murmur: Skill for Claude Code

.agents/skills/ondevice-model-perf/SKILL.md

ondevice-model-perf is a skill for Claude Code, Codex from murmur-io/murmur. It costs 170 tokens per session (2,269 once invoked), scanned B, original, AGPL-3.0.

A reference guide for improving machine-learning model speed and memory use on Apple computers with Apple Silicon. It covers topics such as quantization, the KV cache, audio processing, profiling, crashes, and RAM use.

In plain words
What is it for?
Use it when working on model-level performance in Murmur, including measurement, memory residency, audio context, or Metal-related issues.
Why use it?
It gives the agent project-specific context for evaluating performance instead of relying on general advice.

Skill for Claude CodeCodex

Which agent this was written for is unclear — body not stored (licence); the path alone says nothing. Also seen: installed under .agents/ (shared by several agents).

This is murmur-io/murmur's own configuration. It tells Claude Code and Codex how to work on murmur itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything murmur configures →

Reuse

Borrowing it

Nothing to install: this file belongs to murmur-io/murmur. 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/murmur-io/murmur/murmur/.agents/skills/ondevice-model-perf/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/murmur-io/murmur

Made for: Claude Code, Codex.

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 ondevice-model-perf

README.md
[![agentmods](https://agentmods.dev/badge/skills/murmur-io/murmur/ondevice-model-perf.svg)](https://agentmods.dev/skills/murmur-io/murmur/ondevice-model-perf)
Your own site
<a href="https://agentmods.dev/skills/murmur-io/murmur/ondevice-model-perf"><img src="https://agentmods.dev/badge/skills/murmur-io/murmur/ondevice-model-perf.svg" alt="Measured on agentmods" height="20"></a>
Per session 170 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,269 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00170 $0.02269
Opus 5 $0.00085 $0.01135
Sonnet 5 $0.00034 $0.00454
Haiku 4.5 $0.00017 $0.00227

Measured 7d ago against content hash 4a671f32a47b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

ondevice-model-perf scanned grade B 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 7d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- **watts** → `sudo powermetrics --samplers cpu_power,gpu_power,thermal -i 1000` alongside the app
.agents/skills/ondevice-model-perf/SKILL.md · 119 lines

The source is not reproduced here

Licensed AGPL-3.0

The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

Files

What ships with it

4 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.

  1. 7d ago First seen · 119 lines · 170 tokens per session scan B 4a671f32a47b

Subscribe to this mod's changes

ondevice-model-perf is a skill published in the GitHub repository murmur-io/murmur (11 stars, last pushed today), licensed AGPL-3.0. It adds 170 tokens to every session and 2,269 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

clovy-obsidian

Work with the Obsidian vault currently selected in Clovy.

open-software-network/os-clovy · 19 tokens

s-gw

Use s-gw when working with credentials, private keys, API tokens, SSH identities, browser credentials, or other sensitive data in agentic coding workflows. Prefer typed handles and local approved execution over exposing raw secret values to a model.

sgateway/s-gw · 51 tokens

scgpt

Embed and annotate single-cell expression data with scGPT, a foundation model for single-cell biology. Use this skill when: (1) Producing cell embeddings from an AnnData for clustering/integration, (2) Zero-shot or fine-tuned cell-type annotation, (3) Gene-level representation for perturbation/GRN tasks. For…

aipoch/open-science · 89 tokens

ima2

Use the ima2-gen CLI/server to generate, edit, inspect, and manage local AI image generation jobs.

lidge-jun/ima2-gen · 25 tokens

ai-sdk

Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI…

browseros-ai/BrowserOS · 155 tokens

gno

Search local documents, files, notes, and knowledge bases. Index directories, search with BM25/vector/hybrid, get AI answers with citations. Use when user wants to search files, find documents, query notes, look up information in local folders, index a directory, set up document search, build a knowledge base, needs…

gmickel/gno · 86 tokens