An autonomous workflow for improving software performance through research, proof-of-concept work, benchmarking, implementation, review, and pull-request preparation. A benchmark measures how quickly or efficiently code runs, and a pull request proposes changes for review.

Use it to investigate bottlenecks, test possible optimizations, apply the chosen change, measure the result, review it, and prepare a pull request.

It organizes performance work from measurement through review, helping avoid changes based only on guesses about what is slow.

How raullenchai/Rapid-MLX configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to raullenchai/Rapid-MLX. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/raullenchai/Rapid-MLX/main/.claude/skills/perfup/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/raullenchai/Rapid-MLX

Made for: Claude Code.

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/raullenchai/rapid-mlx/perfup/github.svg)](https://agentmods.dev/skills/raullenchai/rapid-mlx/perfup)

Your own site

<a href="https://agentmods.dev/skills/raullenchai/rapid-mlx/perfup"><img src="https://agentmods.dev/badge/skills/raullenchai/rapid-mlx/perfup/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/raullenchai/rapid-mlx/perfup"><img src="https://agentmods.dev/badge/skills/raullenchai/rapid-mlx/perfup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,757 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. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high Tool Misuse · line 88
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.

How audits are shown

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	$0.00020	$0.01757
Opus 5.5	$0.00008	$0.00703
Sonnet 5.5	$0.00004	$0.00351
Haiku 4.5	$0.00002	$0.00176

Measured 2mo ago against content hash 78f1ec037ef9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

perfup 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 2mo 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.

.claude/skills/perfup/SKILL.md · 171 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

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.

2mo ago First seen · 171 lines · 20 tokens per session scan A 78f1ec037ef9

Subscribe to this mod's changes

perfup is a skill published in the GitHub repository raullenchai/Rapid-MLX (4,104 stars, last pushed today), with no licence file. It adds 20 tokens to every session and 1,757 once invoked, about $0.0001 per session on Opus 5.5. 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.

Apple Silicon Debugging Tool Calling local-llm macos mlx ollama-alternative

perfup next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
perfupraullenchai/Rapid-MLX	Skill	4.1k	today	none	A	20	Claude Code
localvoxtral-doctorT0mSIlver/localvoxtral	Skill	63	today	MIT	A	59	Claude Code
reproducible-github-issuesBlaizzy/mlx-vlm	Skill	5.7k	4d ago	MIT	A	67	Claude Code
benchmarksoniqo/speech-swift	Skill	1.3k	yesterday	Apache-2.0	A	0	Claude Code
review-prsoniqo/speech-swift	Skill	1.3k	yesterday	Apache-2.0	A	71	Claude Code
vocello-designPowerBeef/Vocello	Skill	387	3d ago	MIT	A	24	Claude Code
vox-voice-alertskohlhofer/vox	Skill	7	2mo ago	MIT	A	117	Claude Code, Codex

Rapid-MLX: Skill for Claude Code