design-model

design-model is a command for coding agents from authzed/authzed-marketplace. It costs 12 tokens per session (1,755 once invoked), scanned A, original, Apache-2.0.

An interactive guide for designing SpiceDB permission models, which define who can access which resources and what they can do. It examines existing application models and produces a structured schema document.

In plain words
What is it for?
Use it to design permissions for applications with organizations, repositories, teams, users, and roles. It can help document access rules and prepare a SpiceDB schema.
Why use it?
It helps turn unclear authorization requirements into an organized access model before implementation. It also provides a step-by-step process for covering resources, relationships, and permissions.

Command

Part of the spicedb-dev plugin — 7 skills, 15 commands, 3 agents shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/authzed/authzed-marketplace/design-model
Clone the repo
git clone --depth 1 https://github.com/authzed/authzed-marketplace

Or install spicedb-dev, the plugin that ships this one along with the rest of its 7 skills, 15 commands, 3 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for design-model

README.md
[![agentmods](https://agentmods.dev/badge/commands/authzed/authzed-marketplace/design-model.svg)](https://agentmods.dev/commands/authzed/authzed-marketplace/design-model)
Your own site
<a href="https://agentmods.dev/commands/authzed/authzed-marketplace/design-model"><img src="https://agentmods.dev/badge/commands/authzed/authzed-marketplace/design-model.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,755 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00012 $0.01755
Opus 5 $0.00006 $0.00877
Sonnet 5 $0.00002 $0.00351
Haiku 4.5 $0.00001 $0.00176

Measured 4d ago against content hash e192c333d125, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

design-model scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

spicedb-dev/commands/design-model.md · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Permission Model

Guide the user through designing a comprehensive permission model for their application, then output a structured model document.

Progress Tracking

Before starting, use TaskCreate to create a task for each step. Use TaskUpdate to mark each task in_progress when starting and completed when done.

What You're Building

Before we start, here's what this command produces. The examples/github-style.zed file shows a GitHub-style model: organizations contain repositories, teams have members, and permissions like read, write, and admin are computed from relationships. We'll build something similar for your application.

Before presenting this orientation, read skills/spicedb-schema-design/examples/github-style.zed and reference specific resource types and permissions from it in the explanation above.

Process

Step 1: Understand the Application

First, understand what the application does and its authorization requirements.

Before asking questions: scan for existing models.

Use Glob to search for these patterns in the working directory:

  • **/*.prisma (Prisma schema)
  • **/models.py, **/models/**/*.py (Django)
  • **/internal/models/**/*.go, **/*_model.go (Go)
  • **/*.entity.ts, **/*.model.ts (TypeScript/NestJS)
  • **/db/schema.rb (Rails)
  • **/*.graphql, **/*.gql (GraphQL)
  • **/schema.sql, **/migrations/**/*.sql (SQL schemas)

If model files are found, read them and extract entity and table names. Use these as the starting point for the resource inventory: reference specific entity names in your questions rather than asking abstractly. For example, instead of "What are your main resources?", ask "I can see you have Document, Project, and Organization models -- are these the main things that need permission control, or are there others?"

If no model files are found, proceed with the question-driven approach below.

Ask the user:

  1. Application type: What kind of application is this? (SaaS, internal tool, API, etc.)
  2. User types: Who will use the system? (end users, admins, service accounts, etc.)
  3. Resources: What needs to be protected? (documents, projects, files, etc.)
  4. Access patterns: How do users typically interact with resources?

Read the full file on GitHub · 213 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 213 lines · 12 tokens per session scan A e192c333d125

Subscribe to this mod's changes

design-model is a command published in the GitHub repository authzed/authzed-marketplace (2 stars, last pushed 8d ago), licensed Apache-2.0. It adds 12 tokens to every session and 1,755 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.