BisonNotes-AI CLAUDE.md

BisonNotes-AI CLAUDE.md is an instructions file for coding agents from bisonbet/BisonNotes-AI. It costs 3,505 tokens per session, scanned A, original, MIT.

A repository instruction file for BisonNotes-AI, an iOS app built with Xcode and Swift. It describes the project’s environment, build and test commands, dependencies, architecture, and Core Data storage.

In plain words
What is it for?
Use it when building, running, testing, or understanding BisonNotes-AI, including its Swift Package Manager dependencies and Core Data components.
Why use it?
It gives a coding agent the project context needed to make and verify changes safely. It also explains that app data is managed through Core Data rather than the older file-based storage.

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/bisonbet/bisonnotes-ai/claude-md
Clone the repo
git clone --depth 1 https://github.com/bisonbet/BisonNotes-AI

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 BisonNotes-AI CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/bisonbet/bisonnotes-ai/claude-md.svg)](https://agentmods.dev/instructions/bisonbet/bisonnotes-ai/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/bisonbet/bisonnotes-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/bisonbet/bisonnotes-ai/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,505 This file is loaded in full into every session.
When invoked 3,505 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 $0.03505 $0.03505
Opus 5 $0.01752 $0.01752
Sonnet 5 $0.00701 $0.00701
Haiku 4.5 $0.00350 $0.00350

Measured today against content hash fdb6d0eb55c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

BisonNotes-AI 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 today.

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 · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 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.

Current Environment Context

  • Year: 2026
  • Current iOS: iOS 26 / iPadOS 26
  • Latest Devices: iPhone models through iPhone 17 series, iPad models with M4 chips and A17 Pro

Build and Development Commands

This is an iOS application built with Xcode. Use standard Xcode commands to build, run, test, and verify changes when working in a macOS/Xcode environment:

  • Build: Open BisonNotes AI.xcodeproj in Xcode and build (⌘+B)
  • Run: Build and run on simulator or device (⌘+R)
  • Test: Run unit tests with ⌘+U
  • Clean: Clean build folder (⌘+Shift+K)

The project uses Swift Package Manager for dependencies, including Textual, FluidAudio, and MLX Swift for content rendering, transcription, and on-device AI.

Architecture Overview

Core Data Architecture

The app has migrated from legacy file-based storage to Core Data-only architecture. All data is now managed through Core Data entities:

  • CoreDataManager: Central data access layer for all entities
  • AppDataCoordinator: Unified coordinator for all data operations
  • DataMigrationManager: Handles migration from legacy storage on first launch
  • RecordingEntry: Core Data entity for audio recordings with metadata
  • TranscriptEntry: Core Data entity for transcription data
  • SummaryEntry: Core Data entity for AI-generated summaries

Key Components

Data Flow
  1. Audio RecordingAudioRecorderViewModel → Core Data via CoreDataManager
  2. TranscriptionEnhancedTranscriptionManager → Core Data
  3. AI Processing → Various AI engines → Core Data
  4. Background ProcessingBackgroundProcessingManager → Core Data

For completed Parakeet recordings, imports, and re-runs, optional Local Speaker Labels are a post-ASR enrichment step. AudioFileChunkingService.reassembleTranscript remains the single reassembly path: ASR words are reassembled with absolute timing first, then the selected local diarizer runs once against the complete source audio. Labels are off by default and never run during Live Transcription. Offline VBx is Recommended; LS-EEND DIHARD3 is Experimental and supports up to 10 speakers. A failure retains the unlabeled Parakeet transcript and surfaces a warning.

Read the full file on GitHub · 179 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. today Changed · +14 lines · +778 tokens per session fdb6d0eb55c8
  2. 5d ago First seen · 165 lines · 2,727 tokens per session scan A 47208164c6c4

Subscribe to this mod's changes

BisonNotes-AI CLAUDE.md is an instructions file published in the GitHub repository bisonbet/BisonNotes-AI (11 stars, last pushed today), licensed MIT. It adds 3,505 tokens to every session, about $0.0175 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.

Related

Other instructions, from other repositories