agentsclimarketplace

Mission control tool policy

Skill MN755/Codex-Mission_Control/apps/mcp-server/src/mission_control_mcp_server/_bundled/skills/mission-control-tool-policy

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.

Install
npx -y skills add MN755/Codex-Mission_Control --skill mission-control-tool-policy

Assembled 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 update Mission Control tool-routing and permission policy. Use when the user wants to see allowed tools, blocked tools, approval-required tools, or per-agent archetype tool constraints.

SKILL.md

1.9 KB, as published. Nobody here has run it

Mission Control Tool Policy

Purpose

Explain or request tool-policy changes without bypassing the policy itself.

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 which tools are allowed.
  • Approval-required tools need explanation.
  • A policy change is needed for a task.

Workflow

  1. Review current status and any tool-policy or approval state that Mission Control exposes.
  2. Summarize allowed, blocked, and approval-required tools plus any archetype-specific constraints.
  3. Route requested policy changes back through Mission Control rather than mutating them directly in chat.

Mission Control calls

Tools:

  • mission_control_get_status
  • mission_control_start_task

Resources:

  • mission-control://projects/{project_id}/status
  • mission-control://projects/{project_id}/pending-decisions

User-facing output

  • Show the effective tool policy, notable restrictions, and what the user would need to approve to loosen it.
  • Keep the summary bridge-safe rather than dumping backend config.

Approval behavior

Tool-policy changes are explicit policy decisions and should be confirmed with the user before they are requested.

Never do

  • Do not override the tool policy from chat.
  • Do not blur approval-required and fully allowed tools.
  • Do not claim blocked tools are available.

Failure and fallback

If dedicated tool-policy state is not exposed, infer current policy from pending approvals and known Mission Control controls, and label that inference clearly.

Example invocation

Show the Mission Control tool policy for this project.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.