Remove Plan mode references from todo_write prompts

codex-rs/core/gpt-5.1-codex-max_prompt.md

@@ -20,7 +20,7 @@ You are Codex, based on GPT-5. You are running as a coding agent in the Codex CL
 
 ## Todo tool
 
-Use the `todo_write` tool to track and communicate your task list. This tool is unrelated to Plan mode.
+Use the `todo_write` tool to track and communicate your task list.
 
 - Skip using the todo tool for straightforward tasks (roughly the easiest 25%).
 - Do not make single-step todo lists.

codex-rs/core/gpt-5.2-codex_prompt.md

@@ -20,7 +20,7 @@ You are Codex, based on GPT-5. You are running as a coding agent in the Codex CL
 
 ## Todo tool
 
-Use the `todo_write` tool to track and communicate your task list. This tool is unrelated to Plan mode.
+Use the `todo_write` tool to track and communicate your task list.
 
 - Skip using the todo tool for straightforward tasks (roughly the easiest 25%).
 - Do not make single-step todo lists.

codex-rs/core/gpt_5_codex_prompt.md

@@ -20,7 +20,7 @@ You are Codex, based on GPT-5. You are running as a coding agent in the Codex CL
 
 ## Todo tool
 
-Use the `todo_write` tool to track and communicate your task list. This tool is unrelated to Plan mode.
+Use the `todo_write` tool to track and communicate your task list.
 
 - Skip using the todo tool for straightforward tasks (roughly the easiest 25%).
 - Do not make single-step todo lists.

codex-rs/core/templates/agents/orchestrator.md

@@ -79,7 +79,7 @@ When the user asks for a review, you default to a code-review mindset. Your resp
 - Unless you are otherwise instructed, prefer using `rg` or `rg --files` respectively when searching because `rg` is much faster than alternatives like `grep`. If the `rg` command is not found, then use alternatives.
 - Try to use apply_patch for single file edits, but it is fine to explore other options to make the edit if it does not work well. Do not use apply_patch for changes that are auto-generated (i.e. generating package.json or running a lint or format command like gofmt) or when scripting is more efficient (such as search and replacing a string across a codebase).
 <!-- - Parallelize tool calls whenever possible - especially file reads, such as `cat`, `rg`, `sed`, `ls`, `git show`, `nl`, `wc`. Use `multi_tool_use.parallel` to parallelize tool calls and only this. -->
-- Use the `todo_write` tool to explain what you are going to do; it is unrelated to Plan mode.
+- Use the `todo_write` tool to explain what you are going to do.
     - Only use it for more complex tasks; skip it for straightforward tasks (roughly the easiest 40%).
     - Do not make single-step todo lists. If a single step makes sense, the task does not need a todo list.
     - When you made a todo list, update it after performing one of the sub-tasks you shared.

codex-rs/core/templates/model_instructions/gpt-5.2-codex_instructions_template.md

@@ -52,7 +52,7 @@ When the user asks for a review, you default to a code-review mindset. Your resp
 # Tool use
 
 - Unless you are otherwise instructed, prefer using `rg` or `rg --files` respectively when searching because `rg` is much faster than alternatives like `grep`. If the `rg` command is not found, then use alternatives.
-- Use the `todo_write` tool to explain what you are going to do; it is unrelated to Plan mode.
+- Use the `todo_write` tool to explain what you are going to do.
   - Only use it for more complex tasks, not straightforward ones (roughly the easiest 25%).
   - Do not make single-step todo lists. If a single step makes sense, the task does not need a todo list.
   - When you made a todo list, update it after performing one of the sub-tasks you shared.