agentsclimarketplace

Mission control debug

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

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-debug

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

Diagnose stuck or failed Mission Control orchestration. Use when runs are blocked, failing repeatedly, waiting too long, missing evidence, or unclear about the next recovery step.

SKILL.md

2.0 KB, 382 tokens by cl100k_base, as published. Nobody here has run it

Mission Control Debug

Purpose

Diagnose stuck or failed orchestration and surface recovery options.

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 says the run is stuck or broken.
  • Status looks stalled.
  • Approvals, diagnostics, or event summaries need to be correlated.

Workflow

  1. Fetch status with mission_control_get_status.
  2. Fetch pending decisions with mission_control_get_pending_decisions.
  3. Fetch diagnostics and recent event digest.
  4. Ask Mission Control for a recovery plan if available.
  5. Summarize blocker, likely causes, and next options.

Mission Control calls

Tools:

  • mission_control_get_status
  • mission_control_get_pending_decisions
  • mission_control_get_event_digest
  • mission_control_request_recovery_plan

Resources:

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

User-facing output

  • State the main blocker, supporting evidence, pending approvals, and recommended next options.
  • Keep diagnostics summarized; do not paste raw logs by default.

Approval behavior

If recovery choices may retry commands, widen scope, or restart work, relay the decision to the user before acting.

Never do

  • Do not freehand a recovery action that Mission Control has not approved.
  • Do not dump raw logs or secrets.
  • Do not say the system is healthy when diagnostics disagree.

Failure and fallback

If recovery tooling is missing, summarize the failure from status, diagnostics, and events, and clearly mark recovery-plan tooling as expected or future.

Example invocation

Mission Control looks stuck. Diagnose it and show my options.

What ships with it: 1 file

127 B alongside SKILL.md

agents/

Keep looking

Skills are one crate of 327,132. 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.