agentsclimarketplace

Mission control approve

Skill MN755/Codex-Mission_Control/.codex/skills/mission-control-approve

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-approve

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

Relay Mission Control approvals and questions to the user. Use when there are pending command approvals, tool approvals, write permissions, Manager questions, swarm approvals, recovery decisions, or handoff review gates.

SKILL.md

2.2 KB, 402 tokens by cl100k_base, as published. Nobody here has run it

Mission Control Approve

Purpose

Present pending Mission Control decisions clearly and relay the user response back safely.

The Codex chat agent is not the Mission Control Manager. It is the bridge between the user and the Mission Control Manager.

Use when

  • A pending decision blocks progress.
  • The user asks what needs approval.
  • Mission Control is waiting on user input.

Workflow

  1. Fetch pending decisions with mission_control_get_pending_decisions or the pending-decisions resource.
  2. Render the top decision with reason, risk, options, and any relevant scope.
  3. Ask the user to choose when no answer is provided.
  4. Call mission_control_answer_decision with the selected answer.
  5. Confirm the updated status.

Mission Control calls

Tools:

  • mission_control_get_pending_decisions
  • mission_control_answer_decision

Resources:

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

User-facing output

  • Identify the decision type: command approval, tool approval, write permission, Manager question, swarm approval, snapshot approval, handoff review, recovery decision, or scope change decision.
  • Explain the risk and the likely impact of each option.
  • Confirm whether the decision was accepted, denied, deferred, or still pending.

Approval behavior

This skill exists to preserve approvals. Never auto-answer a pending decision unless Mission Control explicitly marks it safe and the user already delegated that choice.

Never do

  • Do not answer on the user's behalf.
  • Do not hide the risk level.
  • Do not bypass write-permission or swarm approval gates.

Failure and fallback

If decision-answer tooling is unavailable, present the pending decision textually and tell the user that manual resolution through the expected tool is still required.

Example invocation

Show me the pending Mission Control approval and let me choose.

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.