0
01MCP server Claude CodeCodexCursor +2
MCP server "0" as configured in scalarian/oh-my-codex. Runs ../../packages/mcp-server/dist/index.js with node.
MCP server Claude CodeCodexCursor +2
MCP server "0" as configured in scalarian/oh-my-codex. Runs ../../packages/mcp-server/dist/index.js with node.
Skill Claude CodeCodex
OMX product plugin entry for findings-first verification across code, plans, checks, and durable runtime state.
Skill Claude CodeCodex
OMX product plugin entry for durable tmux-aware multi-worker execution with review gates and resumable state.
Skill Claude CodeCodex
OMX product plugin default for routing intent through interview, planning, execution, team escalation, and verification.
Skill Claude CodeCodex
Boundary-mapping mode for invasive changes, new interfaces, data contracts, and risky tradeoffs.
Skill Claude CodeCodex
Durable research-mission mode for long-running discovery, optimization, and evidence gathering under .omx/.
Skill Claude CodeCodex
Intent-first clarification loop for vague, risky, or product-heavy work before planning or execution.
Skill Claude CodeCodex
Health-check mode for OMX install, repo state, plugin wiring, hook status, and runtime degradation.
Skill Claude CodeCodex
Focused implementation mode for one planned slice with explicit verification and handoff.
Skill Claude CodeCodex
Runtime-truth mode for reading tasks, sessions, reviews, inbox, memory, and team state before acting.
Skill Claude CodeCodex
Execution-plan mode that turns intent into small, verifiable slices backed by durable .omx artifacts.
Skill Claude CodeCodex
Evidence-first research mode for current patterns, implementation risks, and decision support.
Skill Claude CodeCodex
Dedicated verification lane that applies the review protocol and records a durable approval or change request.
Skill Claude CodeCodex
Red-green-refactor mode for behavior with clear inputs, outputs, and regression value.
Skill Claude CodeCodex
Execution-path mapping for entry points, data flow, side effects, and blast radius before risky work.
Agent
Own system shape before implementation starts. Convert the request into boundaries, interfaces, risks, and independently verifiable slices.
Agent
Own one implementation slice and move it to review with clean evidence. Do not absorb adjacent work unless the plan is explicitly updated.
Agent
Run the durable execution system. Keep the queue moving, workers healthy, inbox actionable, and review flow honest.
Agent
Turn intent into an execution-ready plan that can survive handoffs, restarts, and review. The plan must be small enough to execute and strong enough to verify.
Agent
Reduce uncertainty before implementation. Collect repo facts, external constraints, and migration risks, then leave durable research artifacts instead of chat-only conclusions.
Agent
Find the real problems before code lands. Review is findings-first and evidence-driven across code, tests, docs, and runtime state.
MCP server Claude CodeCodexCursor
MCP server that bridges Google's Gemini CLI to any MCP-compatible AI assistant. Runs locally from the @staticpayload/gemini-mcp npm package.