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.
npx agentmods add commands/authzed/authzed-marketplace/design-modelgit clone --depth 1 https://github.com/authzed/authzed-marketplaceWrote 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.
[](https://agentmods.dev/commands/authzed/authzed-marketplace/design-model)<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>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.
| Model | Per session | Once 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 |
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.
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:
- Application type: What kind of application is this? (SaaS, internal tool, API, etc.)
- User types: Who will use the system? (end users, admins, service accounts, etc.)
- Resources: What needs to be protected? (documents, projects, files, etc.)
- Access patterns: How do users typically interact with resources?
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.
- 4d ago First seen · 213 lines · 12 tokens per session scan A e192c333d125
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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.