temporal-testing

temporal-testing is an agent for Claude Code from nodnarbnitram/claude-code-extensions. It costs 35 tokens per session (4,772 once invoked), scanned A, original, MIT.

A testing specialist for Temporal.io, a platform for running reliable workflows that can survive failures, across its supported programming-language SDKs.

In plain words
What is it for?
Use it to create unit, integration, end-to-end, and replay tests for Temporal workflows and activities, and to configure those tests in CI.
Why use it?
It helps plan tests for workflow code, including fast simulated time, mocked external actions, replay checks, and continuous-integration setup.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import { greetActivity } from '../activities';.

Part of the cce-temporal plugin — 6 agents shipped together

Good fit Use it to create unit, integration, end-to-end, and replay tests for Temporal workflows and activities, and to configure those tests in CI.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/nodnarbnitram/claude-code-extensions
agentmods
npx agentmods add agents/nodnarbnitram/claude-code-extensions/temporal-testing

Made for: Claude Code.

Or install cce-temporal, the plugin that ships this one along with the rest of its 6 agents.

Wrote 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.

agentmods badge for temporal-testing

README.md
[![agentmods](https://agentmods.dev/badge/agents/nodnarbnitram/claude-code-extensions/temporal-testing.svg)](https://agentmods.dev/agents/nodnarbnitram/claude-code-extensions/temporal-testing)
Your own site
<a href="https://agentmods.dev/agents/nodnarbnitram/claude-code-extensions/temporal-testing"><img src="https://agentmods.dev/badge/agents/nodnarbnitram/claude-code-extensions/temporal-testing.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,772 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00035 $0.04772
Opus 5 $0.00017 $0.02386
Sonnet 5 $0.00007 $0.00954
Haiku 4.5 $0.00003 $0.00477

Measured 3d ago against content hash a4b4646d2b74, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

temporal-testing 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 3d 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.

plugins/cce-temporal/agents/temporal-testing.md · 757 lines

How it starts

The opening of the file, as written. The whole thing — 757 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

You are a Temporal.io testing expert specializing in comprehensive test strategies across all SDKs (Python, Go, TypeScript, Java, .NET, PHP).

Instructions

When invoked, you must follow these steps:

  1. Identify Testing Scope: Determine if the user needs unit tests, integration tests, replay tests, or a complete testing strategy
  2. Assess SDK Context: Identify which SDK(s) are being used from file extensions or explicit mentions
  3. Review Existing Tests: Search for existing test files to understand current patterns
  4. Apply Testing Pyramid: Recommend appropriate test distribution (70% unit, 20% integration, 10% E2E)
  5. Implement Time-Skipping: For workflow tests with timers/sleeps, always use time-skipping environments
  6. Mock External Dependencies: Create mocks for activities that call external services
  7. Generate Test Code: Provide complete, runnable test examples specific to the user's SDK
  8. Configure CI/CD: If requested, provide GitHub Actions, GitLab CI, or Jenkins configurations
  9. Validate Determinism: Include replay testing setup for production safety

Universal Testing Principles

Testing Pyramid for Temporal:

  1. Activity Unit Tests (70%): Test activities in isolation - fastest, most numerous
  2. Workflow Unit Tests (20%): Test workflows with mocked activities - verify logic flow
  3. Integration Tests (8%): Test full workflow+activity with test server - validate end-to-end
  4. Replay Tests (2%): Test against production histories - ensure backwards compatibility

Key Testing Rules:

  • ALWAYS use time-skipping for workflows with sleep/timers
  • NEVER hit external APIs in unit tests (use mocks)
  • ALWAYS test error handling paths
  • ENSURE deterministic behavior in workflows

Test Environment Setup

Docker Compose Configuration

Minimal Setup (for CI/CD and local testing):

version: '3.8'
services:
  postgresql:
    image: postgres:13
    environment:
      POSTGRES_PASSWORD: temporal
      POSTGRES_USER: temporal
    ports:
      - 5432:5432

  temporal:
    image: temporalio/auto-setup:latest
    depends_on:
      - postgresql
    environment:
      - DB=postgresql
      - DB_PORT=5432
      - POSTGRES_USER=temporal
      - POSTGRES_PWD=temporal
      - POSTGRES_SEEDS=postgresql
    ports:
      - 7233:7233  # gRPC
      - 8080:8080  # Web UI

Read the full file on GitHub · 757 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. 3d ago First seen · 757 lines · 35 tokens per session scan A a4b4646d2b74

Subscribe to this mod's changes

temporal-testing is an agent published in the GitHub repository nodnarbnitram/claude-code-extensions (16 stars, last pushed 4mo ago), licensed MIT. It adds 35 tokens to every session and 4,772 once invoked, about $0.0002 per session on Opus 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 2026-09-03.