juce-guide

juce-guide is a skill for Claude Code, Codex from kunitoki/sonic-skills. It costs 108 tokens per session (975 once invoked), scanned A, original, Unlicense.

A guide for managing Kubernetes resources and workloads with kubectl, the command-line tool for communicating with a Kubernetes cluster.

In plain words
What is it for?
Use it to check cluster connectivity, manage pods and other resources, apply manifests, change namespaces or contexts, inspect events, and troubleshoot crashes or image errors.
Why use it?
It helps inspect cluster state, apply configuration, view logs, switch contexts, and diagnose common workload failures in a controlled way.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to check cluster connectivity, manage pods and other resources, apply manifests, change namespaces or contexts, inspect events, and troubleshoot crashes or image errors.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kunitoki/sonic-skills/juce-guide
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 kunitoki/sonic-skills --skill juce-guide
Clone the repo
git clone --depth 1 https://github.com/kunitoki/sonic-skills

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 juce-guide

README.md
[![agentmods](https://agentmods.dev/badge/skills/kunitoki/sonic-skills/juce-guide/github.svg)](https://agentmods.dev/skills/kunitoki/sonic-skills/juce-guide)
Your own site
<a href="https://agentmods.dev/skills/kunitoki/sonic-skills/juce-guide"><img src="https://agentmods.dev/badge/skills/kunitoki/sonic-skills/juce-guide/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.

agentmods 80×15 button for juce-guide

Your own site · 80×15
<a href="https://agentmods.dev/skills/kunitoki/sonic-skills/juce-guide"><img src="https://agentmods.dev/badge/skills/kunitoki/sonic-skills/juce-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 975 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 original 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 $0.00108 $0.00975
Opus 5.5 $0.00043 $0.00390
Sonnet 5.5 $0.00022 $0.00195
Haiku 4.5 $0.00011 $0.00097

Measured 2mo ago against content hash e13cf9f8714a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

juce-guide 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.

skills/juce-guide/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

JUCE Audio Plugin — Build Guide

Five steps from empty folder to distributable plugin. Do each step in order; skip none.

Step 1 — Project setup (CMake + JUCE)

  • Add JUCE as a git submodule or FetchContent target; call add_subdirectory(JUCE).
  • Use juce_add_plugin(MyPlugin FORMATS VST3 AU Standalone ...) to declare the plugin target.
  • Set PLUGIN_MANUFACTURER_CODE, PLUGIN_CODE, IS_SYNTH, NEEDS_MIDI_INPUT in the same call.
  • Link juce::juce_audio_processors juce::juce_audio_utils juce::juce_dsp to the target.

Step 2 — AudioProcessor skeleton

  • Subclass juce::AudioProcessor; override prepareToPlay, releaseResources, processBlock.
  • In prepareToPlay: store sampleRate and maximumBlockSize, allocate internal buffers, reset all state (filters, envelopes, delay lines — unconditionally).
  • In processBlock: read only pre-cached raw parameter pointers; never allocate, never call JUCE String ops or DBG().
  • Implement getStateInformation / setStateInformation using apvts.copyState() and apvts.replaceState() with a MemoryOutputStream / MemoryBlock.

Step 3 — Parameters via APVTS

  • Declare a static createParameterLayout() method that returns AudioProcessorValueTreeState::ParameterLayout.
  • Construct apvts(*this, nullptr, "Parameters", createParameterLayout()) as a member.
  • After constructing APVTS, cache raw pointers once: gainParam = apvts.getRawParameterValue("Gain").
  • In processBlock, dereference with gainParam->load() — no APVTS calls on the audio thread.
  • Use AudioProcessorValueTreeState::ParameterAttachment (or SliderAttachment) in the editor, never in the processor.

Step 4 — Editor and UI

  • Subclass juce::AudioProcessorEditor; call setSize(w, h) in the constructor.
  • Override paint for background / labels; override resized to lay out components with setBounds.
  • Declare juce::Slider members; attach each via juce::AudioProcessorValueTreeState::SliderAttachment.
  • Keep all UI state in the editor — the processor must function correctly with no editor open.
  • The editor holds a reference to the processor (passed in constructor); never store a raw editor pointer in the processor.

Read the full file on GitHub · 65 lines

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. 2mo ago First seen · 65 lines · 108 tokens per session scan A e13cf9f8714a

Subscribe to this mod's changes

juce-guide is a skill published in the GitHub repository kunitoki/sonic-skills (23 stars, last pushed 5mo ago), licensed Unlicense. It adds 108 tokens to every session and 975 once invoked, about $0.0004 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.

Related

juce-guide compared with skills from other repositories

juce-guide next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
juce-guidekunitoki/sonic-skillsSkill235mo agoUnlicenseA108Claude Code, Codex
coding-guidance-qtn-n-code/n-n-code-skillsSkill45d agoMITA67Claude Code, Codex
coding-guidance-cppn-n-code/n-n-code-skillsSkill45d agoMITA72Claude Code, Codex
cpp-proJeffallan/claude-skillsSkill12k7d agoMITA79Claude Code
embedded-stm32Mindrally/skillsSkill29729d agoApache-2.0A87Claude Code
cppMindrally/skillsSkill29729d agoApache-2.0A23Claude Code
backend-developmentMindrally/skillsSkill29729d agoApache-2.0A31Claude Code