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 serverpod/skills-registry --skill riverpod-from-providergit clone --depth 1 https://github.com/serverpod/skills-registryWrote 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/serverpod/skills-registry/riverpod-from-provider)<a href="https://agentmods.dev/skills/serverpod/skills-registry/riverpod-from-provider"><img src="https://agentmods.dev/badge/skills/serverpod/skills-registry/riverpod-from-provider/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/serverpod/skills-registry/riverpod-from-provider"><img src="https://agentmods.dev/badge/skills/serverpod/skills-registry/riverpod-from-provider.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 | $0.00073 | $0.01179 |
| Opus 5.5 | $0.00029 | $0.00472 |
| Sonnet 5.5 | $0.00015 | $0.00236 |
| Haiku 4.5 | $0.00007 | $0.00118 |
Grade A, and why
riverpod-from-provider 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 2mo 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Riverpod — Migrating from Provider
Motivation
Riverpod was created as a successor to Provider, addressing InheritedWidget limitations:
- Same type: Provider can't have two
Provider<Item>in the tree (only the nearest is found). Riverpod has no such limit; providers are identified by variable, not type. - Combining providers: ProxyProvider is tedious and error-prone. In Riverpod, use ref.watch inside a provider to depend on others; composition is straightforward.
- AsyncValue: Riverpod can expose previous data while loading (e.g. show old list + loading indicator). Provider doesn't offer this cleanly.
- Safety: Provider can throw
ProviderNotFoundExceptionat runtime. Riverpod avoids this by design. - Disposal: Provider can't react when consumers stop listening; scoping is tricky. Riverpod offers autoDispose and ref.keepAlive for clear lifecycle and caching.
- Parameters: Riverpod's .family gives type-safe, parameterized providers with per-parameter state; with autoDispose, state is disposed when unused. Equivalent in Provider is impractical.
- Testing: With Provider you must re-define providers per test. With Riverpod, override with overrides to mock.
- Side effects: Riverpod offers ref.listen for reacting to changes (e.g. navigation, snackbars). Provider has no built-in equivalent.
The main API change: use ConsumerWidget (and WidgetRef) instead of StatelessWidget, and ref.watch / ref.read instead of context.watch / context.read.
Quickstart
- Read the Riverpod getting started guide (riverpod-getting-started) and try a small example.
- Migrate incrementally. You can run Provider and Riverpod side by side (use import aliases if needed).
Start with ChangeNotifierProvider
Keep existing ChangeNotifier classes and wrap them in Riverpod's ChangeNotifierProvider:
final myNotifierProvider = ChangeNotifierProvider<MyNotifier>((ref) => MyNotifier());
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.
- 2mo ago First seen · 98 lines · 73 tokens per session scan A be58c4b6f20a
riverpod-from-provider is a skill published in the GitHub repository serverpod/skills-registry (10 stars, last pushed 8mo ago), licensed BSD-3-Clause. It adds 73 tokens to every session and 1,179 once invoked, about $0.0003 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.
riverpod-from-provider compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| riverpod-from-providerserverpod/skills-registry | Skill | 10 | 8mo ago | BSD-3-Clause | A | 73 | Claude Code, Codex |
| orca-emulator-androidstablyai/orca | Skill | 117k | yesterday | MIT | A | 102 | Claude Code, Codex |
| glance-canonical-layoutsandroid/skills | Skill | 10k | yesterday | Apache-2.0 | A | 56 | Claude Code |
| android-tombstone-symbolicationdotnet/skills | Skill | 5.8k | yesterday | MIT | A | 176 | Claude Code |
| dogfoodcallstack/agent-device | Skill | 5.3k | yesterday | MIT | A | 55 | Claude Code |
| winapp-mauimicrosoft/winappCli | Skill | 1.4k | yesterday | MIT | A | 68 | Claude Code |
| app_remixrome-os/rome | Skill | 889 | yesterday | MIT | A | 50 | Claude Code, Codex |