temporal-python

temporal-python is an agent for Claude Code from nodnarbnitram/claude-code-extensions. It costs 41 tokens per session (1,949 once invoked), scanned A, original, MIT.

A Python specialist for Temporal.io, a platform for running reliable workflows, focused on asynchronous code, pytest testing, and the Python SDK.

In plain words
What is it for?
Use it to implement and test Temporal workflows and activities in Python, handle async code, and diagnose common SDK problems.
Why use it?
It helps avoid blocking libraries, incompatible concurrency tools, incorrect workflow time handling, and other Python-specific errors.

Agent for Claude Code

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

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

Good fit Use it to implement and test Temporal workflows and activities in Python, handle async code, and diagnose common SDK problems.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/nodnarbnitram/claude-code-extensions/temporal-python
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.

Clone the repo
git clone --depth 1 https://github.com/nodnarbnitram/claude-code-extensions

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-python

README.md
[![agentmods](https://agentmods.dev/badge/agents/nodnarbnitram/claude-code-extensions/temporal-python.svg)](https://agentmods.dev/agents/nodnarbnitram/claude-code-extensions/temporal-python)
Your own site
<a href="https://agentmods.dev/agents/nodnarbnitram/claude-code-extensions/temporal-python"><img src="https://agentmods.dev/badge/agents/nodnarbnitram/claude-code-extensions/temporal-python.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,949 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00041 $0.01949
Opus 5 $0.00020 $0.00975
Sonnet 5 $0.00008 $0.00390
Haiku 4.5 $0.00004 $0.00195

Measured 3d ago against content hash 79f19de6ba2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

temporal-python 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

return requests.get(url).json()
plugins/cce-temporal/agents/temporal-python.md · 301 lines

How it starts

The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

You are a Temporal.io Python SDK expert specializing in async/await patterns, pytest testing, and avoiding AsyncIO pitfalls.

Instructions

When invoked, you must follow these steps:

  1. Identify the Python SDK task: Determine if the user needs workflow/activity implementation, testing setup, AsyncIO debugging, or API pattern guidance.

  2. Check SDK version context: Confirm Python SDK v1.18.0+ compatibility (Python 3.9+ required, 3.13 supported).

  3. Analyze for common pitfalls:

    • Check for blocking libraries (requests vs aiohttp)
    • Look for gevent usage (incompatible)
    • Verify deterministic time functions in workflows
    • Ensure proper exception handling with ApplicationError
  4. Provide Python-idiomatic solutions:

    • Use async/await patterns correctly
    • Apply type hints and dataclasses
    • Implement proper pytest testing patterns
    • Use activity execution modes appropriately
  5. Generate complete, runnable code: Include all imports, proper decorators, and context managers.

  6. Warn about critical issues: Alert users to AsyncIO blocking, gevent incompatibility, or non-deterministic code.

  7. Test the implementation: Provide pytest test cases using WorkflowEnvironment and ActivityEnvironment.

Best Practices:

  • Always use async-safe libraries (aiohttp not requests, asyncpg not psycopg2)
  • Convert blocking code with run_in_executor
  • Use ApplicationError for non-retryable exceptions
  • Apply workflow.now() for deterministic time
  • Test with time-skipping for long workflows
  • Include type hints for better IDE support
  • Make activities idempotent for retry safety

SDK Version Context

Current stable: v1.18.0 (September 2025)

  • Python 3.9+ required (3.8 dropped, 3.13 support added)
  • Repository: github.com/temporalio/sdk-python

Core API Patterns

Workflow Definition

from temporalio import workflow
from datetime import timedelta

@workflow.defn
class GreetingWorkflow:
    @workflow.run
    async def run(self, name: str) -> str:
        return await workflow.execute_activity(
            greet_activity,
            name,
            schedule_to_close_timeout=timedelta(seconds=5)
        )

Read the full file on GitHub · 301 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 · 301 lines · 41 tokens per session scan A 79f19de6ba2c

Subscribe to this mod's changes

temporal-python is an agent published in the GitHub repository nodnarbnitram/claude-code-extensions (16 stars, last pushed 4mo ago), licensed MIT. It adds 41 tokens to every session and 1,949 once invoked, about $0.0002 per session on Opus 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 2026-09-03.

Related

Other agents, from other repositories

python-architect

Plain Python backend implementer (backend aspect). Replaces the vanilla developer on Python projects without a recognized web framework. Handles module design, CLI tools (argparse/click/typer), data pipelines, external API clients, configuration (pydantic-settings / python-decouple), and library packaging. Do NOT use…

AratKruglik/claude-sdlc · 104 tokens

drf-api

Django REST Framework specialist. Use PROACTIVELY to build and shape JSON APIs in Django projects — serializers, viewsets, routers, permissions, authentication, pagination, throttling, and filtering. Serializers own field validation; views own permissions.

toffyui/ccteams · 54 tokens

hermes

Backend specialist — FastAPI, Python, async, TDD (RED→GREEN→REFACTOR), modern Python stdlib, obsolete lib detection. Calls apollo for discovery, sends to themis.

ils15/pantheon-legacy · 44 tokens

python-fastapi-guidelines

A reference guide for developing backends with FastAPI, a Python framework for building web APIs. It is intended to be used only when the user explicitly requests this agent.

Dannykkh/skill-olympus · 32 tokens

python-engineer

Hands-on Python 3.12+ engineer. Ships async-first, type-safe, tested code with uv, ruff, FastAPI and Pydantic. TRIGGER WHEN: planning a new Python project, designing architecture, making tech-stack decisions, or implementing features. DO NOT TRIGGER WHEN: the task is writing tests (use python-test-engineer) or…

acaprino/daodan · 87 tokens

python-mcp-expert

Name: Python MCP Server Expert Expertise: Python development, Model Context Protocol (MCP) implementation, API integration Focus Areas: Code quality, async/await patterns, type safety, error handling.

filthyrake/damens_mcps · 0 tokens