Coordinate subagents, separate agents assigned tasks, to pursue a long-running goal in one session. Maintain dialogue with the user while improving working conditions, shared rules, and access to information needed for future tasks.
Pursue a long-running goal in a single session by co-ordinating subagents.
Pursue a long-running goal within one session by coordinating subagents responsible for individual tasks. This skill acts as a coordinator with two concerns: advancing the immediate task and improving the environment so the next task is easier to carry out. Background agents handle the work while dialogue with the user continues.
Use it when a goal involves a continuing series of tasks and you want coordination of responsibilities and ongoing decisions. Information is shared through references to research notes and previous commits, reducing repeated explanations. It also helps review the conditions needed for sustained work, including shared conventions and access to relevant data.
Possible improvements include rules that catch errors, CODING_STANDARDS.md, and access to logs or data in test environments. These support future tasks as well as the current work.
The user must explicitly invoke this skill. It requires an execution environment that supports subagents. Recurring schedules are suggested when the execution environment supports them.
This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.
AI rated this skill on four points using only the contents of its SKILL.md. Stars and popularity are not taken into account.
The total counts each point as A = 25, B = 15, C = 5. Rated by AI (OpenAI Codex) as of Oct 19, 2026. Treat it as a guide and read the original before installing.
Review the instructions the agent will receive before you install.
You are a chief of staff, co-ordinating subagents and schedules to pursue a long-running goal. This session will run for a long time, accruing tribal knowledge and helping you make long-term strategic decisions.
You are the Directly Responsible Individual for this goal. You are empowered to think much longer-term than you're used to. You must think on two tracks simultaneously:
Harness-permitting, you will suggest recurring schedules which can help in achieving the goal.
All work should be done in subagents. Protect your context window.
Use background agents so you can stay in active dialogue with the user.
Communication to and from subagents should be sparse. Communicate primarily through context pointers: research notes, previous commits, and others. Don't duplicate information already available via pointers.
As part of any and all work, FIRST consider how the environment the agents operate in might be improved. Agents thrive in the pit of success:
They also need relevant data sources to succeed:
Finally, create environments (and codebases) that obey the "no workarounds" rule:
Be relentless in improving the environment. Use every user message as an excuse to search for these improvements.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Choose which related skill to use and in what order for planning, building, debugging, or maintaining software. It explains routes through the available workflows and helps select the next step based on your situation and project size.
Summarize an ongoing conversation and launch a fresh background agent to continue the work. The handoff includes the next focus, references to existing documents, and suggested skills, with sensitive information removed.
Review code changes from a chosen Git reference against two separate criteria: documented coding standards and the original requirements. Independent reviewers check each criterion, then present findings separately so convention problems and requirement gaps remain visible.
Design modules that offer substantial behavior through a small interface, the rules callers must understand. Use shared design terms to simplify usage, contain complexity, choose where implementations can vary, and make behavior easier to test.
Investigate difficult bugs and performance slowdowns by building a repeatable test or script that detects the exact symptom. Reduce the failing case, compare possible causes, and verify the fix with checks that catch the bug if it returns.
Clarify a project's business concepts and terminology through concrete scenarios and comparisons with code. Record agreed definitions in a glossary and document significant design trade-offs in ADRs, records explaining why a decision was made.