vscode learnings.instructions.md

A meta-instruction for recording reusable lessons from mistakes or corrections in instruction files.

In plain words
What is it for?
Use it when someone asks the agent to learn from a conversation and add the lesson to the appropriate instruction file.
Why use it?
It gives a consistent way to turn a recent problem and its solution into guidance for future work.

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/microsoft/vscode/learnings
Clone the repo
git clone --depth 1 https://github.com/microsoft/vscode

Made for: GitHub Copilot.

Per session 225 This file is loaded in full into every session.
When invoked 225 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 $0.00225 $0.00225
Opus 5 $0.00112 $0.00112
Sonnet 5 $0.00045 $0.00045
Haiku 4.5 $0.00022 $0.00022

Measured yesterday against content hash 9c9af2e42865, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vscode learnings.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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.github/instructions/learnings.instructions.md · 28 lines

What it actually says

This document describes how to deal with learnings that you make. It is a meta-instruction file.

Structure of learnings:

  • Each instruction file has a "Learnings" section.
  • Each learning has a 1-4 sentences description of the learning.

Example:

## Learnings
* Prefer `const` over `let` whenever possible
* Avoid `any` type

When the user tells you "learn!", you should:

  • extract a learning from the recent conversation
    • identify the problem that you created
    • identify why it was a problem
    • identify how you were told to fix it/how the user fixed it
    • reflect over it, maybe it can be generalized? Avoid too specific learnings.
  • create a learning (1-4 sentences) from that
    • Write this out to the user and reflect over these sentences
    • then, add the reflected learning to the "Learnings" section of the most appropriate instruction file
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 · 28 lines · 225 tokens per session scan A 9c9af2e42865

Subscribe to this mod's changes

vscode learnings.instructions.md is an instructions file published in the GitHub repository microsoft/vscode (190,061 stars, last pushed yesterday), licensed MIT. It adds 225 tokens to every session, about $0.0011 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 2026-08-30.