validate-schema

validate-schema is a command for coding agents from authzed/authzed-marketplace. It costs 17 tokens per session (522 once invoked), scanned A, original, Apache-2.0.

A schema-validation command for SpiceDB .zed files. A schema is the written definition of resource types, relationships, and permissions used by SpiceDB.

In plain words
What is it for?
It locates a .zed file and reviews its syntax, naming, relationships, permissions, annotations, and possible improvements.
Why use it?
It catches invalid syntax, unclear structures, and potential authorization design problems before the schema is used.

Command

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/validate-schema
Clone the repo
git clone --depth 1 https://github.com/authzed/authzed-marketplace

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 validate-schema

README.md
[![agentmods](https://agentmods.dev/badge/commands/authzed/authzed-marketplace/validate-schema.svg)](https://agentmods.dev/commands/authzed/authzed-marketplace/validate-schema)
Your own site
<a href="https://agentmods.dev/commands/authzed/authzed-marketplace/validate-schema"><img src="https://agentmods.dev/badge/commands/authzed/authzed-marketplace/validate-schema.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 522 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 $0.00017 $0.00522
Opus 5 $0.00009 $0.00261
Sonnet 5 $0.00003 $0.00104
Haiku 4.5 $0.00002 $0.00052

Measured 3d ago against content hash f20b9e0245dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

validate-schema 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 3d 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/validate-schema.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Validate SpiceDB Schema

Validate any SpiceDB .zed schema file using the schema-validator agent. Works on any .zed file -- plugin-generated, manually edited, or migrated from another system.

Process

Step 1: Locate Schema

If the user provided a schema file path, use that. Otherwise:

  1. Search for *.zed files in the current working directory
  2. If exactly one is found, use it
  3. If multiple are found, ask the user which to validate using AskUserQuestion
  4. If none are found, ask the user for the schema file location

Step 2: Launch schema-validator Agent

Use the Task tool to launch the schema-validator agent:

Task(
    subagent_type="spicedb-dev:schema-validator",
    description="Validate SpiceDB schema",
    prompt="Validate the schema file at [path] and suggest improvements"
)

The agent will:

  • Check syntax for .zed schema language validity
  • Validate best practices (naming conventions, relation/permission structure)
  • Suggest optimizations
  • Identify potential issues (anti-patterns, missing type annotations, etc.)

Step 3: Present Results

Present the validation results to the user with:

  1. Summary: Pass/fail and number of issues found
  2. Issues: List each issue with its severity (error, warning, suggestion) and location
  3. Next steps:
    • If issues found: describe what to fix and how
    • If no issues: suggest running /spicedb-dev:generate-schema (if no schema yet) or /spicedb-dev:implement-spicedb-checks to add authorization code

Tips

  • This command works on any .zed file, not just plugin-generated schemas
  • Run after manually editing a schema to catch regressions
  • Run after migrating a schema from another system to verify correctness
  • The generate-schema command runs this automatically after generation

Notes

  • The schema-validator agent performs static analysis only -- it does not connect to a live SpiceDB instance
  • For runtime validation with actual relationships, use spicedb serve-testing (see authorization-testing skill)

Read the full file on GitHub · 66 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. 3d ago First seen · 66 lines · 17 tokens per session scan A f20b9e0245dc

Subscribe to this mod's changes

validate-schema is a command published in the GitHub repository authzed/authzed-marketplace (2 stars, last pushed 7d ago), licensed Apache-2.0. It adds 17 tokens to every session and 522 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.