devloop

Archive a completed plan to .devloop/archive/

Start development workflow - lightweight entry point

Save current plan state and prepare for fresh context restart

Learn how to use devloop - interactive guide to commands, workflow, and best practices

List GitHub issues for the current repository

Create a GitHub issue (or local issue with --local)

Create an actionable plan with autonomous exploration

Fetch and integrate PR review feedback into devloop plan

Comprehensive code review for existing changes or PR

Execute plan tasks via fresh-context subagents (swarm mode)

Execute plan tasks autonomously until completion

Complete validation and git integration for shipping a feature

Configure the devloop statusline for Claude Code

Use this agent to generate or update READMEs, API docs, inline comments, and changelogs. Use when: User asks to write or update documentation, README, API docs, CHANGELOG, or code comments. Do NOT use when: User needs code exploration (use engineer), test writing (use qa-engineer), or security analysis (use security-scanner). <example> user: "Update the API documentation" assistant: "I'll launch devloop:doc-generator to document the API changes." </example>

Use this agent for code exploration, architecture design, refactoring analysis, git operations, and code review. Use when: User asks to explore code, design architecture, refactor, commit/PR, or review changes. Do NOT use when: User needs test generation (use qa-engineer), security audit (use security-scanner), or documentation (use doc-generator). <example> user: "How does the payment processing work?" assistant: "I'll launch devloop:engineer to explore the payment system." </example> <example> user: "Create a PR for this feature" assistant: "I'll use devloop:engineer to handle the git workflow." </example> <example> user: "Review my changes before commit" assistant: "I'll launch devloop:engineer in reviewer mode to review your code." </example>

Use this agent for test generation, test execution, bug tracking, and deployment validation. Use when: User asks to write tests, run tests, track bugs, or validate deployment readiness. Do NOT use when: User needs code review (use engineer), security scan (use security-scanner), or code exploration (use engineer). <example> user: "Write tests for the new UserService" assistant: "I'll launch devloop:qa-engineer to create tests." </example> <example> user: "Run the tests" assistant: "I'll use devloop:qa-engineer to run tests and analyze results." </example>

Use this agent for security vulnerability scanning including OWASP Top 10, hardcoded secrets, and injection risks. Use when: User asks about security, vulnerabilities, hardcoded secrets, injection risks, or OWASP compliance. Do NOT use when: User needs code review for quality (use engineer), test generation (use qa-engineer), or general code exploration (use engineer). <example> user: "Check if this auth code is secure" assistant: "I'll launch devloop:security-scanner to analyze security." </example>

Use this agent to configure the user's Claude Code status line setting. Use when: User asks to set up, configure, or update the devloop statusline. Do NOT use when: User asks about statusline content/data (that's the statusline script itself). <example> user: "Set up the devloop statusline" assistant: "I'll configure the devloop statusline for you." </example>

Autonomous task executor for devloop:run-swarm. Implements a single plan task with fresh context. Do not use for interactive work. Use when: Orchestrator is running swarm mode and needs to parallelize independent plan tasks. Do NOT use when: Interactive work is needed, or for single-task execution (just do the work directly). <example> Context: The orchestrator is running devloop:run-swarm and needs to execute a plan task assistant: "I'll spawn a swarm-worker to implement this task with fresh context." </example>

Use this agent for planning implementations, gathering requirements, managing issues, and validating completion. Use when: User asks to break down tasks, plan implementation, gather requirements, validate DoD, or manage issues. Do NOT use when: User wants to explore code (use engineer), write tests (use qa-engineer), or generate docs (use doc-generator). <example> user: "Break this into tasks" assistant: "I'll launch devloop:task-planner to create an implementation plan." </example> <example> user: "Is this feature ready to ship?" assistant: "I'll use devloop:task-planner to validate Definition of Done." </example>

This skill should be used for REST API, GraphQL, versioning, pagination, authentication, backend routes, web services, HTTP endpoints, server API design

This skill should be used for system design, design patterns, architectural decisions, SOLID principles, clean code structure, code organization, refactoring strategy, software architecture

This skill should be used for guidance on commit size, scope, and creating reviewable commits, splitting large changes, commit hygiene

This skill should be used for database schema design, indexes, query optimization, migrations, SQL, PostgreSQL, MySQL, ORM patterns, data modeling, database relationships

Audit devloop against Claude Code updates to identify integration opportunities. Use after Claude Code releases, monthly maintenance, or when exploring new features.

This skill should be used for branching strategies, conventional commits, PR workflows, and release management, git flow, trunk-based development, merge strategies

This skill should be used for Go idioms, error handling, goroutines, interfaces, and testing, golang, Go language, Go modules, Go concurrency

This skill should be used for Java/Spring patterns, dependency injection, streams, Optional, Kotlin, Spring Boot, Maven, Gradle, JVM backend

This skill should be used for configuring devloop project settings via .devloop/local.md, git workflow preferences, commit settings, review options

This skill should be used when creating, reading, or updating devloop plans in .devloop/plan.md, task tracking, progress logs, phase management, PR feedback

This skill should be used for integrating PR review comments back into devloop plan, parsing review feedback, addressing reviewer concerns

This skill should be used for Python idioms, type hints, async/await, pytest, Django, Flask, FastAPI, Python web frameworks, pandas, data processing

This skill should be used for React hooks, components, state management, performance, frontend TypeScript, Next.js, JSX/TSX, web UI components

This skill should be used for OWASP, security review, authentication, XSS, SQL injection prevention, CSRF, input validation, secure coding, vulnerability scanning

This skill should be used for test coverage, test pyramid, unit/integration/E2E test design, TDD, BDD, mocking strategies, test doubles, test architecture

2 hooks across 2 events