feat: Codex cross-platform support (Phase 1)

.agents/plugins/marketplace.json

@@ -0,0 +1,15 @@
+{
+  "plugins": [
+    {
+      "name": "flow-code",
+      "source": {
+        "source": "local",
+        "path": "."
+      },
+      "policy": {
+        "installation": "AVAILABLE",
+        "authentication": "ON_INSTALL"
+      }
+    }
+  ]
+}

.codex-plugin/plugin.json

@@ -0,0 +1,9 @@
+{
+  "name": "flow-code",
+  "version": "0.1.31",
+  "description": "Zero-dependency planning + execution with .flow/ task tracking and Ralph autonomous mode (multi-model review gates). Worker subagent per task with git worktree isolation for parallel execution. Three-layer quality system (guard + RP plan-review + Codex adversarial). Full-auto by default — AI decides from context, zero questions. Teams-default with file locking, DAG mutation, Codex-driven conflict resolution, auto draft-PR. Auto-detected stack profiles with one-command guard (test/lint/typecheck). Enhanced agent definitions with permissionMode/maxTurns/effort. Lifecycle hooks with state preservation (PreCompact injects .flow state into compaction, TaskCompleted auto-unlocks files, SubagentStart context injection). Memory v2 with atomic entries, dedup, and progressive disclosure. TDD enforcement mode. Multi-epic queue with dependency visualization. Includes 20 subagents, 25+ commands, 23 skills.",
+  "author": {
+    "name": "z23cc",
+    "url": "https://github.com/z23cc"
+  }
+}

agents/cross-model-reviewer.md

@@ -1,3 +1,10 @@
+---
+name: cross-model-reviewer
+description: Runs both Codex adversarial AND Claude review, then computes consensus
+model: opus
+disallowedTools: Edit, Write, Task
+---
+
 # Cross-Model Reviewer Agent
 
 Orchestrates adversarial code review across multiple AI models (Codex + Claude) and computes consensus.