By ETdoFresh
Full project lifecycle orchestration — from request to 100% completion using agent swarms
Codebase exploration specialist for the project-runner workflow. Use this agent at the start of a new project to explore the repository structure, tech stack, existing patterns, dependencies, CI/CD configuration, test infrastructure, and anything relevant to the user's request. This agent gathers the foundational context that all subsequent phases depend on.
Requirements interview specialist for the project-runner workflow. Use this agent after exploration to conduct a thorough interview with the user. Asks clarifying questions about requirements, edge cases, preferences, and constraints using the AskUserQuestion tool. Must run as a FOREGROUND agent since it requires user interaction. Supports a no-interview mode where it auto-selects recommended answers.
Milestone and task decomposition specialist for the project-runner workflow. Use this agent after planning to break the plan into ordered milestones, each with detailed tasks. Creates individual milestone files with all tasks inline. The decomposition must be exhaustive — leaving no gaps — and result in a production-ready deliverable.
Milestone verification specialist for the project-runner workflow. Use this agent after milestone creation to verify completeness, correctness, and consistency. If issues are found, this agent fixes them directly in the milestone files and re-verifies until everything passes.
High-level planning specialist for the project-runner workflow. Use this agent after the interview phase to create a strategic plan. Produces architecture decisions, component breakdowns, and technology choices — but NOT milestones or tasks.
Same as project-implement but skips the interactive interview — auto-selects recommended answers for all interview questions. Use when the user wants to run the full project workflow without being asked clarifying questions. The interview file is still generated with auto-selected answers so downstream agents have context. Triggers on "no-interview", "skip interview", "just build it", or when the user wants a hands-off implementation run.
Start a new project from a request — explores, interviews, plans, creates milestones, and implements with agent swarms. Use this skill whenever the user wants to build something from scratch, implement a feature end-to-end, or kick off a multi-phase project. Triggers on phrases like "build me...", "implement...", "create a project for...", "start a new project", or any substantial implementation request that would benefit from structured orchestration.
Track and report project-runner project status. Use when the user asks about project progress, status, milestones, or tasks for an active project-runner project. Reads the project's status.md and milestone files to provide a comprehensive progress report.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub etdofresh/claude-marketplace --plugin project-runnerFind and kill processes listening on specific network ports. Cross-platform support for Windows, macOS, and Linux.
Delegate tasks to an opencode agent — runs opencode as a subprocess to handle tasks with alternative AI models like glm-5-turbo.
Comprehensive GitHub CLI (gh) reference — PRs, issues, repos, releases, workflows, API recipes, and more
Launch new Claude Code sessions in different working directories — equivalent to the CCY alias with --dangerously-skip-permissions and --remote-control
Plan using Claude Opus 4.6 — spawns an Opus Plan subagent with ultrathink for maximum reasoning depth
Context-Driven Development plugin that transforms Claude Code into a project management tool with structured workflow: Context → Spec & Plan → Implement
Multi-agent team orchestration for Claude Code. Set up parallel AI agent teams with file-based planning, progress tracking, and role-based collaboration.
Multi-agent orchestrator — supervisor loop that launches agents to implement plans
HelloAGENTS — The orchestration kernel that makes any AI CLI smarter. Adds intelligent routing, unified QA gates, safety guards, and notifications.
This skill should be used when the model's ROLE_TYPE is orchestrator and needs to delegate tasks to specialist sub-agents. Provides scientific delegation framework ensuring world-building context (WHERE, WHAT, WHY) while preserving agent autonomy in implementation decisions (HOW). Use when planning task delegation, structuring sub-agent prompts, or coordinating multi-agent workflows.
Autonomous multi-agent development framework with spec-driven sprints and convergent iteration