agentmods.dev

Ollie: Instructions file for Claude Code

CLAUDE.md

Ollie CLAUDE.md is an instructions file for Claude Code from MedGm/Ollie. It costs 1,643 tokens per session, scanned A, original, MIT.

A project guide for Ollie, a desktop AI assistant built with a Rust application backend and a React and TypeScript interface. It documents the project layout, development commands, testing, and communication between the interface and backend.

In plain words
What is it for?
Use it when developing Ollie, especially for running the app, checking or building the frontend, checking Rust code, testing, and understanding its two-part project structure.
Why use it?
It gives coding agents the project-specific instructions they need to work in the right part of the codebase and check their changes correctly.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is MedGm/Ollie's own configuration. It tells Claude Code how to work on Ollie itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Ollie configures →

not rated 59repo +1 changed 1mo ago A scan 1,643 tokens original MIT
View source ↗ MedGm/Ollie
Reuse

Borrowing it

Nothing to install: this file belongs to MedGm/Ollie. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/MedGm/Ollie/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/MedGm/Ollie

Made for: Claude Code.

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 Ollie CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/medgm/ollie/claude-md/github.svg)](https://agentmods.dev/instructions/medgm/ollie/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/medgm/ollie/claude-md"><img src="https://agentmods.dev/badge/instructions/medgm/ollie/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for Ollie CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/medgm/ollie/claude-md"><img src="https://agentmods.dev/badge/instructions/medgm/ollie/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,643 This file is loaded in full into every session.
When invoked 1,643 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.01643 $0.01643
Opus 5.5 $0.00657 $0.00657
Sonnet 5.5 $0.00329 $0.00329
Haiku 4.5 $0.00164 $0.00164

Measured 1mo ago against content hash 95e0eba8f704, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Ollie 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 1mo 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 · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 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.

Overview

Ollie is a local-first desktop AI assistant for Linux built with Tauri v2 (Rust backend) + React 19 (TypeScript frontend). It supports local LLMs via Ollama and cloud providers (OpenAI, Anthropic, Google Gemini, GroqCloud).

Commands

Development

# Start full dev environment (Tauri launches Vite automatically)
cargo tauri dev

# Frontend only (from app/)
cd app && npm run dev

# Build for production
cargo tauri build

Frontend (from app/)

npm run lint       # ESLint
npm run build      # tsc + vite build

Backend (Rust)

cargo check        # Type-check without building
cargo clippy       # Lints
cargo test         # Run tests

Architecture

Monorepo Structure

  • app/ — React 19 + TypeScript frontend (Vite)
  • src-tauri/ — Rust backend (Tauri v2)

Communication (IPC)

Frontend calls backend via invoke('command_name', args). Real-time streaming uses Tauri events:

  • chat-chunk — streaming token
  • chat-error — stream error
  • chat-complete — stream finished
  • chat:stream-start — stream ID assigned
  • chat:cancelled — stream cancelled

Backend Layout (src-tauri/src/)

  • commands/ — Tauri command handlers: chat.rs, models.rs, db.rs, settings.rs, monitoring.rs, sys.rs, mcp.rs
  • providers/ — Multi-provider abstraction: traits.rs defines LLMProvider trait; orchestrator.rs routes to ollama.rs, openai.rs, anthropic.rs, google.rs
  • db/ — SQLite connection pool + schema (WAL mode; tables: chats, messages)
  • mcp/ — Model Context Protocol: protocol.rs (message types), transport.rs (stdio/SSE)

Frontend Layout (app/src/)

  • store/ — Zustand stores: chatStore.ts (thin state slice), settingsStore.ts, modelsStore.ts, monitoringStore.ts, mcpStore.ts, uiStore.ts, setupStore.ts
  • services/ — Business logic extracted from stores: conversationService.ts (provider resolution, context budget, API messages), persistenceService.ts (all DB invoke wrappers), streamingPipeline.ts (drip queue, event listeners, render throttle)
  • components/ — React UI components
  • routes/ — Page components: chat.tsx, models.tsx, settings.tsx
  • lib/ — Utilities: markdown.tsx (rehype pipeline), pdf.ts, shortcuts.ts (keyboard hook), export.ts (Markdown download), hooks.ts
  • types/ — TypeScript interfaces

Read the full file on GitHub · 102 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. 1mo ago Changed · +41 tokens per session 95e0eba8f704
  2. 2mo ago First seen · 102 lines · 1,602 tokens per session scan A 42676c7e1a2d

Subscribe to this mod's changes

Ollie CLAUDE.md is an instructions file published in the GitHub repository MedGm/Ollie (59 stars, last pushed 4d ago), licensed MIT. It adds 1,643 tokens to every session, about $0.0066 per session on Opus 5.5. 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

Ollie CLAUDE.md compared with instructions from other repositories

Ollie CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Ollie CLAUDE.mdMedGm/OllieInstructions file594d agoMITA1,643Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode