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.
git 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/plan)<a href="https://agentmods.dev/commands/authzed/authzed-marketplace/plan"><img src="https://agentmods.dev/badge/commands/authzed/authzed-marketplace/plan/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/authzed/authzed-marketplace/plan"><img src="https://agentmods.dev/badge/commands/authzed/authzed-marketplace/plan.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00034 | $0.03251 |
| Opus 5.5 | $0.00014 | $0.01300 |
| Sonnet 5.5 | $0.00007 | $0.00650 |
| Haiku 4.5 | $0.00003 | $0.00325 |
Grade A, and why
plan 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 1mo 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 — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Authorization Implementation
Guide the user from "I need to add authorization" to a concrete, phased implementation
plan. Produces authorization-plan.md as a shareable file artifact.
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: Understand the Application
Ask using AskUserQuestion (infer from context where possible):
- Application context: what does it do? what language? new or existing?
- Authorization scope: what resources need protection? who are the actors? is there a hierarchy?
- Starting point: does a schema already exist? does existing auth code exist? are there tests?
Step 2: Identify Complexity
Based on the answers, classify the authorization model:
| Complexity | Indicators | Typical Pattern |
|---|---|---|
| Simple | 1-3 resource types, flat access, no groups | Basic RBAC |
| Moderate | 3-6 resource types, teams/groups, some hierarchy | ReBAC with inheritance |
| Complex | Many resources, multi-tenant, custom roles, caveats | Multi-tenant SaaS |
Complexity determines how much design work is needed in Phase 1 before generating artifacts.
Step 3: Identify Which Phases Are Needed
Not every project starts at Phase 1. Match the user's starting point to the right entry phase:
| Starting Point | Entry Phase | Command |
|---|---|---|
| Just an idea, no schema | Phase 1: Design | /spicedb-dev:design-model |
| Has a permission model doc but no schema | Phase 2: Generate | /spicedb-dev:generate-schema |
| Has a schema but no implementation | Phase 3: Implement | /spicedb-dev:implement-spicedb-checks |
| Has implementation but no bootstrap | Phase 4: Bootstrap | /spicedb-dev:implement-spicedb-relationships (bulk patterns) |
| Has implementation but no tests | Phase 5: Test | /spicedb-dev:test-permissions |
| Has existing auth (role checks, Casbin, OPA, middleware) | Migration track | Start at Phase 1 with migration context (read existing auth code first) |
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.
- 1mo ago First seen · 327 lines · 34 tokens per session scan A 198cba1c49cf
plan is a command published in the GitHub repository authzed/authzed-marketplace (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 3,251 once invoked, about $0.0001 per session on Opus 5.5. 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.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.