From 3260efcf914859a9b4c8d7c42210a813b9fa9e39 Mon Sep 17 00:00:00 2001 From: tony Date: Fri, 8 May 2026 14:53:59 +0200 Subject: [PATCH] refactor: rename gpt-5-4-prompting skill to codex-prompting The skill label baked in a specific GPT generation, so it goes stale whenever the underlying model iterates. Codex itself already routes to whatever model the user has configured in ~/.codex/config.toml, so the skill name shouldn't promise a specific generation. - Rename folder + SKILL.md frontmatter: gpt-5-4-prompting -> codex-prompting - Drop "GPT-5.4" mentions from skill body and reference files - Update cross-references in agents/codex-rescue.md and codex-cli-runtime - Replace gpt-5.4-mini examples in README with placeholder - Update test assertions in commands.test.mjs to match --- README.md | 6 +++--- plugins/codex/agents/codex-rescue.md | 6 +++--- plugins/codex/skills/codex-cli-runtime/SKILL.md | 2 +- .../{gpt-5-4-prompting => codex-prompting}/SKILL.md | 8 ++++---- .../references/codex-prompt-antipatterns.md | 2 +- .../references/codex-prompt-recipes.md | 4 ++-- .../references/prompt-blocks.md | 2 +- tests/commands.test.mjs | 12 ++++++------ 8 files changed, 21 insertions(+), 21 deletions(-) rename plugins/codex/skills/{gpt-5-4-prompting => codex-prompting}/SKILL.md (91%) rename plugins/codex/skills/{gpt-5-4-prompting => codex-prompting}/references/codex-prompt-antipatterns.md (96%) rename plugins/codex/skills/{gpt-5-4-prompting => codex-prompting}/references/codex-prompt-recipes.md (95%) rename plugins/codex/skills/{gpt-5-4-prompting => codex-prompting}/references/prompt-blocks.md (98%) diff --git a/README.md b/README.md index 458c39fb..c62ca4a9 100644 --- a/README.md +++ b/README.md @@ -145,7 +145,7 @@ Examples: /codex:rescue investigate why the tests started failing /codex:rescue fix the failing test with the smallest safe patch /codex:rescue --resume apply the top fix from the last run -/codex:rescue --model gpt-5.4-mini --effort medium investigate the flaky integration test +/codex:rescue --model --effort medium investigate the flaky integration test /codex:rescue --model spark fix the issue quickly /codex:rescue --background investigate the regression ``` @@ -255,10 +255,10 @@ The Codex plugin wraps the [Codex app server](https://developers.openai.com/code ### Common Configurations -If you want to change the default reasoning effort or the default model that gets used by the plugin, you can define that inside your user-level or project-level `config.toml`. For example to always use `gpt-5.4-mini` on `high` for a specific project you can add the following to a `.codex/config.toml` file at the root of the directory you started Claude in: +If you want to change the default reasoning effort or the default model that gets used by the plugin, you can define that inside your user-level or project-level `config.toml`. For example to always use a specific model on `high` reasoning effort for a project you can add the following to a `.codex/config.toml` file at the root of the directory you started Claude in: ```toml -model = "gpt-5.4-mini" +model = "" model_reasoning_effort = "high" ``` diff --git a/plugins/codex/agents/codex-rescue.md b/plugins/codex/agents/codex-rescue.md index 7009ec86..1a2726f9 100644 --- a/plugins/codex/agents/codex-rescue.md +++ b/plugins/codex/agents/codex-rescue.md @@ -5,7 +5,7 @@ model: sonnet tools: Bash skills: - codex-cli-runtime - - gpt-5-4-prompting + - codex-prompting --- You are a thin forwarding wrapper around the Codex companion task runtime. @@ -22,14 +22,14 @@ 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 `codex-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`. - Leave `--effort` unset unless the user explicitly requests a specific reasoning effort. - Leave model unset by default. Only add `--model` when the user explicitly asks for a specific model. - If the user asks for `spark`, map that to `--model gpt-5.3-codex-spark`. -- If the user asks for a concrete model name such as `gpt-5.4-mini`, pass it through with `--model`. +- If the user asks for a concrete model name (such as one configured in their `~/.codex/config.toml`), pass it through with `--model`. - Treat `--effort ` and `--model ` as runtime controls and do not include them in the task text you pass through. - Default to a write-capable Codex run by adding `--write` unless the user explicitly asks for read-only behavior or only wants review, diagnosis, or research without edits. - Treat `--resume` and `--fresh` as routing controls and do not include them in the task text you pass through. diff --git a/plugins/codex/skills/codex-cli-runtime/SKILL.md b/plugins/codex/skills/codex-cli-runtime/SKILL.md index 0e91bfb5..e31a5b45 100644 --- a/plugins/codex/skills/codex-cli-runtime/SKILL.md +++ b/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 `codex-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. diff --git a/plugins/codex/skills/gpt-5-4-prompting/SKILL.md b/plugins/codex/skills/codex-prompting/SKILL.md similarity index 91% rename from plugins/codex/skills/gpt-5-4-prompting/SKILL.md rename to plugins/codex/skills/codex-prompting/SKILL.md index 16669d92..10378f39 100644 --- a/plugins/codex/skills/gpt-5-4-prompting/SKILL.md +++ b/plugins/codex/skills/codex-prompting/SKILL.md @@ -1,12 +1,12 @@ --- -name: gpt-5-4-prompting -description: Internal guidance for composing Codex and GPT-5.4 prompts for coding, review, diagnosis, and research tasks inside the Codex Claude Code plugin +name: codex-prompting +description: Internal guidance for composing Codex prompts for coding, review, diagnosis, and research tasks inside the Codex Claude Code plugin user-invocable: false --- -# GPT-5.4 Prompting +# Codex Prompting -Use this skill when `codex:codex-rescue` needs to ask Codex or another GPT-5.4-based workflow for help. +Use this skill when `codex:codex-rescue` needs to ask Codex for help. Prompt Codex like an operator, not a collaborator. Keep prompts compact and block-structured with XML tags. State the task, the output contract, the follow-through defaults, and the small set of extra constraints that matter. diff --git a/plugins/codex/skills/gpt-5-4-prompting/references/codex-prompt-antipatterns.md b/plugins/codex/skills/codex-prompting/references/codex-prompt-antipatterns.md similarity index 96% rename from plugins/codex/skills/gpt-5-4-prompting/references/codex-prompt-antipatterns.md rename to plugins/codex/skills/codex-prompting/references/codex-prompt-antipatterns.md index 10a44d6b..53da9357 100644 --- a/plugins/codex/skills/gpt-5-4-prompting/references/codex-prompt-antipatterns.md +++ b/plugins/codex/skills/codex-prompting/references/codex-prompt-antipatterns.md @@ -1,6 +1,6 @@ # Codex Prompt Anti-Patterns -Avoid these when prompting Codex or GPT-5.4. +Avoid these when prompting Codex. ## Vague task framing diff --git a/plugins/codex/skills/gpt-5-4-prompting/references/codex-prompt-recipes.md b/plugins/codex/skills/codex-prompting/references/codex-prompt-recipes.md similarity index 95% rename from plugins/codex/skills/gpt-5-4-prompting/references/codex-prompt-recipes.md rename to plugins/codex/skills/codex-prompting/references/codex-prompt-recipes.md index 7711de20..91b1de80 100644 --- a/plugins/codex/skills/gpt-5-4-prompting/references/codex-prompt-recipes.md +++ b/plugins/codex/skills/codex-prompting/references/codex-prompt-recipes.md @@ -1,6 +1,6 @@ # Codex Prompt Recipes -Use these as starting templates for Codex task prompts or other Codex/GPT-5.4 prompt construction. +Use these as starting templates for Codex task prompts. Copy the smallest recipe that fits the task, then trim anything you do not need. In `codex:codex-rescue`, run diagnosis and fix-oriented recipes in write mode by default unless the user explicitly asked for read-only behavior. @@ -128,7 +128,7 @@ Prefer primary sources. ```xml -Diagnose why this existing prompt is underperforming and propose the smallest high-leverage changes to improve it for Codex or GPT-5.4. +Diagnose why this existing prompt is underperforming and propose the smallest high-leverage changes to improve it for Codex. diff --git a/plugins/codex/skills/gpt-5-4-prompting/references/prompt-blocks.md b/plugins/codex/skills/codex-prompting/references/prompt-blocks.md similarity index 98% rename from plugins/codex/skills/gpt-5-4-prompting/references/prompt-blocks.md rename to plugins/codex/skills/codex-prompting/references/prompt-blocks.md index cbf66940..76a0f6fd 100644 --- a/plugins/codex/skills/gpt-5-4-prompting/references/prompt-blocks.md +++ b/plugins/codex/skills/codex-prompting/references/prompt-blocks.md @@ -1,6 +1,6 @@ # Prompt Blocks -Use these blocks selectively when composing Codex or GPT-5.4 prompts. +Use these blocks selectively when composing Codex prompts. Wrap each block in the XML tag shown in its heading. ## Core Wrapper diff --git a/tests/commands.test.mjs b/tests/commands.test.mjs index 3724ffa4..209639ad 100644 --- a/tests/commands.test.mjs +++ b/tests/commands.test.mjs @@ -134,15 +134,15 @@ test("rescue command absorbs continue semantics", () => { assert.match(agent, /Leave `--effort` unset unless the user explicitly requests a specific reasoning effort/i); assert.match(agent, /Leave model unset by default/i); assert.match(agent, /If the user asks for `spark`, map that to `--model gpt-5\.3-codex-spark`/i); - assert.match(agent, /If the user asks for a concrete model name such as `gpt-5\.4-mini`, pass it through with `--model`/i); + assert.match(agent, /If the user asks for a concrete model name \(such as one configured in their `~\/\.codex\/config\.toml`\), pass it through with `--model`/i); assert.match(agent, /Return the stdout of the `codex-companion` command exactly as-is/i); assert.match(agent, /If the Bash call fails or Codex cannot be invoked, return nothing/i); - assert.match(agent, /gpt-5-4-prompting/); + assert.match(agent, /codex-prompting/); assert.match(agent, /only to tighten the user's request into a better Codex prompt/i); assert.match(agent, /Do not use that skill to inspect the repository, reason through the problem yourself, draft a solution, or do any independent work/i); assert.match(runtimeSkill, /only job is to invoke `task` once and return that stdout unchanged/i); assert.match(runtimeSkill, /Do not call `setup`, `review`, `adversarial-review`, `status`, `result`, or `cancel`/i); - assert.match(runtimeSkill, /use the `gpt-5-4-prompting` skill to rewrite the user's request into a tighter Codex prompt/i); + assert.match(runtimeSkill, /use the `codex-prompting` skill to rewrite the user's request into a tighter Codex prompt/i); assert.match(runtimeSkill, /That prompt drafting is the only Claude-side work allowed/i); assert.match(runtimeSkill, /Leave `--effort` unset unless the user explicitly requests a specific effort/i); assert.match(runtimeSkill, /Leave model unset by default/i); @@ -154,7 +154,7 @@ test("rescue command absorbs continue semantics", () => { assert.match(runtimeSkill, /If the Bash call fails or Codex cannot be invoked, return nothing/i); assert.match(readme, /`codex:codex-rescue` subagent/i); assert.match(readme, /if you do not pass `--model` or `--effort`, Codex chooses its own defaults/i); - assert.match(readme, /--model gpt-5\.4-mini --effort medium/i); + assert.match(readme, /--model --effort medium/i); assert.match(readme, /`spark`, the plugin maps that to `gpt-5\.3-codex-spark`/i); assert.match(readme, /continue a previous Codex task/i); assert.match(readme, /### `\/codex:setup`/); @@ -183,8 +183,8 @@ test("result and cancel commands are exposed as deterministic runtime entrypoint test("internal docs use task terminology for rescue runs", () => { const runtimeSkill = read("skills/codex-cli-runtime/SKILL.md"); - const promptingSkill = read("skills/gpt-5-4-prompting/SKILL.md"); - const promptRecipes = read("skills/gpt-5-4-prompting/references/codex-prompt-recipes.md"); + const promptingSkill = read("skills/codex-prompting/SKILL.md"); + const promptRecipes = read("skills/codex-prompting/references/codex-prompt-recipes.md"); assert.match(runtimeSkill, /codex-companion\.mjs" task ""/); assert.match(runtimeSkill, /Use `task` for every rescue request/i);