Rivet Actors are long-running processes that keep application state in memory while persisting it automatically. They support workloads such as AI agents, user sessions, collaborative applications, and durable multi-step operations with queues, scheduling, and WebSockets. Catalogue add-ons help operate and develop Rivet Actors.
Borrowing it
Nothing to install: this file belongs to rivet-dev/actors. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rivet-dev/actors/main/.claude/skills/driver-test-runner/SKILL.mdgit clone --depth 1 https://github.com/rivet-dev/actorsWrote 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/rivet-dev/actors/driver-test-runner)<a href="https://agentmods.dev/skills/rivet-dev/actors/driver-test-runner"><img src="https://agentmods.dev/badge/skills/rivet-dev/actors/driver-test-runner/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/rivet-dev/actors/driver-test-runner"><img src="https://agentmods.dev/badge/skills/rivet-dev/actors/driver-test-runner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00068 | $0.03699 |
| Opus 5.5 | $0.00027 | $0.01480 |
| Sonnet 5.5 | $0.00014 | $0.00740 |
| Haiku 4.5 | $0.00007 | $0.00370 |
Grade A, and why
driver-test-runner scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sf http://127.0.0.1:6420/health || echo "NOT RUNNING" How it starts
The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Driver Test Suite Runner
Methodically run the RivetKit driver test suite one file group at a time across the native (NAPI) and wasm runtimes, tracking progress in ~/.agents/notes/driver-test-progress.md.
Arguments
The skill accepts optional arguments:
reset— Clear progress and start from the beginning.resume— Pick up from where we left off (default behavior).only <file>— Run only a specific test file group (e.g.,only actor-conn).from <file>— Start from a specific file group, skipping earlier ones.runtime <native|wasm|both>— Which runtime(s) to run (default:both).encoding <bare|cbor|json>— Override encoding (default:bare).registry <static>— Override registry type (default:static).
Runtime Matrix
The driver suite runs over a runtime × SQLite-backend × encoding matrix defined in rivetkit-typescript/packages/rivetkit/tests/driver/shared-matrix.ts. The runtime dimension has two values:
native— NAPI bindings (@rivetkit/rivetkit-napi). Pairs withsqlite=localfor the primary native driver pass.wasm— WebAssembly bindings (@rivetkit/rivetkit-wasm). Wasm cannot use local SQLite; it must pair withsqlite=remote(executes SQL through the engine over the wire).
The skill defaults to running each test file twice: once on native/local and once on wasm/remote, each at encoding=bare. A file is checked off only when both runtimes pass.
The test harness does not read environment variables for matrix selection. Always select matrix cells with Vitest -t using the full inner describe name: runtime (<runtime>) / sqlite (<backend>) / encoding (<encoding>).
How It Works
0. Anchor the reference before fixing parity bugs
If a RivetKit driver test fails because native or Rust behavior diverges from the old runtime, do this before inventing a separate debugging workflow:
- Treat
rivetkit-typescript/packages/rivetkitdriver tests as the primary oracle. - Compare the failing behavior against the original TypeScript implementation at ref
feat/sqlite-vfs-v2usinggit showorgit diff. - Patch native/Rust to match the original TypeScript behavior.
- Rerun the same TypeScript driver test before adding any lower-level native tests.
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 · 321 lines · 68 tokens per session scan A 63049087cf11
driver-test-runner is a skill published in the GitHub repository rivet-dev/actors (6,309 stars, last pushed yesterday), licensed Apache-2.0. It adds 68 tokens to every session and 3,699 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
benchmark-workflow
Run, diagnose, or change Xberg extraction benchmarks, quality scoring, benchmark fixtures, artifact contracts, and independently sourced ground truth. Load for the Benchmarks workflow or benchmark-harness work, not ordinary unit tests.
hotpath_cloud
Read hotpath Cloud performance verdicts with the hotpath cloud CLI and fix Rust performance regressions. Fetches the benchmark report of a commit or pull request, compares it with its baseline under the repository's regression policy and performance budgets, and lists what regressed and which budgets broke, as JSON.…
hotpath_init_ci_forks
Set up the hotpath Cloud CI integration in a public Rust project that benchmarks pull requests from forks. Adds the hotpath-cloud feature, a regression policy file, a GitHub Actions benchmark workflow that writes hotpath reports as artifacts and a relay workflow that uploads them, so every pull request, forks…
hotpath_init_ci
Set up the hotpath Cloud CI integration in a Rust project whose pull requests come from branches of the same repository (private repositories, or public ones that do not benchmark fork pull requests). Adds the hotpath-cloud feature, a regression policy file and a GitHub Actions benchmark workflow that uploads hotpath…
pair-programming
AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with…
stacked-prs
Optional workflow for large features using stacked PRs via gh-stack. Use ONLY when a feature has 3+ distinct concerns with clear dependencies. NOT for bug fixes, hotfixes, or small changes. Requires GitHub. Triggers: "stacked PRs", "gh stack", "split into layers", "stack this".