agentmods.dev

app.spectrum.analyzer javascript.instructions.md

Project-specific JavaScript coding rules for Spectrum Analyzer for the Browser, an application that analyzes sound in a web browser. They define how the code should be organized, formatted, documented, and styled.

In plain words
What is it for?
Use them when changing the application's startup, user-interface wiring, audio handling, spectrogram drawing, note overlays, colors, utilities, or exported functions.
Why use it?
They keep related code responsibilities separate and make changes easier to review and maintain. They also prevent unfinished interface paths from being treated as complete features.

Instructions file for GitHub Copilot

21 5mo ago A scan 179 tokens original MIT
View the source file polarity/app.spectrum.analyzer
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.

agentmods
npx agentmods add instructions/polarity/app.spectrum.analyzer/javascript
Clone the repo
git clone --depth 1 https://github.com/polarity/app.spectrum.analyzer

Made for: GitHub Copilot.

Per session 179 This file is loaded in full into every session.
When invoked 179 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00179 $0.00179
Opus 5 $0.00089 $0.00089
Sonnet 5 $0.00036 $0.00036
Haiku 4.5 $0.00018 $0.00018

Measured 2d ago against content hash 2d134f1ec10c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

app.spectrum.analyzer javascript.instructions.md 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 2d 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.

.github/instructions/javascript.instructions.md · 17 lines

What it actually says

JavaScript Instructions

  • Follow StandardJS conventions used by the repo: 2-space indentation and no semicolons.
  • Keep responsibilities separated:
    • main.js for bootstrap and sizing
    • uiController.js for DOM wiring
    • audioHandler.js for Web Audio lifecycle
    • spectrogramRenderer.js for drawing and note overlay behavior
    • colorThemes.js and utils/ for reusable helpers
  • Add or maintain JSDoc for exported functions and non-obvious logic.
  • Prefer small, focused functions and avoid duplicating logic across modules.
  • Do not document or expose unfinished UI paths as stable features without checking the DOM and runtime behavior.
  • When visual token work begins, avoid hard-coding new palette values in JavaScript if the same value belongs in CSS.
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. 2d ago First seen · 17 lines · 179 tokens per session scan A 2d134f1ec10c

Subscribe to this mod's changes

app.spectrum.analyzer javascript.instructions.md is an instructions file published in the GitHub repository polarity/app.spectrum.analyzer (21 stars, last pushed 5mo ago), licensed MIT. It adds 179 tokens to every session, about $0.0009 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 2026-08-30.

Browser automationCreative and mediaLanguagesaudio-visualizer
Related

Other instructions, from other repositories

hyperframes AGENTS.md

Instructions for heygen-com/hyperframes, covering hyperframes, skills, build & test, linting & formatting and composition validation.

heygen-com/hyperframes · 1,468 tokens

librosa AGENTS.md

Instructions for librosa/librosa, covering agent interaction policy for librosa, 1. automated platform interactions, 2. exception for project-authorized automation and 3. machine-readable directive.

librosa/librosa · 212 tokens

tilawa AGENTS.md

Instructions for yazinsai/tilawa, covering tilawa, layout, sdk architecture, public surface (@tilawa/core) and build & test the sdk.

yazinsai/tilawa · 1,281 tokens

elah AGENTS.md

Instructions for elahlabs/elah, covering agents.md, what this is, layout, commands and the export worker.

elahlabs/elah · 1,568 tokens

gmc64 CLAUDE.md

Instructions for needlestack/gmc64, covering gmc64 technical documentation, quick reference, project structure, architecture decisions and data architecture & serialization.

needlestack/gmc64 · 11,120 tokens

autodoubao AGENTS.md

AGENTS.md instructions for linxxcat000/autodoubao, covering autodoubao project instructions, durable context, using the mcp, browser constraints and verification.

linxxcat000/autodoubao · 667 tokens