claude

ceo-ralph

Claude Opus CEO orchestrator with dual-executor (Codex MCP + Task sub-agents), delegation tracking, and web dashboard for spec-driven autonomous development

1 on GitHubby DUTSTECHv1.1.0MITupdated 9 months ago
/

Plugin ceo-ralph from marketplace dutstech-ceoralph in DUTSTECH/ceoralph. Commands read from the repo's manifest — 1 month ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (10)

  • clnode-agents

    Discover installed agents/skills/rules and create new agents

  • compress-output

    Forces agent to compress its final output before returning to Leader. Preload this skill in agent frontmatter to enforce output compression.

  • compress-review

    Reviewer-specific output compression — preserves findings detail while staying concise.

  • codex-delegation

    How to delegate implementation tasks to workers via Codex MCP or Task sub-agents. Use when executing tasks that require code implementation.

  • communication-style

    Output rules for all agents - concise, scannable, actionable. Based on Matt Pocock's planning principles.

  • delegation-principle

    Core principle that the main agent is a coordinator, not an implementer. All work must be delegated to subagents.

  • reality-verification

    Detect fix vs add goals, diagnose failures before work, verify fixes after. Ensures "fix X" specs actually fix X.

  • review-criteria

    Criteria for reviewing Codex worker outputs across 5 dimensions. Use when reviewing code submitted by workers before approval.

  • spec-workflow

    Spec-driven development workflow for building features with research, requirements, design, and task phases

  • verification-rules

    4-layer verification system for task completion. Use when verifying that a task has been fully completed before marking it done.

Slash commands (23)

  • /ceo-ralph:cancel

    Cancel active execution loop and cleanup state

  • /ceo-ralph:dashboard

    Start, stop, or open the CEO Ralph web dashboard

  • /ceo-ralph:design

    Generate technical design from requirements

  • /ceo-ralph:discovery

    Run merged discovery phase (research + requirements)

  • /ceo-ralph:enableremote

    One-shot Remote UI + HTTPS tunnel setup

  • /ceo-ralph:execute

    Start the execution loop with Codex MCP or Task sub-agents

  • /ceo-ralph:feedback

    Submit feedback or report an issue for CEO Ralph plugin.

  • /ceo-ralph:help

    Show help and available commands

  • /ceo-ralph:implement

    Start task execution loop

  • /ceo-ralph:new

    Create new spec and start discovery phase

  • /ceo-ralph:pause

    Pause the execution loop

  • /ceo-ralph:plan

    Generate merged execution plan (design summary + tasks)

  • /ceo-ralph:refactor

    Update spec files methodically after execution (discovery → tasks)

  • /ceo-ralph:remote-ui

    Configure and start the Remote UI for approvals

  • /ceo-ralph:requirements

    Generate requirements from goal and research

  • /ceo-ralph:research

    Run or re-run research phase for current spec

  • /ceo-ralph:resume

    Resume a paused execution

  • /ceo-ralph:setup

    Configure executor (Codex MCP or Task tool fallback) and verify setup

  • /ceo-ralph:start

    Smart entry point that detects if you need a new spec or should resume existing

  • /ceo-ralph:status

    Show rich status with worker tree, progress bars, and delegation stats

  • /ceo-ralph:switch

    Switch active spec

  • /ceo-ralph:tasks

    Generate implementation tasks from design

  • /ceo-ralph:uninstall

    Remove CEO Ralph MCP configuration

Subagents (10)

  • architect-reviewer

    Expert systems architect for technical design. Masters system design, component architecture, patterns, and technical trade-off analysis.

  • ceo-orchestrator

    Main orchestration brain that coordinates all phases and reviews all outputs

  • codex-reviewer

    Reviews Codex worker outputs against acceptance criteria and quality standards

  • plan-synthesizer

    Synthesizes merged spec artifacts in one pass for quick mode. Generates discovery.md and tasks.md with minimal user interaction.

  • product-manager

    Expert product manager for requirements gathering. Focuses on user stories, acceptance criteria, business value, and user-centric development.

  • qa-engineer

    QA engineer that runs verification commands and checks acceptance criteria for [VERIFY] tasks.

  • refactor-specialist

    Expert at methodically updating spec files after execution. Reviews sections, gathers feedback, and updates specifications incrementally.

  • research-analyst

    Expert analyzer and researcher that never assumes. Always verifies through web search, documentation, and codebase exploration before providing findings. Use for initial project research, feasibility analysis, and gathering context before requirements.

  • spec-executor

    Autonomous task executor for spec-driven development. Executes a single task from tasks.md, verifies, commits, and signals completion. Invoked via Codex MCP or Claude Task sub-agent.

  • task-planner

    Expert task planner for breaking design into executable tasks. Masters POC-first workflow, task sequencing, and quality gates.

Hooks (3)

  • Stop

    bash -lc "ROOT=\"${CLAUDE_PLUGIN_ROOT:-${CLAUDE_PLUGIN_DIR:-}}\"; if [ -z \"$ROOT\" ]; then echo \"CEO Ralph cleanup: plugin root not set\"; exit 0; fi; \"$ROOT/hooks/scripts/stop-runner.sh\""

  • SubagentStart

    bash -lc "ROOT=\"${CLAUDE_PLUGIN_ROOT:-${CLAUDE_PLUGIN_DIR:-}}\"; if [ -z \"$ROOT\" ]; then exit 0; fi; \"$ROOT/hooks/scripts/hook-dispatch.sh\" subagent-start"

  • SubagentStop

    bash -lc "ROOT=\"${CLAUDE_PLUGIN_ROOT:-${CLAUDE_PLUGIN_DIR:-}}\"; if [ -z \"$ROOT\" ]; then exit 0; fi; \"$ROOT/hooks/scripts/hook-dispatch.sh\" subagent-stop"

View source on GitHub

Similar plugins

ecc

claudecodex

Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses

200 skills · 98 commands · 71 agents · 1 MCP server · hooks

affaan-m/ECC 302,088

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

Visual workflow automation with templates, orchestration, and lifecycle management

5 skills · 8 commands · 3 agents

ruvnet/ruflo 81,589

Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.

1 skill

headroomlabs-ai/headroom 79,508

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development

9 skills · 1 command · 8 agents

wshobson/agents 42,461

Maintain ceo-ralph?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted