Mission control swarm
An Open Source Platform For Building Projects With OpenAI's Codex, Claude CLI, And Other Coding LLMs Using Multi-Agent Swarms And Customizable Workflows. Runs On Windows, MacOS, And Linux.
npx -y skills add MN755/Codex-Mission_Control --skill mission-control-swarmAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Inspect or adjust Mission Control swarm behavior. Use when the user wants to show the swarm plan, explain agent roles, scale up or down, change strategy, pause dynamic spawning, resume dynamic spawning, or inspect active agents.
SKILL.md
2.2 KB, as published. Nobody here has run it
Mission Control Swarm
Purpose
Inspect the swarm plan and route any swarm changes through Mission Control.
The Codex chat agent is not the Mission Control Manager. It is the bridge between the user and the Mission Control Manager.
Use when
- The user asks how the swarm is organized.
- The user wants to scale up, scale down, or switch swarm strategy.
- Agent activity needs a coordinated explanation.
Workflow
- Read the swarm plan and active agents resources.
- Explain current swarm shape, role assignments, ownership boundaries, and approvals.
- If the user requests a change, route it through Mission Control tools or prompts.
- Require explicit approval before scaling above the configured threshold or changing risk posture.
Mission Control calls
Tools:
mission_control_get_statusmission_control_start_task(for swarm-change requests)mission_control_pauseandmission_control_resumewhen pausing or resuming swarm activity is supported
Resources:
mission-control://projects/{project_id}/swarm-planmission-control://projects/{project_id}/agentsmission-control://projects/{project_id}/pending-decisions
User-facing output
- Show swarm plan, active agents, ownership boundaries, approval state, and any scaling warnings.
- If change is requested, explain what Mission Control will need from the user next.
Approval behavior
Never scale above threshold, broaden write scope, or change dynamic spawning policy without user approval or an explicit Mission Control approval record.
Never do
- Do not invent your own swarm topology.
- Do not spawn workers outside Mission Control.
- Do not bypass swarm approvals.
Failure and fallback
If direct swarm controls are not exposed yet, explain the current swarm from resources and treat any adjustment as an expected or future Mission Control task request.
Example invocation
Show the swarm plan and explain whether we should scale up.