Prevent Codex subagent skill leakage via gate check and dispatch routing table

Codex subagents inherit filesystem access and can discover superpowers skills
via native discovery. Without guidance, they activate the 1% rule and invoke
full skill workflows instead of executing their assigned task.

- Add SUBAGENT-STOP gate check above the 1% rule in using-superpowers
- Add Codex dispatch routing table (spawn_agent/wait/close_agent)
- Add scope directives to all 4 subagent dispatch templates

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

skills/requesting-code-review/code-reviewer.md

@@ -1,6 +1,6 @@
 # Code Review Agent
 
-You are reviewing code changes for production readiness.
+You are reviewing code changes for production readiness. Do not independently discover or invoke superpowers skills — your orchestrator handles workflow decisions. Just execute this review.
 
 **Your task:**
 1. Review {WHAT_WAS_IMPLEMENTED}

skills/subagent-driven-development/implementer-prompt.md

@@ -26,6 +26,10 @@ Task tool (general-purpose):
 
     **Ask them now.** Raise any concerns before starting work.
 
+    ## Scope
+
+    You are a focused implementer. Do not independently discover or invoke superpowers skills — your orchestrator handles workflow decisions. Just execute this task.
+
     ## Your Job
 
     Once you're clear on requirements:

skills/subagent-driven-development/spec-reviewer-prompt.md

@@ -18,6 +18,10 @@ Task tool (general-purpose):
 
     [From implementer's report]
 
+    ## Scope
+
+    You are a focused reviewer. Do not independently discover or invoke superpowers skills — your orchestrator handles workflow decisions. Just execute this review.
+
     ## CRITICAL: Do Not Trust the Report
 
     The implementer finished suspiciously quickly. Their report may be incomplete,

skills/using-superpowers/SKILL.md

@@ -3,6 +3,10 @@ name: using-superpowers
 description: Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
 ---
 
+<SUBAGENT-STOP>
+If you were dispatched as a subagent to execute a specific task, STOP. This skill is not for you. Your dispatch prompt is your instructions. Do not invoke skills. Go execute your task.
+</SUBAGENT-STOP>
+
 <EXTREMELY-IMPORTANT>
 If you think there is even a 1% chance a skill might apply to what you are doing, you ABSOLUTELY MUST invoke the skill.
 
@@ -27,6 +31,17 @@ If CLAUDE.md says "don't use TDD" and a skill says "always use TDD," follow CLAU
 
 **In other environments:** Check your platform's documentation for how skills are loaded.
 
+## Dispatching Tasks
+
+Skills that dispatch subagent tasks (like `dispatching-parallel-agents`, `subagent-driven-development`) use platform-specific mechanisms. Skill examples use Claude Code syntax — translate to your platform:
+
+| Concept | Claude Code | Codex (`[features] collab = true`) |
+|---------|------------|-----|
+| Dispatch a task | `Task` tool | `spawn_agent` |
+| Parallel tasks | Multiple `Task` calls in one response | Multiple `spawn_agent` calls |
+| Wait for result | Task returns inline | `wait` |
+| End subagent | Task completes automatically | `close_agent` |
+
 # Using Skills
 
 ## The Rule