# Design Control Loop

Interview the user to design an agentic control loop (sensor, controller, actuator...

- Repository: https://github.com/humanlayer/skills (5529 stars)
- Category: Design
- License: MIT
- Last updated: 2026-11-01
- Runs scripts: yes, review before use

## Install

Claude Code: `npx skills add humanlayer/skills --skill design-control-loop -g -a claude-code -y`
Codex: `npx skills add humanlayer/skills --skill design-control-loop -g -a codex -y`
Cursor: `npx skills add humanlayer/skills --skill design-control-loop -g -a cursor -y`
Gemini CLI: `npx skills add humanlayer/skills --skill design-control-loop -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add humanlayer/skills`

## Description

interview the user to design an agentic control loop (sensor, controller, actuator under disturbances) tailored to their codebase, then build it as locally-runnable components plus a scheduled coding-agent workflow

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Design Control Loop

Use this skill when a user wants to drive some property of their codebase toward a target with small, low-risk, reviewable changes on a schedule, an **agentic control loop**.

Your job is to **interview the user, design the loop _with_ them, and then build it for them**. The design must be tailored to *their* codebase and the tooling they already use. There is no fixed toolset and no template to reproduce: propose options grounded in what you find in the repo, discuss trade-offs, agree on a design, then implement it.

## The mental model

Borrow from control theory. The codebase is a dynamic system being changed continuously (by teammates, dependencies, and generated code, the **disturbances**). A control loop drives it toward a desired state instead of all at once:

- **Set point**, the desired end state for some property of the codebase.
- **Sensor**, measures the current state, producing the gap to the set point.
- **Controller**, decides the next small, low-risk change from that measurement.
- **Actuator**, a coding agent that applies the change and opens a PR.
- The result feeds back into the next run. A human stays *on* the loop to steer it.

Read `references/control-loop-taxonomy.md` and walk the user through these concepts before designing anything. For one fully worked example, see `references/example-control-loop.md`, treat it as an illustration, not a blueprint.

## How to run this skill

The rest: https://github.com/humanlayer/skills/blob/HEAD/plugins/design-control-loop/skills/design-control-loop/SKILL.md