Mission control recovery plan
Skill MN755/Codex-Mission_Control/plugins/mission-control/skills/mission-control-recovery-plan
Ask Mission Control Manager for recovery guidance after a failure. Use when the user wants a failure summary, likely causes, recovery options, recommendation, and risks without losing the orchestration context.From its SKILL.md
npx -y skills add MN755/Codex-Mission_Control --skill mission-control-recovery-planAssembled 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.
SKILL.md
2.0 KB, 356 tokens by cl100k_base, as published. Nobody here has run it
Mission Control Recovery Plan
Purpose
Request a structured recovery plan from Mission Control after failure or uncertainty.
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 run failed or stalled.
- The user asks for recovery options.
- Status and diagnostics show unresolved blockers.
Workflow
- Review status, diagnostics, and event digest.
- Call
mission_control_request_recovery_planwhen available. - Return the failure summary, possible causes, recovery options, recommended option, and risks.
- If the user chooses an option, relay it through the approval flow.
Mission Control calls
Tools:
mission_control_request_recovery_planmission_control_get_statusmission_control_get_event_digest
Resources:
mission-control://projects/{project_id}/statusmission-control://projects/{project_id}/diagnosticsmission-control://projects/{project_id}/pending-decisions
User-facing output
- Show failure summary, causes, options, recommendation, and risks in plain language.
- Make it obvious which options require approval or broader scope changes.
Approval behavior
Recovery choices that restart work, relax safety controls, or widen scope must stay behind explicit user decisions.
Never do
- Do not turn a recommendation into an action automatically.
- Do not hide uncertainty.
- Do not discard current evidence while discussing recovery.
Failure and fallback
If the dedicated recovery-plan tool is absent, synthesize the same structure from status, diagnostics, and event resources and label it as a best-effort summary.
Example invocation
Ask Mission Control Manager for a recovery plan for the failed run.
What ships with it: 1 file
152 B alongside SKILL.md
agents/
- openai.yaml152 B