A reference skill for XLA, a compiler that turns machine-learning operations into code optimized for CPUs, GPUs, and TPUs. It covers XLA’s internal representations, compilation process, APIs, debugging, and build system.

Use it when working on XLA architecture, HLO programs, compiler passes, hardware backends, PJRT, MLIR integration, partitioning, autotuning, debugging, or builds.

It gives an agent background for understanding, developing, or debugging XLA-related code without searching through the whole project first.

xla — Skill for Claude Code and Codex by jstzwj

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.

Any agent

npx skills add jstzwj/ai-infra-plugins --skill xla

Clone the repo

git clone --depth 1 https://github.com/jstzwj/ai-infra-plugins

Made for: Claude Code, Codex.

Its marketplace also offers this one on its own, as the plugin xla — /plugin install xla after adding the marketplace above.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jstzwj/ai-infra-plugins/xla/github.svg)](https://agentmods.dev/skills/jstzwj/ai-infra-plugins/xla)

Your own site

<a href="https://agentmods.dev/skills/jstzwj/ai-infra-plugins/xla"><img src="https://agentmods.dev/badge/skills/jstzwj/ai-infra-plugins/xla/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jstzwj/ai-infra-plugins/xla"><img src="https://agentmods.dev/badge/skills/jstzwj/ai-infra-plugins/xla.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,095 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 unknown 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.

Model	Per session	Once invoked
Fable 5.1	$0.00066	$0.02095
Opus 5	$0.00033	$0.01047
Sonnet 5	$0.00013	$0.00419
Haiku 4.5	$0.00007	$0.00210

Measured 10d ago against content hash c4870a4b64cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

xla 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 10d 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/xla/skills/xla/SKILL.md · 162 lines

The source is not reproduced here

No licence file

Read it on GitHub

Files

What ships with it

30 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

10d ago First seen · 162 lines · 66 tokens per session scan A c4870a4b64cc

Subscribe to this mod's changes

xla is a skill published in the GitHub repository jstzwj/ai-infra-plugins (4 stars, last pushed 4mo ago), with no licence file. It adds 66 tokens to every session and 2,095 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 2026-08-31.

Data and AI Learning and teaching

fs-notebook-tabs

A computer-science capstone: an on-device ML keyboard that predicts next words privately — problem, method, evaluation, and defense answers. Built as a decision-grade coursework defense deck for professor, defense committee.

nexu-io/open-design · 47 tokens

implementing-llms-litgpt

Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.

davila7/claude-code-templates · 77 tokens

rwkv-architecture

RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.

davila7/claude-code-templates · 72 tokens

nanogpt

Educational GPT implementation in 300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).

davila7/claude-code-templates · 65 tokens

kaggle-learner

This skill should be used when the user asks to "learn from Kaggle", "study Kaggle solutions", "analyze Kaggle competitions", or mentions Kaggle competition URLs. Provides access to extracted knowledge from winning Kaggle solutions across NLP, CV, time series, tabular, and multimodal domains.

Galaxy-Dawn/claude-scholar · 69 tokens

data-science-engineering-foundation

State, resume, reconstruction, job-lifecycle, transition, and flow-state mechanics for the Data Science and Engineering Coach. Loaded by the coach; not a user entry point.

microsoft/hve-core · 43 tokens