Mission control runnable chain design

Skill MN755/Codex-Mission_Control/.codex/plugins/mission-control/skills/mission-control-runnable-chain-design

Design LangChain-style runnable chains, model pipelines, and composable agent steps inside Mission Control without requiring LangChain as a runtime dependency.From its SKILL.md

Install

npx -y skills add MN755/Codex-Mission_Control --skill mission-control-runnable-chain-design

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, 336 tokens by cl100k_base, as published. Nobody here has run it

Mission Control Runnable Chain Design

Purpose

Apply composable chain design patterns to Mission Control workflows while keeping the runtime provider-agnostic.

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 wants an LLM pipeline or agent workflow designed.
A task needs staged prompt, tool, validation, and handoff steps.
Provider interchangeability matters.

Workflow

Ask Mission Control to identify inputs, model calls, tools, transforms, validators, and outputs.
Model the workflow as composable steps with explicit contracts.
Define retry, fallback, and human-approval boundaries.
Recommend implementation in Mission Control primitives or external frameworks only when useful.

Mission Control calls

Tools:

mission_control_start_task
mission_control_get_status

Resources:

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

User-facing output

Provide chain stages, inputs/outputs, tools, error handling, and validation checkpoints.

Approval behavior

Ask before adding new external services or write-capable tools.

Never do

Do not force LangChain where Mission Control primitives are enough.
Do not hide state or retry behavior.
Do not make model outputs look executable without validation.

Failure and fallback

If implementation details are unknown, return an architecture sketch and questions.

Example invocation

Use Mission Control to design a provider-agnostic chain for triaging issues.

What ships with it

Read from the repository

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