nyrve copilot-instructions.md

Project instructions for Nyrve, a VS Code-based code editor with built-in AI coding agents. They explain where Nyrve-specific code belongs and how it should extend the underlying editor.

In plain words
What is it for?
Use them when implementing or modifying Nyrve features, especially code under src/nyrve/, agent behavior, context handling, editor integration, and project-specific conventions.
Why use it?
They help prevent changes from conflicting with VS Code’s core code and keep agent features, project memory, background work, and other Nyrve additions organized.

Instructions file for GitHub Copilot

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/malwarebo/nyrve/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/malwarebo/nyrve

Made for: GitHub Copilot.

Per session 3,729 This file is loaded in full into every session.
When invoked 3,729 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 $0.03729 $0.03729
Opus 5 $0.01865 $0.01865
Sonnet 5 $0.00746 $0.00746
Haiku 4.5 $0.00373 $0.00373

Measured 2d ago against content hash 869ba869381e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nyrve copilot-instructions.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.

.github/copilot-instructions.md · 256 lines

How it starts

The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Nyrve IDE — AI-Native Code Editor

What Is This Project

Nyrve is a VS Code fork with Claude's agentic coding capabilities deeply integrated into every layer of the editor. Unlike Cursor (interactive AI editing) or Copilot (AI bolted onto an existing editor), Nyrve treats the AI agent as a first-class citizen — capable of autonomous multi-file edits, background monitoring, GitHub workflow automation, and persistent project memory.

Full product specification: .claude/nyrve-spec.md Always reference this spec when implementing features. Follow the architecture, interfaces, file structure, and naming conventions defined there.

Project Architecture

Nyrve inherits VS Code's layered architecture and adds a src/nyrve/ directory for all Nyrve-specific code. Never modify VS Code core files directly unless absolutely necessary — prefer extending via contribution points and service injection.

Nyrve-Specific Code (src/nyrve/)

All new Nyrve code lives here. This is the code YOU are building:

src/nyrve/
├── agent/           # Core agent engine, orchestration, action execution (Claude models only — Opus, Sonnet, Haiku)
├── context/         # @-mention system, context builder, editor bridge
├── indexer/         # Codebase indexer (Rust native addon in indexer/native/)
├── memory/          # Session memory, auto-extraction, decay
├── github/          # GitHub API integration, PR/issue management, CI monitoring
├── ui/              # All Nyrve UI panels (agent chat, diff review, task queue, etc.)
├── api/             # Public extension API for third-party integrations
└── core/            # Config, storage, encryption, updater

VS Code Base Architecture (read-only reference)

You need to understand these but should rarely modify them:

  • src/vs/base/ — Foundation utilities and cross-platform abstractions
  • src/vs/platform/ — Platform services and dependency injection infrastructure
  • src/vs/editor/ — Text editor (Monaco) implementation
  • src/vs/workbench/ — Main application workbench
    • workbench/browser/ — Core workbench UI components (parts, layout, actions)
    • workbench/services/ — Service implementations
    • workbench/contrib/ — Feature contributions (git, debug, search, terminal, etc.)
    • workbench/api/ — Extension host and VS Code API implementation
  • src/vs/code/ — Electron main process
  • src/vs/server/ — Server implementation

Read the full file on GitHub · 256 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. 2d ago First seen · 256 lines · 3,729 tokens per session scan A 869ba869381e

Subscribe to this mod's changes

nyrve copilot-instructions.md is an instructions file published in the GitHub repository malwarebo/nyrve (5 stars, last pushed 2mo ago), licensed MIT. It adds 3,729 tokens to every session, about $0.0186 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 2026-08-31.