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 agentmods add agents/growthxai/output/temporal-expertgit clone --depth 1 https://github.com/growthxai/outputWrote 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/agents/growthxai/output/temporal-expert)<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>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 | $0.00050 | $0.00356 |
| Opus 5 | $0.00025 | $0.00178 |
| Sonnet 5 | $0.00010 | $0.00071 |
| Haiku 4.5 | $0.00005 | $0.00036 |
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.
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.
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.
- 4d ago First seen · 39 lines · 50 tokens per session scan A a260cdc55f3d
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.
Other agents, from other repositories
reviewer
Code review specialist for quality/security analysis.
memory
LangGraph supports two types of memory essential for building conversational agents.
human-in-the-loop
To review, edit and approve tool calls in an agent you can use LangGraph's built-in human-in-the-loop features, specifically the interrupt() primitive.
streaming
Streaming is key to building responsive applications. There are a few types of data you’ll want to stream.
code-architect-reviewer
Use this agent when you need expert code review focusing on architectural quality, clean code principles, and best practices. Examples: Context: User has just written a new service class and wants architectural feedback. user: 'I just implemented a user authentication service. Can you review it?' assistant: 'I'll use…
librarian
Researches external libraries and APIs by reading source code. Returns definitive, source-verified answers.