Mission control restore plan

Skill MN755/Codex-Mission_Control/plugins/mission-control/skills/mission-control-restore-plan

Generate a rollback or restore plan from Mission Control state. Use when the user wants to know what would be reverted, what evidence would be preserved, and which destructive steps would still need approval before any restore action.From its SKILL.md

Install

npx -y skills add MN755/Codex-Mission_Control --skill mission-control-restore-plan

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.

SKILL.md

1.9 KB, 353 tokens by cl100k_base, as published. Nobody here has run it

Mission Control Restore Plan

Purpose

Describe how rollback would work without executing it.

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 to roll back safely.
A risky change needs a restore plan.
Recovery decisions need a concrete revert outline.

Workflow

Review snapshot, handoff, and status state.
Ask Mission Control for a restore or rollback plan if available.
Summarize what would be reverted, what would remain, and which steps would need approval.
Do not execute the restore in this skill.

Mission Control calls

Tools:

mission_control_request_snapshot
mission_control_request_recovery_plan
mission_control_get_status

Resources:

mission-control://projects/{project_id}/handoff
mission-control://projects/{project_id}/status
mission-control://projects/{project_id}/decision-ledger

User-facing output

Explain the rollback target, affected files or milestones, evidence preservation, and approval gates for destructive steps.
Keep it actionable enough for the user to decide.

Approval behavior

Any actual restore or revert remains behind explicit approval. This skill only prepares the plan.

Never do

Do not execute restore steps.
Do not understate destructive impact.
Do not claim rollback coverage for unsnapshotted work.

Failure and fallback

If no restore-plan tool exists, build the plan from snapshot availability, handoff evidence, and current status, and mark the dedicated tool as expected or future.

Example invocation

Generate a restore plan in case the current change set goes bad.

What ships with it: 1 file

120 B alongside SKILL.md

agents/

openai.yaml120 B

Gives 0 of the 12 instructions most plan spec skills give in 353 tokens

Counted across 1,099 of the 1,860 authors here whose files we hold, read 2026-08-07

Ask one question at a timein 51 of 1099
Break plans into vertical slicesin 29 of 1099, across 11 files
Publish issues in dependency orderin 27 of 1099, across 9 files
Iterate until user approves the breakdownin 25 of 1099, across 7 files
Explore the repository to understand the codebase statein 24 of 1099, across 7 files
Use domain glossary vocabularyin 23 of 1099, across 5 files
Apply correct triage labels to published issuesin 23 of 1099, across 5 files
Prefer AFK slices over HITLin 22 of 1099, across 7 files
Write a specification before writing any codein 22 of 1099, across 14 files
Write failing tests before implementation codein 22 of 1099, across 20 files
Ask clarifying questions until requirements are concretein 21 of 1099, across 13 files
Respect existing architecture decision recordsin 20 of 1099, across 5 files

Said here and by no other author read

review snapshot handoff and status state
request recovery plan from mission control
summarize reverts remaining steps and approval gates
explain rollback target and affected files
explain evidence preservation and approval gates
keep output actionable for user decision

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.