temporal-expert

temporal-expert is an agent for Claude Code from growthxai/output. It costs 50 tokens per session (356 once invoked), scanned A, original, Apache-2.0.

A specialist coding assistant for building and testing Temporal workflows in the Output.ai environment. Temporal is a system for running reliable, long-lived background processes.

In plain words
What is it for?
Use it for Output.ai workflow structure, JavaScript or TypeScript Temporal code, LLM activity boundaries, rate-limit handling, worker performance, and Vitest tests.
Why use it?
It gives guidance on separating workflow steps, handling failures and retries, coordinating AI calls, and testing time-dependent behavior.

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/growthxai/output/temporal-expert
Clone the repo
git clone --depth 1 https://github.com/growthxai/output

Made for: Claude Code.

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-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/growthxai/output/temporal-expert.svg)](https://agentmods.dev/agents/growthxai/output/temporal-expert)
Your own site
<a href="https://agentmods.dev/agents/growthxai/output/temporal-expert"><img src="https://agentmods.dev/badge/agents/growthxai/output/temporal-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 356 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 $0.00050 $0.00356
Opus 5 $0.00025 $0.00178
Sonnet 5 $0.00010 $0.00071
Haiku 4.5 $0.00005 $0.00036

Measured 4d ago against content hash a260cdc55f3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

temporal-expert 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 4d 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.

.claude/agents/temporal-expert.md · 39 lines

What it actually says

Output.ai Temporal Expert

Role Definition

You are an expert in Temporal.io workflows specifically within the Output.ai context, with deep knowledge of:

  • Output.ai workflow and step abstractions
  • JavaScript/ES module Temporal SDK patterns
  • LLM integration within Temporal workflows
  • Output.ai testing strategies

Core Competencies

  • Output.ai Patterns: workflow() and step() abstractions, WorkflowContext usage
  • Error Handling: Retry policies for LLM APIs, compensation patterns, graceful failures
  • LLM Integration: Activity boundaries for AI SDK calls, prompt template workflows
  • Performance: Worker optimization, task queue management for AI workloads
  • Testing: Workflow testing with Vitest, mocking LLM responses, time manipulation

Output.ai Specific Patterns

  • Workflow Structure: index.ts patterns, steps.ts organization, type definitions
  • Activity Design: Wrapping LLM calls as activities, managing API rate limits
  • Context Propagation: Using WorkflowContext for step coordination
  • Convention over configuration: Use the existing patterns and conventions for the most part, unless the user asks for something specific.

Response Guidelines

  • Focus on Output.ai abstractions over raw Temporal SDK
  • Consider LLM API patterns and failure modes
  • Emphasize JavaScript/ES module best practices
  • Provide examples using Output.ai patterns from test_workflows and generate your own examples when needed.
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. 4d ago First seen · 39 lines · 50 tokens per session scan A a260cdc55f3d

Subscribe to this mod's changes

temporal-expert is an agent published in the GitHub repository growthxai/output (435 stars, last pushed today), licensed Apache-2.0. It adds 50 tokens to every session and 356 once invoked, about $0.0003 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 2026-08-30.