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/supremehui/-auto-accounting/gemini-mdgit clone --depth 1 https://github.com/supremehui/-Auto-AccountingWrote 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/supremehui/-auto-accounting/gemini-md)<a href="https://agentmods.dev/instructions/supremehui/-auto-accounting/gemini-md"><img src="https://agentmods.dev/badge/instructions/supremehui/-auto-accounting/gemini-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 5.1 | $0.01163 | $0.01163 |
| Opus 5 | $0.00581 | $0.00581 |
| Sonnet 5 | $0.00233 | $0.00233 |
| Haiku 4.5 | $0.00116 | $0.00116 |
Grade A, and why
-Auto-Accounting GEMINI.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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PinMe - Intelligent Screen Capture & Extraction
Project Overview
PinMe (supreme) is an Android application designed to intelligently capture screen content and extract key information (e.g., pickup codes, train tickets, verification codes) using Vision Large Language Models (LLMs). The extracted information is then presented via Meizu Flyme's Live Notifications (Capsule) or a standard Android AppWidget for quick access.
Technology Stack
- Language: Kotlin
- UI Framework: Jetpack Compose (Material3)
- Architecture: Modern Android Architecture (Compose + Room + Coroutines)
- Database: Room (SQLite abstraction)
- Networking: OkHttp (for LLM API communication)
- AI/LLM Integration: OpenAI-compatible API client (supports Zhipu AI, SiliconFlow, Custom)
- Key Android APIs:
MediaProjection: For screen capture.AccessibilityService: For silent/background capture.Glance: For building AppWidgets with Compose-like syntax.NotificationManager: For system and Flyme-specific notifications.
Project Structure
app/src/main/java/com/brycewg/pinme/
├── Constants.kt # App-wide constants (Prefs keys, LLM defaults)
├── MainActivity.kt # Main entry point / Configuration UI
├── capture/ # Screen capture logic
│ ├── CaptureActivity.kt # Foreground capture (MediaProjection)
│ ├── Accessibility... # Background/Silent capture service
│ └── QuickCaptureTile... # Quick Settings Tile implementation
├── db/ # Room Database definitions
│ ├── AppDatabase.kt # Database holder
│ ├── Entity.kt # Data models (ExtractEntity, PreferenceEntity)
│ └── PinMeDao.kt # Data Access Objects
├── extract/ # Core Business Logic
│ ├── ExtractWorkflow.kt # Orchestrates Capture -> LLM -> DB flow
│ └── ExtractParsing.kt # Parses LLM JSON response
├── notification/ # Notification handling
│ └── UnifiedNotification... # Handles Flyme Live Capsules & Standard Notifs
├── ui/ # Jetpack Compose UI
│ ├── components/ # Reusable UI elements
│ ├── layouts/ # Screen layouts (Settings, Home, etc.)
│ └── theme/ # Theme definitions
├── vllm/ # LLM Client Network Layer
│ └── VllmClient.kt # OkHttp client for OpenAI-compatible APIs
└── widget/ # Home Screen Widget
└── PinMeWidget.kt # Glance AppWidget implementation
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 First seen · 109 lines · 1,163 tokens per session scan A 187e476c15b1
-Auto-Accounting GEMINI.md is an instructions file published in the GitHub repository supremehui/-Auto-Accounting (7 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 1,163 tokens to every session, about $0.0058 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 2026-09-04.
Other instructions, from other repositories
onnx2coreml AGENTS.md
Instructions for devin-lai/onnx2coreml, covering developer guide for onnx2coreml, what this is, architecture (one pass through the pipeline), adding an operator lowering and testing.
Swift-Foundation-Models-Skills AGENTS.md
Instructions for sambitcreate/Swift-Foundation-Models-Skills, covering apple foundation models skills repository, skills overview, core session management, structured generation and tools & system integration.
tachyon CLAUDE.md
Claude Code instructions for kpavlov/tachyon, a project described as: 💫 Tachyon MCP Runtime for Java and Kotlin - Model Context Protocol (MCP) server with Streamable HTTP, native Netty transports, tools, tasks, resources, prompts, completions, resumable sessions, and stateless deployment support.
flutter-ai-skills CLAUDE.md
Claude Code instructions for smurzaliev/flutter-ai-skills, covering flutter ai skills by samat — claude code skill pack, what is this?, quick reference, commands (use with / prefix) and key skills.
GPT-RAG release.instructions.md
Instructions for Azure/GPT-RAG, a project described as: Enterprise-grade accelerator for agentic RAG on Azure. Built on Microsoft Foundry with Foundry IQ as the default retrieval backend, Microsoft Agent Framework orchestration, Zero-Trust architecture and IaC.
MobiAI-Core CLAUDE.md
Claude Code instructions for ArisGuimera/MobiAI-Core, covering mobiai — mobile development ai ecosystem, bootstrap and principles.