implement-spicedb

implement-spicedb is a command for coding agents from authzed/authzed-marketplace. It costs 25 tokens per session (533 once invoked), scanned A, original, Apache-2.0.

A coding command for adding SpiceDB authorization operations to an application. SpiceDB is a service that stores relationships such as who can access which resource and answers permission questions.

In plain words
What is it for?
It adds relationship writes and deletes, permission checks, resource lookups, and bulk checks to application code.
Why use it?
It helps prevent an application from writing access relationships without also checking them, or checking permissions when no relationships have been recorded.

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/implement-spicedb
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 implement-spicedb

README.md
[![agentmods](https://agentmods.dev/badge/commands/authzed/authzed-marketplace/implement-spicedb.svg)](https://agentmods.dev/commands/authzed/authzed-marketplace/implement-spicedb)
Your own site
<a href="https://agentmods.dev/commands/authzed/authzed-marketplace/implement-spicedb"><img src="https://agentmods.dev/badge/commands/authzed/authzed-marketplace/implement-spicedb.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 533 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 $0.00025 $0.00533
Opus 5 $0.00013 $0.00267
Sonnet 5 $0.00005 $0.00107
Haiku 4.5 $0.00003 $0.00053

Measured 3d ago against content hash ce2181c93467, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implement-spicedb 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/implement-spicedb.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implement SpiceDB Operations

For any application feature, both operations are required:

  1. Relationship writes (WriteRelationships, DeleteRelationships) -- builds the graph
  2. Permission checks (CheckPermission, LookupResources, etc.) -- queries the graph

If SpiceDB has no relationships for a resource type, all permission checks return NO_PERMISSION regardless of what checks you add. Always implement writes first.

Which do you need right now?

Use AskUserQuestion to ask:

  • Writes: Add WriteRelationships / DeleteRelationships to application code (do this when adding: resource creation, membership grants, role assignments, deletions)
  • Checks: Add CheckPermission / LookupResources / BulkCheckPermission to application code (do this when adding: access guards on endpoints, list filtering, permission lookups)
  • Both: Start with writes (run writes command first, then checks)

After the user selects, carry out the corresponding command's instructions in this context: read the file named below and follow it as written, exactly as if the user had invoked it directly.

  • Writes selected: commands/implement-spicedb-relationships.md
  • Checks selected: commands/implement-spicedb-checks.md
  • Both selected: follow implement-spicedb-relationships.md to completion first, then implement-spicedb-checks.md -- writes before checks, for the reason given above.

Both files are commands, not agents and not skills, so they cannot be dispatched with Task(subagent_type=...): that parameter resolves against the agent registry, which contains only this plugin's three agents (migration-analyzer, schema-validator, checkpoint-identifier), and the call fails with an unknown-agent error rather than running anything. Read the file and follow it instead. If reading it fails, say so plainly and tell the user to run /spicedb-dev:implement-spicedb-relationships or /spicedb-dev:implement-spicedb-checks directly -- do not improvise the operation from this file's summary, which is a router, not an implementation guide.

Read the full file on GitHub · 50 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 · 50 lines · 25 tokens per session scan A ce2181c93467

Subscribe to this mod's changes

implement-spicedb is a command published in the GitHub repository authzed/authzed-marketplace (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 25 tokens to every session and 533 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.