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/selfagency/opilot/agents-mdgit clone --depth 1 https://github.com/selfagency/opilotWhat 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 | $0.02161 | $0.02161 |
| Opus 5 | $0.01081 | $0.01081 |
| Sonnet 5 | $0.00432 | $0.00432 |
| Haiku 4.5 | $0.00216 | $0.00216 |
Grade A, and why
opilot AGENTS.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 2d 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.
This is a copy
100% identical to opilot copilot-instructions.md — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions: Visual Studio Code Extension Integrating Ollama into GitHub Copilot Chat
Welcome! This document guides you through the recommended workflows, conventions, and tooling when working on the Opilot VS Code extension project. Follow these instructions strictly to ensure consistency, quality, and smooth collaboration.
Before Starting Work
- Create or switch to the correct branch before editing code.
- Branch name format:
[type]/[short-title](e.g.,feat/add-ollama-integration).
Project Overview
You are working on the Opilot extension, which integrates Ollama models into GitHub Copilot Chat inside VS Code.
Key Features to Keep in Mind
- Local and cloud Ollama model usage inside Copilot Chat.
- Custom Ollama sidebar for model management.
@ollamachat participant for dedicated conversations.- Inline code completions using local models.
- Modelfile creation, editing, and building with syntax support.
- Streaming responses and vision model support.
- Local execution for privacy.
- Configuration via VS Code settings.
Development Environment Setup
-
Prerequisites:
- Node.js 20+
- pnpm (version pinned in
package.json) - VS Code 1.109.0 or higher
- GitHub Copilot Chat extension installed
- Ollama installed locally or remote access configured
-
Installing Ollama:
- Download from https://ollama.ai/download
- Start Ollama app or run
ollama serve - Login to Ollama Cloud if using cloud models (
ollama login)
-
Extension Installation:
- Install from VS Code Marketplace or
.vsixfile
- Install from VS Code Marketplace or
Code Quality Standards
This project uses Ultracite, a zero-config preset built on Biome that enforces strict code quality standards through automated formatting and linting. The project has migrated from oxlint/oxfmt to Biome via Ultracite, so check-formatting and format tasks are no longer needed — ultracite check and ultracite fix cover both linting and formatting in a single command.
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.
- 2d ago First seen · 252 lines · 2,161 tokens per session scan A 90e512a39f57
opilot AGENTS.md is an instructions file published in the GitHub repository selfagency/opilot (90 stars, last pushed 1mo ago), licensed MIT. It adds 2,161 tokens to every session, about $0.0108 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to opilot copilot-instructions.md, differing in 2 lines, and is treated as a copy.
Other instructions, from other repositories
witsy copilot-instructions.md
Copilot instructions for Kochava-Studios/witsy, covering witsy ai assistant - developer guide, project overview, architecture & key components, core structure and build system (electron forge + vite).
witsy AGENTS.md
AGENTS.md instructions for Kochava-Studios/witsy, covering witsy ai assistant - developer guide, project overview, architecture & key components, core structure and build system (electron forge + vite).
witsy CLAUDE.md
Claude Code instructions for Kochava-Studios/witsy, covering witsy ai assistant - developer guide, project overview, architecture & key components, core structure and build system (electron forge + vite).
kilocode AGENTS.md
AGENTS.md instructions for Kilo-Org/kilocode, covering agents.md, build and dev, quality checks, products and package instructions.
ollama CLAUDE.md
Claude Code instructions for ollama/ollama: See AGENTS.md for the shared agent instructions for this repository.
getspecstory copilot-instructions.md
Instructions for specstoryai/getspecstory: Examine the file changes for the pull request.