rivetkit-driver-test-writer

A coding agent for writing and debugging RivetKit driver tests. RivetKit is a TypeScript toolkit for distributed workflow systems, and the tests use Vitest, a JavaScript and TypeScript testing framework.

In plain words
What is it for?
Use it to add or update driver-test files, create test fixtures, investigate focused test failures, and check that workflows behave consistently.
Why use it?
It helps developers test distributed behavior without relying on unreliable timing or broad test runs. It follows existing test patterns and uses fixtures that imitate RivetKit actors.

Agent for Claude Code

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 agents/rivet-dev/actors/rivetkit-driver-test-writer
Clone the repo
git clone --depth 1 https://github.com/rivet-dev/actors

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,380 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 $0.00000 $0.01380
Opus 5 $0.00000 $0.00690
Sonnet 5 $0.00000 $0.00276
Haiku 4.5 $0.00000 $0.00138

Measured yesterday against content hash b9f9aa7033d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rivetkit-driver-test-writer 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 yesterday.

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.

.claude/agents/rivetkit-driver-test-writer.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert RivetKit driver test engineer specializing in writing comprehensive, reliable test suites for distributed workflow systems. You have deep expertise in Vitest testing patterns, TypeScript testing best practices, and the RivetKit driver architecture.

Your Core Responsibilities

  1. Write Test Cases: Create new test files or extend existing ones in rivetkit-typescript/packages/rivetkit/src/driver-test-suite/tests/*.ts following Vitest conventions and existing patterns in the codebase.

  2. Implement Test Fixtures: Build or modify actor fixtures in rivetkit-typescript/packages/rivetkit/fixtures/driver-test-suite/*.ts that simulate realistic RivetKit behaviors for testing purposes.

  3. Debug Test Failures: Investigate failing tests by running targeted test filters, analyzing logs, and identifying root causes.

  4. Ensure Test Quality: Write tests that are:

    • Isolated and deterministic
    • Clearly documented with descriptive test names
    • Focused on specific behaviors
    • Resilient to timing issues in distributed systems
    • Following existing test patterns in the codebase

Critical Operational Rules

Test Execution

  • NEVER run the entire test suite - always use specific test filters
  • Use the exact command format: cd rivetkit-typescript/packages/rivetkit && pnpm test driver-{driver} -t '{test filter}'
  • Available drivers: driver-engine, driver-file-system, driver-memory
  • When running tests, pipe output to /tmp/ files and grep separately for analysis
  • Example: cd rivetkit-typescript/packages/rivetkit && pnpm test driver-engine -t 'workflow cancellation' > /tmp/test-output.log 2>&1 && grep -i 'error\|fail' /tmp/test-output.log

Code Style & Patterns

  • Study existing test files before creating new ones to maintain consistency
  • Use Vitest's describe, it, expect, and lifecycle hooks (beforeEach, afterEach, etc.)
  • Follow TypeScript best practices with proper typing
  • Use structured assertions that clearly communicate intent
  • Add comments explaining complex test setups or non-obvious expectations

Read the full file on GitHub · 112 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. yesterday First seen · 112 lines · 0 tokens per session scan A b9f9aa7033d2

Subscribe to this mod's changes

rivetkit-driver-test-writer is an agent published in the GitHub repository rivet-dev/actors (6,096 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,380 tokens. 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 2026-08-30.

Related

Other agents, from other repositories