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/test-permissionsgit 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/test-permissions)<a href="https://agentmods.dev/commands/authzed/authzed-marketplace/test-permissions"><img src="https://agentmods.dev/badge/commands/authzed/authzed-marketplace/test-permissions.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 5.1 | $0.00014 | $0.03974 |
| Opus 5 | $0.00007 | $0.01987 |
| Sonnet 5 | $0.00003 | $0.00795 |
| Haiku 4.5 | $0.00001 | $0.00397 |
Grade A, and why
test-permissions 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 5d 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 — 512 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Permission Tests
Generate test data fixtures and test scenarios for a SpiceDB authorization schema.
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.
Process
Step 1: Locate Schema
If user provided schema file, use that. Otherwise:
- Look for
*.zedfiles in current directory - If multiple found, ask which to use
- If none found, ask for schema location
Step 2: Parse Schema
Read the schema and extract:
- Resource definitions
- Relations for each resource
- Permissions for each resource
- Hierarchical relationships
- Wildcards or caveats
Step 3: Determine Test Language
Ask the user (or detect from codebase):
- Go (use go test)
- TypeScript/JavaScript (use Jest/Mocha)
- Python (use pytest)
- YAML (use SpiceDB assertions)
Step 4: Generate Test Fixtures
Use the resource types, relation names, and permission names parsed in Step 2.
Do not use placeholder names (document, doc-1, alice) unless those are actually
in the schema. For each definition found, use that definition name as the object type
and its declared relations as the relation names in all generated fixtures.
For each resource type in the schema, generate:
Basic relationships:
# Direct ownership
document:doc-1#owner@user:alice
# Role-based access
document:doc-1#editor@user:bob
document:doc-1#viewer@user:charlie
# No access
# user:dave has no relationships
Hierarchical relationships:
# Organization hierarchy
organization:acme#admin@user:alice
organization:acme#member@user:bob
team:engineering#org@organization:acme
team:engineering#member@user:charlie
project:api#parent@team:engineering
Complex scenarios:
# Multi-path access
organization:acme#admin@user:alice
project:api#org@organization:acme
project:api#owner@user:bob
# alice can access via org admin, bob via ownership
Replace document, organization, user with the actual definition names from
Step 2. Replace owner, editor, viewer with the actual relation names declared
in that definition.
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.
- 5d ago First seen · 512 lines · 14 tokens per session scan A 4a395316d306
test-permissions is a command published in the GitHub repository authzed/authzed-marketplace (2 stars, last pushed 8d ago), licensed Apache-2.0. It adds 14 tokens to every session and 3,974 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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.