herakoi-web CLAUDE.md

herakoi-web CLAUDE.md is an instructions file for coding agents from herakoi/herakoi-web. It costs 1,146 tokens per session, scanned A, original, MIT.

A set of instructions for developing Herakoi, a webcam app that tracks hand positions and turns sampled image colours into sound. It describes the app’s plugin structure and development commands.

In plain words
What is it for?
Running the app, building it, checking types and style, running tests, and working on hand tracking, image-colour sampling, or sound-generation plugins.
Why use it?
It gives an agent the project’s architecture, available plugin stages, and checks to run, reducing guesswork when changing the code.

Instructions file

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/herakoi/herakoi-web/claude-md
Clone the repo
git clone --depth 1 https://github.com/herakoi/herakoi-web

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 herakoi-web CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/herakoi/herakoi-web/claude-md.svg)](https://agentmods.dev/instructions/herakoi/herakoi-web/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/herakoi/herakoi-web/claude-md"><img src="https://agentmods.dev/badge/instructions/herakoi/herakoi-web/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,146 This file is loaded in full into every session.
When invoked 1,146 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 5.1 $0.01146 $0.01146
Opus 5 $0.00573 $0.00573
Sonnet 5 $0.00229 $0.00229
Haiku 4.5 $0.00115 $0.00115

Measured 5d ago against content hash 7897291507fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

herakoi-web CLAUDE.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 5d 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.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Commands

pnpm dev          # Vite dev server (http://localhost:5173)
pnpm dev:https    # HTTPS dev server (required for camera on mobile)
pnpm build        # Production build → dist/
pnpm lint         # biome check + eslint a11y + typecheck (all three)
pnpm lint:biome:fix  # Auto-fix Biome issues (run before committing manually)
pnpm typecheck    # TypeScript only (tsc --noEmit)
pnpm test         # Full Vitest suite (--pool=threads)
pnpm commit       # Commitizen prompt for conventional commits

Run a single test file: pnpm vitest run src/plugins/detection/mediapipe/plugin.test.tsx

Architecture Overview

Herakoi is a webcam hand-tracking sonification app: MediaPipe detects hand landmarks → pixel colors at those points are sampled → colors are converted to audio via Web Audio API.

Plugin Pipeline

The app is built around a compile-time plugin system with four pipeline slots:

Slot Interface Current implementation
detection PointDetector mediapipe/ — MediaPipe Hands
sampling ImageSampler hsv/ — HSV color space sampler
sonification Sonifier oscillator/ — Web Audio oscillators
visualization (optional) debugHud/ — Canvas overlay

Data flow: Video → MediaPipe → normalized (0–1) points → pixel color samples ({h,s,v,...}) → oscillator tones → speakers.

Plugin discovery (src/engineConfig.ts): Uses import.meta.glob() to find all src/plugins/<kind>/<name>/plugin.ts(x) files at build time. The path determines the plugin's kind and id (e.g. detection/mediapipe).

Plugin isolation: Biome enforces that plugins only import from #src/core/*, #src/shared/*, or other plugins — never from shell/app code. Adding a new plugin means creating a directory under src/plugins/<kind>/<name>/ with a plugin.ts(x) entry exporting a typed plugin object.

Read the full file on GitHub · 87 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. 5d ago First seen · 87 lines · 1,146 tokens per session scan A 7897291507fe

Subscribe to this mod's changes

herakoi-web CLAUDE.md is an instructions file published in the GitHub repository herakoi/herakoi-web (5 stars, last pushed 3mo ago), licensed MIT. It adds 1,146 tokens to every session, about $0.0057 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 2026-08-31.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens