Claude Code usage
Model Citizen
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.
Install
/plugin marketplace add JakeSelby/model-citizenFound in the project README. Check it for setup steps after installing.
git clone https://github.com/JakeSelby/model-citizen.gitFrom the README
Model Citizen The control plane for your coding agents, however you run them. 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 model access, native permissions and client behavior. What it does for you The same six groups are held as data in product.json, so this list, the reference site and the GitHub description cannot drift apart. Guardrails that leave room for judgment Hooks handle the few things that should be deterministic, and each has an id you can switch off; the four that enforce need your acknowledgement first. Everything else stays the agent's call. - Graded shell commands: Every command is graded read-only to irreversible, your autonomy stance decides which grades ask, a risky one is snapshotted first, and an opt-in OS sandbox fences it. - Stop gate: The turn doesn't end while your repo's own gate is red. - Fresh-context review: Scope is checked against the ask, then quality, by agents that never saw the code, and a framework's own review spawns are held to that whatever they call themselves. - Secrets and personal data: Lint catches tokens, keys and personal strings before they're…
Details
- Repository
- JakeSelby/model-citizen
- Website
- model-citizen.dev
- Language
- Python
- License
- MIT
- Last updated
- 19 November 2026
- Topics
- agent-harnessagent-skillsagentic-aiagentic-codingagents-mdai-agentsai-coding-agentclaude-codeclaude-code-hooksclaude-code-pluginclaude-code-rulesclaude-skills
FAQ
What is Model Citizen?
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. It is a usage for Claude Code, from JakeSelby/model-citizen on GitHub.
How do I install Model Citizen?
Run /plugin marketplace add JakeSelby/model-citizen inside Claude Code, then follow the setup in the README.
Is Model Citizen popular?
JakeSelby/model-citizen has 25 GitHub stars and 5 forks. It was last updated on 19 November 2026.
More usage & cost trackers
Retok
33d-date/retok
Token-efficiency analyzer for AI coding agents (Claude Code, OpenAI Codex CLI): cost estimates, cache analysis, and savings advice. Zero dependencies.
CC Budget
29boyand/cc-budget
Budget intelligence for Claude Code — pacing targets, per-prompt cost, peak/off-peak awareness, and threshold warnings.
Checkyouragent
26TarekAwwad/checkyouragent
An analytics tool to explore Claude code usage patterns, errors, and token costs
Llm Usage Dashboard
27iangithub/llm-usage-dashboard
一次看到 Codex (OpenAI) 與 Claude Code (Anthropic) 的訂閱用量、額度與花費的本機桌面儀表板。安裝: npx llm-usage-dashboard
Golden Thread
27shaven/golden-thread
Cuts Claude Code token cost: handoffs to fresh sessions (20–66% lower cost, 8 test runs) and LOTR, which keeps your MCPs from eating your tokens (measured on 9 bulk reads: median 74% less context growth, 45–94% on 8 of 9). Plus shared markdown memory and hook-enforced rules. MIT.
Budi
26siropkin/budi
Local-first cost analytics for AI coding agents. See where your tokens and money go across Claude Code, Cursor, and more.
Browse the most popular Claude Code mods, all usage & cost trackers, or the skills and MCP server directories.