berrzebb/SoulFlow-Orchestrator
Skill Claude CodeCodex
Execute any dependency-requiring task inside ephemeral containers (podman/docker) with automatic cleanup. Use for Python scripts (pip packages), SQLite/DuckDB local DB, PostgreSQL/MySQL connections, or any tool requiring system packages. Container is pulled, used, and removed — nothing stays on host. Do NOT use for…
berrzebb/SoulFlow-Orchestrator
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and validate skill structure. Use when users want to create a skill from scratch, update or optimize an existing skill, restructure SKILL.md for better triggering, or add scripts/references/assets. Do NOT use for general coding tasks, when the user just wants to…
berrzebb/SoulFlow-Orchestrator
Skill Claude CodeCodex
Summarize or extract text from URLs, local files, YouTube videos, and podcasts using the summarize CLI. Use when the user asks to summarize a link, article, video, or document. Supports multiple output lengths and models. Do NOT use for web search (use web-search) or for content the agent can read directly.
berrzebb/SoulFlow-Orchestrator
Skill Claude CodeCodex
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output. Use when the task needs an interactive TTY: Python REPLs, long-running processes, or orchestrating multiple agents in parallel. Requires tmux on PATH (macOS/Linux, WSL on Windows). Do NOT use for simple non-interactive…
berrzebb/SoulFlow-Orchestrator
Skill Claude CodeCodex
Get current weather conditions and forecasts for any location using Open-Meteo API with KMA (Korea Meteorological Administration) data. No API key required. High-resolution 1.5km model for Korea. Use when the user asks about weather, temperature, rain, snow, humidity, wind, or forecasts. Do NOT use for historical…
berrzebb/SoulFlow-Orchestrator
Skill Claude CodeCodex
A workflow-design role for building and editing automated processes that connect providers, backends, agents, and quality checks.
Plugin Claude Code
AI development loop — orchestrator distributes tasks to headless workers, independent auditor verifies, structural enforcement auto-blocks downstream on upstream failure. Full-cycle validated with 10-scenario test harness.
Instructions file
Claude Code instructions for berrzebb/consensus-loop, covering consensus-loop (v2.5.1), quick commands, module map, skills (9) + agents (3) and mcp tools (9).
Agent
Headless worker for quorum — receives task + context, implements code, runs tests, submits evidence to watch file, handles audit corrections. Use when the orchestrator needs to delegate a coding task to a worker agent.
Agent
Read-only RTM generator — reads all track work-breakdowns, verifies each requirement against the actual codebase using deterministic tools, and produces 3 Requirements Traceability Matrices (Forward, Backward, Bidirectional). Use when the orchestrator needs to establish or update the RTM before distributing work.
Agent
Find UI issues that code-level analysis (scout, codemap, dependencygraph) cannot detect. Launches a real browser to check rendering, visual states, interactions, a11y, and runtime errors. Use after FE implementation to catch issues invisible to static analysis.
Command
Shortcut for /consensus-loop:guide — evidence writing guide.
Command
Shortcut for /consensus-loop:merge — squash-merge worktree branch.
Command
Shortcut for /consensus-loop:orchestrator — distribute tasks, manage agents.
Command
Shortcut for /consensus-loop:planner — design PRD, tracks, work breakdowns.
Command
Shortcut for /consensus-loop:retrospect — extract learnings, manage memories.
Command
Shortcut for /consensus-loop:tools — run deterministic analysis tools.
Command
Shortcut for /consensus-loop:verify — run done-criteria checks (CQ/T/CC/CL/S/I/FV/CV).
Command
Shortcut for /consensus-loop:audit.
Command
Shortcut for /consensus-loop:status.
Hook
Runs when a session starts, executing session-start.mjs via node. From berrzebb/consensus-loop.
Hook
Runs when the agent finishes a response, executing session-stop.mjs via node. From berrzebb/consensus-loop.
Hook
Runs before the agent uses a tool for Bash and Agent tool calls, executing session-gate.mjs via node. From berrzebb/consensus-loop.
Hook
Runs after a tool call finishes for Edit and Write tool calls, executing index.mjs via node. From berrzebb/consensus-loop.