Mission control agent graph workflows

Skill MN755/Codex-Mission_Control/.codex/plugins/mission-control/skills/mission-control-agent-graph-workflows

Design graph-style agent workflows with nodes, edges, gates, retries, checkpoints, and human approvals through Mission Control.From its SKILL.md

Install

npx -y skills add MN755/Codex-Mission_Control --skill mission-control-agent-graph-workflows

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

1.8 KB, 338 tokens by cl100k_base, as published. Nobody here has run it

Mission Control Agent Graph Workflows

Purpose

Model complex agent work as controllable graph workflows instead of linear hope with extra steps.

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 task needs branching, retries, approval gates, or subagents.
The user wants a workflow diagram or execution plan.
Failure handling and resumability matter.

Workflow

Ask Mission Control to define workflow nodes, edges, inputs, outputs, and gates.
Identify deterministic steps, model steps, tool steps, human approvals, and checkpoints.
Define retry and fallback behavior for each failure class.
Summarize the graph and execute only through Mission Control approvals.

Mission Control calls

Tools:

mission_control_start_task
mission_control_get_status

Resources:

mission-control://projects/{project_id}/swarm-plan
mission-control://projects/{project_id}/agent-contracts
mission-control://projects/{project_id}/decision-ledger

User-facing output

Provide nodes, edges, gates, retries, checkpoints, and current execution state.

Approval behavior

Ask before increasing agent count, adding tools, or executing risky branches.

Never do

Do not spawn parallel work outside Mission Control.
Do not hide approval gates.
Do not let graph complexity outrun the task.

Failure and fallback

If graph execution is overkill, recommend a simpler linear workflow and say why.

Example invocation

Use Mission Control to design a graph workflow for release validation and rollback.

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 338 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

ask mission control to define workflow components
identify deterministic, model, tool, approval, and checkpoint steps
define retry and fallback behavior per failure class
summarize the graph and execute through mission control approvals
ask before increasing agent count
ask before adding tools

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.