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/microsoft/vscode/learningsgit clone --depth 1 https://github.com/microsoft/vscodeWhat 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 | $0.00225 | $0.00225 |
| Opus 5 | $0.00112 | $0.00112 |
| Sonnet 5 | $0.00045 | $0.00045 |
| Haiku 4.5 | $0.00022 | $0.00022 |
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- nyrve learnings.instructions.md — 100% identical, 0 lines differ
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
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.
- yesterday First seen · 28 lines · 225 tokens per session scan A 9c9af2e42865
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.
Other instructions, from other repositories
vscode-peacock AGENTS.md
Instructions for johnpapa/vscode-peacock, covering peacock — agent guide, project overview, repository structure, tech stack and build & run.
vscode-peacock copilot-instructions.md
Instructions for johnpapa/vscode-peacock, covering copilot instructions — peacock, project type, typescript conventions, vs code extension patterns and color handling.
code-by-wire CLAUDE.md
Instructions for luojiahai/code-by-wire, covering claude.md, development, website, architecture and code style.
swob AGENTS.md
Instructions for IvyYang1999/swob, covering swob 研发协作唯一规范, 不可越过的边界, 角色与职责, 生命周期 and 分支、worktree 与提交.
clodex-ide AGENTS.md
AGENTS.md instructions for mereyabdenbekuly-ctrl/clodex-ide, covering clodex repository agent rules, open/closed product boundary, commercial product invariant, current protocol v0 phase and current authorization state.
ab900 CLAUDE.md
Instructions for timothywarner-org/ab900, covering claude.md, repository purpose, architecture, commands and 2. non-ascii punctuation -- must return zero.