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/malwarebo/nyrve/notebookgit clone --depth 1 https://github.com/malwarebo/nyrveWhat 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 | $0.01105 | $0.01105 |
| Opus 5 | $0.00553 | $0.00553 |
| Sonnet 5 | $0.00221 | $0.00221 |
| Haiku 4.5 | $0.00111 | $0.00111 |
Grade A, and why
nyrve notebook.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.
This is a copy
100% identical to vscode notebook.instructions.md — 0 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Notebook Architecture
This document describes the internal architecture of VS Code's notebook implementation.
Model resolution
Notebook model resolution is handled by NotebookService. It resolves notebook models from the file system or other sources. The notebook model is a tree of cells, where each cell has a type (code or markdown) and a list of outputs.
Viewport rendering (virtualization)
The notebook viewport is virtualized to improve performance. Only visible cells are rendered, and cells outside the viewport are recycled. The viewport rendering is handled by NotebookCellList which extends WorkbenchList<CellViewModel>.
The rendering has the following steps:
- Render Viewport - Layout/render only the cells that are in the visible viewport
- Render Template - Each cell type has a template (code cell, markdown cell) that is instantiated via
CodeCellRendererorMarkupCellRenderer - Render Element - The cell content is rendered into the template
- Get Dynamic Height - Cell height is computed dynamically based on content (editor lines, outputs, etc.)
- Cell Parts Lifecycle - Each cell has lifecycle parts that manage focus, selection, and other state
Cell resize above viewport
When a cell above the viewport is resized (e.g., output grows), the viewport needs to be updated to maintain scroll position. This is handled by tracking scroll anchors.
Cell Rendering
The notebook editor renders cells through a contribution system. Cell parts are organized into two categories via CellPartsCollection:
- CellContentPart - Non-floating elements rendered inside a cell synchronously to avoid flickering
prepareRenderCell()- Prepare model (no DOM operations)renderCell()/didRenderCell()- Update DOM for the cellunrenderCell()- Cleanup when cell leaves viewportupdateInternalLayoutNow()- Update layout per cell layout changesupdateState()- Update per cell state changeupdateForExecutionState()- Update per execution state change
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 · 109 lines · 1,105 tokens per session scan A f8f6b89cd062
nyrve notebook.instructions.md is an instructions file published in the GitHub repository malwarebo/nyrve (5 stars, last pushed 2mo ago), licensed MIT. It adds 1,105 tokens to every session, about $0.0055 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to vscode notebook.instructions.md, differing in 0 lines, and is treated as a copy.
Other instructions, from other repositories
bb AGENTS.md
AGENTS.md instructions for get-bb/bb, covering codebase guidelines, simplicity first, code comments, types and contracts and server and daemon.
vibeyard CLAUDE.md
Claude Code instructions for elirantutia/vibeyard, covering claude.md, what this is, build & run, testing and architecture.
nimbalyst AGENTS.md
AGENTS.md instructions for nimbalyst/nimbalyst: At the beginning of every AI session, read the root CLAUDE.md and any applicable package-level CLAUDE.md before taking actions.
coder CLAUDE.md
Claude Code instructions for coder/coder, a project described as: Secure environments for developers and their agents.
dockside CLAUDE.md
Instructions for newsnowlabs/dockside, covering repo notes, the dockside cli, session setup, ad-hoc http checks and integration suite invocation (local mode).
nezha AGENTS.md
AGENTS.md instructions for hanshuaikang/nezha, covering nezha — agents.md, 项目概述, 开发命令, 架构设计 and 前端(src/).