Generate consensus-based plans before multi-agent execution for underspecified requests.
npx skills add https://github.com/xdkp/oh-my-claudecode --skill ralplan-xdkp
Please help me install this Agent Skill. Skill: ralplan Source: https://github.com/xdkp/oh-my-claudecode/tree/main/skills/ralplan Command: npx skills add https://github.com/xdkp/oh-my-claudecode --skill ralplan-xdkp
Ralplan prevents wasted, misaligned work by forcing vague execution requests to be converted into a concrete, testable consensus plan before any heavy multi-agent execution starts.
Use Ralplan when your request is unclear and you want a safe, structured plan first: run /oh-my-claudecode:ralplan "task description".
High-intent search queries and answers about installing and using this skill.
Multi-agent execution requests need a pre-execution gate that converts vague inputs into a concrete, testable consensus plan before any heavy implementation starts, preventing wasted and misaligned work.
Consensus-based planning enforces an ordered Planner, Architect, and Critic workflow that iterates until agreement or a bounded retry limit is reached, producing a final plan with explicit verification steps.
High-risk software tasks require a deliberate mode that applies pre-mortem analysis and expanded test planning across unit, integration, e2e, and observability layers before execution begins.
Yes, you can gate multi-agent task execution using optional interactive approvals within the consensus planning loop, ensuring human validation occurs before proceeding to the implementation phase.
ADR-style decision documentation is needed when finalizing a consensus plan, as it explicitly records architectural decisions and verification criteria alongside the pre-execution scope definitions.
Without pre-execution gating, multi-agent orchestration risks wasted effort on underspecified requests lacking concrete files, symbols, issue references, or acceptance criteria, leading to misaligned implementations.
pkuppensDecompose issues into actionable work items linked to code, tests, and related issues.
OliverOuyangGate vague multi-agent prompts through Planner, Architect, and Critic consensus reviews.
JaCha00Coordinate Planner, Architect, and Critic agents for consensus-driven task planning.
0xjc65ethOrchestrate autonomous Bitcoin and token trading with multi-agent consensus and pre-trade risk checks.
