nyrve api-version.instructions.md

Rules for changing proposed VS Code APIs, which are experimental interfaces that may later become public or change.

In plain words
What is it for?
Use it when editing vscode.proposed API definition files, especially for chat or language-model features.
Why use it?
It helps keep API version numbers and extension declarations aligned when a change breaks compatibility.

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

Made for: GitHub Copilot.

Per session 263 This file is loaded in full into every session.
When invoked 263 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 $0.00263 $0.00263
Opus 5 $0.00131 $0.00131
Sonnet 5 $0.00053 $0.00053
Haiku 4.5 $0.00026 $0.00026

Measured yesterday against content hash d2e102d5267e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nyrve api-version.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 yesterday.

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/instructions/api-version.instructions.md · 19 lines

What it actually says

The following is only required for proposed API related to chat and languageModel proposals. It's optional for other proposed API, but recommended.

When a proposed API is changed in a non-backwards-compatible way, the version number at the top of the file must be incremented. If it doesn't have a version number, we must add one. The format of the number like this:

// version: 1

No semver, just a basic incrementing integer. See existing examples in vscode.proposed.chatParticipantPrivate.d.ts (version 12), vscode.proposed.chatProvider.d.ts (version 4), and other chat/languageModel proposals. The corresponding version number in the extension's package.json must be incremented to match (you could remind the user of this if you don't have access to the extension code yourself).

An example of a non-backwards-compatible change is removing a non-optional property or changing the type to one that is incompatible with the previous type.

An example of a backwards-compatible change is an additive change or deleting a property that was already optional.

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. yesterday First seen · 19 lines · 263 tokens per session scan A d2e102d5267e

Subscribe to this mod's changes

nyrve api-version.instructions.md is an instructions file published in the GitHub repository malwarebo/nyrve (5 stars, last pushed 2mo ago), licensed MIT. It adds 263 tokens to every session, about $0.0013 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.