JakeSelby

Model Citizen — AI skill for Claude Code

AI community

The control plane for your coding agents, however you run them.

How to install Model Citizen

This entry records only its repository, not the path inside it, so there is no exact command to give. Open JakeSelby/model-citizen and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Model Citizen does

The control plane for your coding agents, however you run them. One checkout of rules, skills, subagents, hooks and stances, projected into Claude Code and Codex with your own primitives: hook-enforced guardrails, usage telemetry, cost postures and model tiering, under any rules library or orchestration layer.

Alternatives in AI

Pi Agent VS OpenCode — Customization & Control Comparison — Pi v0.52+ vs OpenCode v1.1+ (Feb 2026) Thesis: Pi and OpenCode are both MIT-licensed, open-source, model-agnos 526 ★
Claudexor — Multi-harness control plane for Claude Code, Codex, Cursor, and OpenCode: quota-aware rotation across multiple 425 ★
HarnessKit — More than a skill manager — manage skills, MCP servers, plugins, hooks, CLIs, configs, memory & rules across e 416 ★

README

Model Citizen

Formerly Agent Harness.

[![CI](https://github.com/JakeSelby/agent-harness/actions/workflows/ci.yml/badge.svg)](https://github.com/JakeSelby/agent-harness/actions/workflows/ci.yml) [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE) [![PRs welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](CONTRIBUTING.md) [![Reference](https://img.shields.io/badge/reference-agent--harness.jakeselby.com-d97706.svg)](https://agent-harness.jakeselby.com) ![CodeRabbit Pull Request Reviews](https://img.shields.io/coderabbit/prs/github/JakeSelby/agent-harness?utm_source=oss&utm_medium=github&utm_campaign=JakeSelby%2Fagent-harness&labelColor=171717&color=FF570A&link=https%3A%2F%2Fcoderabbit.ai&label=CodeRabbit+Reviews)

The control plane for your coding agents, however you run them.

![Terminal output of `bin/citizen sync --dry-run` on a fresh home: the resolved personal stances, then every link, rendered file and setting the sync would create for Claude Code and Codex, ending in "sync complete". Nothing is written.](docs/assets/sync-dry-run.svg)

Model Citizen is the layer under your coding agents. You write your rules, skills, roles and stances once, as your own primitives. The harness projects them into Claude Code and Codex, enforces them with hooks, and keeps a ledger of what every session did and spent. It sits under whatever rules library you like and whatever orchestration you run, so you can change how your agents work without changing how you run them.

Every file it touches goes in an ownership journal, and uninstall puts things back. The same ledger exports over OTLP to Langfuse, Phoenix or Opik, off by default.

Model Citizen is not an LLM API gateway, a model provider or a replacement agent runtime. Claude Code and Codex remain responsible for m