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 skills add authzed/authzed-marketplace --skill openfga-to-spicedbgit 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/skills/authzed/authzed-marketplace/openfga-to-spicedb)<a href="https://agentmods.dev/skills/authzed/authzed-marketplace/openfga-to-spicedb"><img src="https://agentmods.dev/badge/skills/authzed/authzed-marketplace/openfga-to-spicedb/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/skills/authzed/authzed-marketplace/openfga-to-spicedb"><img src="https://agentmods.dev/badge/skills/authzed/authzed-marketplace/openfga-to-spicedb.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 | $0.00058 | $0.04380 |
| Opus 5.5 | $0.00023 | $0.01752 |
| Sonnet 5.5 | $0.00012 | $0.00876 |
| Haiku 4.5 | $0.00006 | $0.00438 |
Grade A, and why
OpenFGA to 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 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 — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenFGA to SpiceDB
The conversion pack for OpenFGA and its hosted variants (Okta FGA, the deprecated Auth0
FGA). It supplies the source-specific half of the migration pipeline defined by the
migrating-to-spicedb skill; that skill owns the phases, the gate, and the finding
taxonomy, and this pack owns everything that mentions OpenFGA by name.
The DSL is identical across all three variants. Target OpenFGA and nothing changes --
Okta FGA's deltas are entirely in its data plane (store CRUD and the AuthZEN surface are
absent; it adds four SaaS-only endpoints; its token issuer appears in official sources as
both auth.fga.dev and fga.us.auth0.com, and either is valid). Those deltas matter in
phase 4, not phase 1.
Reference files
| Need to... | Read this |
|---|---|
Translate a model construct into .zed |
references/schema-mapping.md |
| Decide what a name becomes, or how object IDs are encoded | references/naming-normalization.md |
| Detect and resolve a Class A hard blocker | references/blockers.md |
| Extract, transform, and load a live store's relationship data into SpiceDB | references/data-mapping.md |
Convert .fga.yaml test/assertion files into SpiceDB validation YAML |
references/test-mapping.md |
Implement the differential-harness seam /spicedb-dev:migrate-verify emits from -- dual-run, replay, and the OpenFGA-to-five-state Outcome mapping |
references/source-adapter.md |
| See the full corpus record -- what's been run vs. only intended, and which rules carry corpus confirmation vs. none | references/validation-corpus.md |
Status: what this pack covers today
This pack is hardened by running it against a real corpus, not by authoring reference material from research (spec decision D11). Rules are written when a real store forces them, so the absence of a rule is information: it means nothing in the corpus has needed it yet, not that the construct is unsupported.
| Pack-contract item | State |
|---|---|
| 1. Detection | in this file |
| 2. Model extraction | in this file |
| 3. Schema mapping | references/schema-mapping.md -- clean constructs only |
| 4. Blocker catalog | references/blockers.md -- the Class A blockers (read the file for the list; it is added to as new shapes are found) |
| 5. Naming normalization | references/naming-normalization.md |
| 6. Data mapping | references/data-mapping.md -- consumed by /spicedb-dev:migrate-data (phase 3) |
| 7. Code mapping | references/code-mapping.md -- consumed by /spicedb-dev:migrate-code (phase 4) |
| 8. Test mapping | references/test-mapping.md -- consumed by /spicedb-dev:migrate-tests (phase 5) |
| 9. Scoping questionnaire | in this file |
| 10. Validation corpus | references/validation-corpus.md -- summarized in this file |
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 271 lines · 58 tokens per session scan A bb6809858dfa
OpenFGA to SpiceDB is a skill published in the GitHub repository authzed/authzed-marketplace (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 58 tokens to every session and 4,380 once invoked, about $0.0002 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 skills, from other repositories
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
agui-dotnet-protobuf
Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
fastapi-router-py
Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.
dev-runtime
How the Node side of a dev stack runs without haven, and the backend host: pnpm dev (UI built once, backend reloading), pnpm dev:hmr (adds the Vite ui lane), tools/dev-runtime (api + worker in one Node process), backend reload on a file change, the debounce (quiet window + max wait), ports derived from PORT. Use when…
api-design
Use when settling the contract of an API you expose, before implementation: resources/URLs, REST vs GraphQL, versioning, one RFC 9457 error envelope, pagination, idempotency — emitted as OpenAPI 3.1. NOT implementing the endpoints (that is fastapi/nestjs/go/nodejs), NOT auth hardening (that is secure-coding), NOT…