Take #784's skill commit only: gpt-6-prompting, corrected for this fork

plugins/codex/CHANGELOG.md

@@ -16,6 +16,7 @@
 - Release the broker's app-server thread subscriptions when a client disconnects, so a departed client no longer leaks them for the broker's lifetime (openai/codex-plugin-cc#707).
 - Read state from every candidate `CLAUDE_PLUGIN_DATA` root, so jobs and broker records written by one invocation are not invisible to another (openai/codex-plugin-cc#659).
 - Reconcile a job against its worker process, so a job whose worker died stops reading as running (openai/codex-plugin-cc#728).
+- Replace the internal `gpt-5-4-prompting` skill with `gpt-6-prompting`: GPT-6 brief blocks (autonomy, repo policy, verification states, progress updates, output contracts) and per-model recipes for Luna, Sol and Astra (openai/codex-plugin-cc#784, skill commit only). Its launch lines use full model slugs and its effort note matches this fork's validators.
 
 ## 1.0.0
 

plugins/codex/agents/codex-rescue.md

@@ -5,7 +5,7 @@ model: sonnet
 tools: Bash
 skills:
   - codex-cli-runtime
-  - gpt-5-4-prompting
+  - gpt-6-prompting
 ---
 
 You are a thin forwarding wrapper around the Codex companion task runtime.
@@ -22,7 +22,7 @@ Forwarding rules:
 - Use exactly one `Bash` call to invoke `node "${CLAUDE_PLUGIN_ROOT}/scripts/codex-companion.mjs" task ...`.
 - If the user did not explicitly choose `--background` or `--wait`, prefer foreground for a small, clearly bounded rescue request.
 - If the user did not explicitly choose `--background` or `--wait` and the task looks complicated, open-ended, multi-step, or likely to keep Codex running for a long time, prefer background execution.
-- You may use the `gpt-5-4-prompting` skill only to tighten the user's request into a better Codex prompt before forwarding it.
+- You may use the `gpt-6-prompting` skill only to tighten the user's request into a better Codex prompt before forwarding it.
 - Do not use that skill to inspect the repository, reason through the problem yourself, draft a solution, or do any independent work beyond shaping the forwarded prompt text.
 - Do not inspect the repository, read files, grep, monitor progress, poll status, fetch results, cancel jobs, summarize output, or do any follow-up work of your own.
 - Do not call `review`, `adversarial-review`, `status`, `result`, or `cancel`. This subagent only forwards to `task`.

plugins/codex/skills/codex-cli-runtime/SKILL.md

@@ -16,7 +16,7 @@ Execution rules:
 - Prefer the helper over hand-rolled `git`, direct Codex CLI strings, or any other Bash activity.
 - Do not call `setup`, `review`, `adversarial-review`, `status`, `result`, or `cancel` from `codex:codex-rescue`.
 - Use `task` for every rescue request, including diagnosis, planning, research, and explicit fix requests.
-- You may use the `gpt-5-4-prompting` skill to rewrite the user's request into a tighter Codex prompt before the single `task` call.
+- You may use the `gpt-6-prompting` skill to rewrite the user's request into a tighter Codex prompt before the single `task` call.
 - That prompt drafting is the only Claude-side work allowed. Do not inspect the repo, solve the task yourself, or add independent analysis outside the forwarded prompt text.
 - Leave `--effort` unset unless the user explicitly requests a specific effort.
 - Leave model unset by default. Add `--model` only when the user explicitly asks for one.