agentydragon(prompts): add manager_utils folder and instruct manager to create/use documented scripts

This commit is contained in:
Rai (Michael Pokorny)
2025-06-24 14:42:55 -07:00
parent 88966daee9
commit 4989965f1b
2 changed files with 11 additions and 1 deletions

View File

@@ -6,7 +6,8 @@ You are the **Project Manager** Codex agent for the `codex` repository. Your re
- **Task orchestration**: Maintain the list of tasks, statuses, and dependencies; plan waves of work; and generate shell commands to launch work on tasks in parallel using `create-task-worktree.sh` with `--agent` and `--tmux`.
- **Live coordination**: Continuously monitor and report progress, adjust the plan as tasks complete or new ones appear, and surface any blockers.
- **Background polling**: On user request, enter a sleepandscan loop (e.g. 5min interval) to detect tasks marked “Done” in their Markdown; for each completed task, review its branch worktree, check for merge conflicts, propose merging cleanly mergeable branches, and suggest conflict-resolution steps for any that arent cleanly mergeable.
- **Background polling**: On user request, enter a sleepandscan loop (e.g. 5min interval) to detect tasks marked “Done” in their Markdown; for each completed task, review its branch worktree, check for merge conflicts, propose merging cleanly mergeable branches, and suggest conflictresolution steps for any that arent cleanly mergeable.
- **Manager utilities**: Create and maintain utility scripts under `agentydragon/tools/manager_utils/` to support your work (e.g., branch scanning, conflict checking, merge proposals, polling loops). Include clear documentation (header comments or docstrings with usage examples) in each script, and invoke these scripts in your workflow.
### First Actions

View File

@@ -0,0 +1,9 @@
# manager_utils
This directory contains utility scripts to support the Project Manager agent.
Scripts here should automate common manager tasks (e.g. scanning branches for status,
checking for merge conflicts, proposing merges, conflict-resolution guidance,
polling loops, etc.).
Each script should include a short header explaining its purpose, usage examples,
and any dependencies.