Mission control subagent burst

Skill MN755/Codex-Mission_Control/.codex/plugins/mission-control/skills/mission-control-subagent-burst

Recommend or review Mission Control Codex subagent bursts for bounded read-heavy work. Use when the user wants parallel exploration, review, planning, handoff audit, or failure diagnosis without replacing the normal worker system.From its SKILL.md

Install

npx -y skills add MN755/Codex-Mission_Control --skill mission-control-subagent-burst

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

2.4 KB, 474 tokens by cl100k_base, as published. Nobody here has run it

Mission Control Subagent Burst

Purpose

Route short-lived Codex subagent burst recommendations through Mission Control.

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 task is read-heavy and parallelizable.
The user wants bounded parallel exploration or review.
Mission Control should recommend whether a burst is worth it.

Workflow

Check status and current orchestration context.
Fetch subagent policy.
Ask Mission Control to recommend a burst for the current task.
If a pending decision is created, render it in Codex chat and wait for the user.
After approval, fetch the batch and present spawn instructions or manual prompt text.
When results come back, send them to Mission Control result ingestion.

Mission Control calls

Tools:

mission_control_get_status

Daemon/API:

GET /api/subagent-policy
POST /api/projects/{project_id}/subagent-bursts/recommend
GET /api/projects/{project_id}/subagent-batches
GET /api/subagents/batches/{batch_id}
POST /api/subagents/batches/{batch_id}/results
GET /api/decisions/{decision_id}/bridge-message
POST /api/decisions/{decision_id}/answer

Resources:

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

User-facing output

Explain whether Mission Control recommends a burst.
Show purpose, count, risk, intensity, and the proposed subagent list.
If approved, show spawn instructions and expected report format.

Approval behavior

Never bypass a subagent_burst_approval pending decision. Larger bursts must be answered by the user in Codex chat.

Never do

Do not replace the normal Mission Control worker system.
Do not default to file edits or commands.
Do not recursively fan out more agents.

Failure and fallback

If burst planning is unavailable, say so clearly and fall back to normal Mission Control planning or status-only guidance.

Example invocation

Ask Mission Control whether a read-only subagent burst makes sense for this repo review.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most context ai engineering skills give in 474 tokens

Counted across 1,193 of the 1,976 authors here whose files we hold, read 2026-08-07

Dispatch a fresh implementer subagent per taskin 48 of 1193, across 19 files
Dispatch a final code reviewer after all tasksin 33 of 1193, across 8 files
Provide full task text to the subagentin 30 of 1193, across 9 files
Review spec compliance before code qualityin 27 of 1193, across 10 files
Make the hook script executablein 26 of 1193, across 8 files
Re-snapshot after navigation or DOM changesin 25 of 1193, across 19 files
Read files before editing themin 22 of 1193, across 11 files
Answer subagent questions before proceedingin 22 of 1193, across 7 files
Mark task complete in TodoWrite after approvalin 22 of 1193, across 6 files
Merge hook into existing settingsin 21 of 1193, across 3 files
Ask if installation is global or projectin 20 of 1193, across 2 files
Copy the hook script to target locationin 20 of 1193, across 2 files

Said here and by no other author read

fetch subagent policy
ask Mission Control to recommend a burst
render pending decisions and await user input
send returned results to Mission Control result ingestion

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.