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/agentHostTesting.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/agenthosttesting)<a href="https://agentmods.dev/instructions/microsoft/vscode/agenthosttesting"><img src="https://agentmods.dev/badge/instructions/microsoft/vscode/agenthosttesting/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/agenthosttesting"><img src="https://agentmods.dev/badge/instructions/microsoft/vscode/agenthosttesting.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 | $0.00710 | $0.00710 |
| Opus 5.5 | $0.00284 | $0.00284 |
| Sonnet 5.5 | $0.00142 | $0.00142 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
vscode agentHostTesting.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 13d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Host
The agent host communicates via the Agent Host Protocol. The specification for this lives in a directory ../agent-host-protocol as a sibling of the VS Code directory.
If this directory doesn't exist, you should use the "ask questions" tool to ask the user if they want to clone [email protected]:microsoft/agent-host-protocol.git to that directory. After doing so, you should also prompt the user to add file:///<path/to/agent-host-protocol>/plugins/copilot-plugin as a plugin in their chat.pluginLocations settings.
Overall Protocol
The sessions process is a portable, standalone server that multiple clients can connect to. Clients see a synchronized view of sessions and can send commands that are reflected back as state-changing actions. The protocol is designed around four requirements:
- Synchronized multi-client state — an immutable, redux-like state tree mutated exclusively by actions flowing through pure reducers. While there is the option to implement functionality via imperative commands, we ALWAYS prefer to model features as pure state and actions.
- Lazy loading — clients subscribe to state by URI and load data on demand. The session list is fetched imperatively. Large content (images, long tool outputs) is stored by reference and fetched separately.
- Write-ahead with reconciliation — clients optimistically apply their own actions locally, then reconcile when the server echoes them back alongside any concurrent actions from other clients or the server itself.
- Forward-compatible versioning — newer clients can connect to older servers. A single protocol version number maps to a capabilities object; clients check capabilities before using features.
See the agent host protocol documentation for more details.
Service Construction
Read src/vs/platform/agentHost/node/serviceBootstrapping.md before adding or moving a node Agent Host service. It is the canonical guide for service placement, static constructor arguments, activation, test overrides, and disposal ownership.
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.
- 13d ago Changed · +2 lines · +54 tokens per session 3ccb1cf0918e
- 1mo ago Changed · +1 lines · +81 tokens per session b6b8a63eeb81
- 1mo ago First seen · 39 lines · 575 tokens per session scan A d89031b9b5a2
vscode agentHostTesting.instructions.md is an instructions file published in the GitHub repository microsoft/vscode (193,657 stars, last pushed today), licensed MIT. It adds 710 tokens to every session, about $0.0028 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 2026-08-30.
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.