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.
npx agentmods add instructions/bisonbet/bisonnotes-ai/claude-mdgit clone --depth 1 https://github.com/bisonbet/BisonNotes-AIWrote 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.
[](https://agentmods.dev/instructions/bisonbet/bisonnotes-ai/claude-md)<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>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.
| Model | Per session | Once 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 |
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.
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.xcodeprojin 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
- Audio Recording →
AudioRecorderViewModel→ Core Data viaCoreDataManager - Transcription →
EnhancedTranscriptionManager→ Core Data - AI Processing → Various AI engines → Core Data
- Background Processing →
BackgroundProcessingManager→ 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.
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.
- today Changed · +14 lines · +778 tokens per session fdb6d0eb55c8
- 5d ago First seen · 165 lines · 2,727 tokens per session scan A 47208164c6c4
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.
Other instructions, from other repositories
MarkdownView AGENTS.md
Instructions for keitaoouchi/MarkdownView, covering agents, technical components, relationships (data/event flow overview), extension points (overview) and platform / distribution.
droidconKeKotlin AGENTS.md
AGENTS.md instructions for droidconKE/droidconKeKotlin, covering agents.md, commands, module layout, stack and conventions.
skills copilot-instructions.md
Instructions for dhruvanbhalara/skills, covering project instructions & best practices, core tech stack, coding standards, architecture & data and ui & ux (design system).
compose-android-template CLAUDE.md
Claude Code instructions for ashtanko/compose-android-template, a project described as: 📱 A simple GitHub template to quickly set up an Android project using Kotlin and Jetpack Compose, getting you up and running in just seconds. Perfect for starting new apps with modern Android UI.
intentflow-ios AGENTS.md
Instructions for emrecanozturk/intentflow-ios, covering agent instructions, read first, architecture rules, commands and token budget.
swift-kmp-skill AGENTS.md
Instructions for sorunokoe/swift-kmp-skill, covering agents.md — swift-kmp, what this repository is, repository structure, how to apply this skill and skill loading order.