Visual Studio Code is a code editor that supports editing, navigating, understanding, debugging, and extending software projects. Developers use it for the edit-build-debug cycle, and the catalogue add-ons provide skills, instructions, and agents for working within the editor.
Borrowing it
Nothing to install: this file belongs to microsoft/vscode. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/microsoft/vscode/main/.github/instructions/agent-host-interoperability.instructions.mdgit clone --depth 1 https://github.com/microsoft/vscodeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/microsoft/vscode/agent-host-interoperability)<a href="https://agentmods.dev/instructions/microsoft/vscode/agent-host-interoperability"><img src="https://agentmods.dev/badge/instructions/microsoft/vscode/agent-host-interoperability/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/microsoft/vscode/agent-host-interoperability"><img src="https://agentmods.dev/badge/instructions/microsoft/vscode/agent-host-interoperability.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00485 | $0.00485 |
| Opus 5.5 | $0.00194 | $0.00194 |
| Sonnet 5.5 | $0.00097 | $0.00097 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
vscode agent-host-interoperability.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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 19 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AHP interoperability
AHP clients communicate with any conforming Agent Host, not only the local VS Code Agent Host. Treat host-advertised session and chat URIs, identifiers, state, and capabilities as authoritative. Do not derive or reinterpret them using the local host's URI format, provider names, or implementation conventions. Helpers that construct IDs for the local host are not a substitute for reading IDs supplied by a remote host.
Use standard AHP fields and negotiated capabilities for shared behavior. If VS Code needs an optional extension, use a namespaced _meta value with a typed reader that validates its shape before use. Do not make the extension a requirement for other hosts, and do not use _meta to replace a standard protocol field or to justify assuming a particular host implementation.
When changing an AHP client, cover a conforming host that advertises valid but different URIs and identifiers, as well as absent optional extensions. Test the behavior at the client boundary, not only against the local VS Code host.
Native session identity
Follow the Agent Host session identity contract. Backend identities are mixed and immutable: negotiate addressing only for new allocations, never rewrite restored, discovered, adopted, or continued conversations. Keep frontend resources, session IDs, and chat fragments stable; carry the advertised provider and exact backend resource through caches and owning-connection resolution. ahp-session carries no provider identity and must never imply Copilot.
Back changes with boundary tests for both version-skew directions, mixed legacy/standard resources, reconnects, opaque advertised chats, and cache reloads. Restart tests must use fresh provider instances, and discovery/deletion tests must preserve provider/backing identity rather than equating raw IDs across providers. Scope legacy visibility to positively identified legacy VS Code connections; unmarked conforming peers must not be classified as legacy.
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.
- 10d ago Changed · +6 lines · +189 tokens per session d4ab9e03f6cb
- 20d ago First seen · 13 lines · 296 tokens per session scan A 81fcb4ec5d90
vscode agent-host-interoperability.instructions.md is an instructions file published in the GitHub repository microsoft/vscode (193,657 stars, last pushed today), licensed MIT. It adds 485 tokens to every session, about $0.0019 per session on Opus 5.5. 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 2026-09-26.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
generative-ai-for-beginners AGENTS.md
AGENTS.md instructions for microsoft/generative-ai-for-beginners, covering agents.md, project overview, setup commands, initial repository setup and clone the repository.
supabase AGENTS.md
AGENTS.md instructions for supabase/supabase, covering supabase monorepo, structure, common commands, ci and conventions.