AsyncOpenAI Concurrency Fix

AsyncOpenAI Concurrency Fix is an AI Engineering skill for Claude Code, published by kennethkhoocy in applied-micro-skills.

48 stars0 forkson kennethkhoocy/applied-micro-skillsAdded 2026/08/11Repository updated 2026/07/22

View source on GitHub Download repo ZIP

applied-microeconomicsclaude-codeclaude-skillscodexcodex-skillsempirical-research

Install in seconds

Install AsyncOpenAI Concurrency Fix

Copy AsyncOpenAI Concurrency Fix into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/kennethkhoocy/applied-micro-skills/tree/main/plugins/applied-micro/skills/asyncopenai-concurrency-httpx-pool ~/.claude/skills/asyncopenai-concurrency-httpx-pool

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/kennethkhoocy/applied-micro-skills.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: plugins/applied-micro/skills/asyncopenai-concurrency-httpx-pool/SKILL.md in kennethkhoocy/applied-micro-skills
Installs to: ~/.claude/skills/asyncopenai-concurrency-httpx-pool
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What AsyncOpenAI Concurrency Fix does

Fixes a silent throughput ceiling in asyncio LLM batch pipelines by overriding the default httpx connection pool limit to match the desired concurrency. Use when raising the asyncio semaphore above ~100 produces no gain.

AsyncOpenAI Concurrency Fix is cataloged under AI Engineering on DirSkills. AsyncOpenAI Concurrency Fix comes from a repository tagged applied-microeconomics, claude-code, claude-skills, codex and codex-skills.

Documentation

README

Excerpt

AsyncOpenAI Concurrency: the Hidden httpx Pool Cap

Problem

Async batch scorers typically gate concurrency with asyncio.Semaphore(N). Raising N above ~100 silently does nothing: the OpenAI SDK's default httpx transport caps the connection pool at max_connections=100, so excess tasks queue inside httpx instead of reaching the provider. The semaphore looks like the throttle but is not the binding constraint — there is no error, just a throughput ceiling.

Context / Trigger Conditions

This is the opening of the README. Read the full README on GitHub.

Frequently asked about AsyncOpenAI Concurrency Fix

What else does kennethkhoocy publish alongside AsyncOpenAI Concurrency Fix?
AsyncOpenAI Concurrency Fix is one of 25 skills that DirSkills catalogs from kennethkhoocy/applied-micro-skills, the repository it ships in. Its siblings there include Adversarial Empirical Review, Annotator Input Parity Check and Cite Placement. Each one is a separate skill with its own page in this directory, installs the same way AsyncOpenAI Concurrency Fix does, and is maintained by kennethkhoocy in that same repository. The rest of the collection is listed on the kennethkhoocy/applied-micro-skills page.
How does AsyncOpenAI Concurrency Fix compare to other AI Engineering skills?
AsyncOpenAI Concurrency Fix ranks #2279 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of AsyncOpenAI Concurrency Fix against them. Open each page to compare what they document and how they install.