planning, complex system design, and code structure analysis. Use for moderate-to-complex features, refactors, and performance optimization planning.
Agent
VP of Quality - oversees quality gates, test strategy, review coordination, and final approval before task completion. Use for complex feature reviews and quality assessments.
Command
Create, list, or remove custom project-specific agents. Subcommands: create, list, remove.
Command
Configure CodeCrew settings - model tiers, default mode, token budgets, and more. Subcommands: show, set, reset.
Command
View CodeCrew task history with optional filters. Supports --type, --agent, and --limit flags.
Command
Initialize CodeCrew in the current project - analyzes codebase, builds index, configures agent team.
Command
Delegate a task to the CodeCrew agent team in lite mode (no Opus). Uses only Sonnet + Haiku agents.
Command
Rebuild the 3-layer codebase index from scratch - use after major refactors or when index seems stale.
Command
Undo the last task's file changes using git. Shows affected files and requires confirmation before reverting.
Command
Show CodeCrew status - team config, index health, skill catalog, and task history.
Command
Delegate a task to the CodeCrew agent team - auto-routes to the right agents with smart model selection. Use --lite flag or /crew lite for lite mode (no Opus).
Command
CodeCrew - Multi-agent orchestration with intelligent model routing. Subcommands: init, task, status, reindex.
Hook
Runs after a tool call finishes for Edit and Write tool calls, running echo "$CLAUDE_FILE_PATHS" >> .claude/.index-stale. From d3x293/code-crew.