xLLM is an inference engine, meaning software that runs trained AI models to produce outputs from inputs, for large language, vision-language, diffusion, and recommendation models on different AI accelerators. Organizations use it to deploy these models with high-throughput and low-latency inference. The catalogue entries provide skills and instructions for working with xLLM.
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.
git clone --depth 1 https://github.com/xLLM-AI/xllmWrote 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/rules/xllm-ai/xllm/move-copy-semantics)<a href="https://agentmods.dev/rules/xllm-ai/xllm/move-copy-semantics"><img src="https://agentmods.dev/badge/rules/xllm-ai/xllm/move-copy-semantics.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 5.1 | $0.00410 | $0.00410 |
| Opus 5 | $0.00205 | $0.00205 |
| Sonnet 5 | $0.00082 | $0.00082 |
| Haiku 4.5 | $0.00041 | $0.00041 |
Grade A, and why
move-copy-semantics 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 today.
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
Move & Copy Semantics
std::move(x) is only a cast to T&&. When x is const& (or const), it yields
a const T&& that binds to the copy constructor, not the move constructor —
so it compiles, looks like a move, and silently deep-copies. This is the bug that
made Request/RequestState construction copy their whole payload.
- Never
std::moveaconst&/ const value. The two ingredients of the bug are always "a const source +std::move". Don't combine them. - Sink parameters go by value +
std::move. If a function/ctor retains its argument, take it by value andstd::moveit into the member. Useconst&only for parameters you read but do not retain. - Make callers move. Pass
std::move(local)when you hand an owned local to a sink parameter and don't use it afterwards; an lvalue silently copies. - Consider making heavy, rarely-copied domain types move-only (
= deletecopy) with an explicitclone(), so an accidental copy is a compile error.
// Bad – const& + std::move => copies
Request(const RequestState& state) : state_(std::move(state)) {}
// Good – sink by value; caller chooses copy (lvalue) vs move (std::move)
Request(RequestState state) : state_(std::move(state)) {}
clang-tidy's performance-move-const-arg (see repo .clang-tidy) flags this.
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.
- today First seen · 33 lines · 410 tokens per session scan A 61fb3fe98e89
move-copy-semantics is a cursor rule published in the GitHub repository xLLM-AI/xllm (1,562 stars, last pushed today), licensed Apache-2.0. It adds 410 tokens to every session, about $0.0020 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 2026-09-08.
Other cursor rules, from other repositories
atmos-rules
This is a Golang CLI project using Cobra for command structure and Viper for configuration management. The project maintains high code quality standards through golangci-lint and aims for maximum test coverage. The repository also includes the website source code for https://atmos.tools.
020-flask
Flask API Gateway conventions for LMForge.
python-3-brutal-audit
Phase-based brutal audit workflow for Python projects - on-demand architectural review.
monitor-c-conventions
C coding conventions for HPCPerfStats monitor (C-only).
monitor-c-refactor-standards
Behavior-preserving C refactor standards for HPCPerfStats monitor.
cpp-advanced-concurrency
A set of C++ guidance for running work at the same time safely. It covers mutexes, atomic operations, condition variables, and worker pools.