Borrowing it
Nothing to install: this file belongs to coconut-svsm/svsm. 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/coconut-svsm/svsm/main/AGENTS.mdgit clone --depth 1 https://github.com/coconut-svsm/svsmWrote 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/coconut-svsm/svsm/agents-md)<a href="https://agentmods.dev/instructions/coconut-svsm/svsm/agents-md"><img src="https://agentmods.dev/badge/instructions/coconut-svsm/svsm/agents-md.svg" alt="Measured on agentmods" 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 | $0.04005 | $0.04005 |
| Opus 5 | $0.02003 | $0.02003 |
| Sonnet 5 | $0.00801 | $0.00801 |
| Haiku 4.5 | $0.00400 | $0.00400 |
Grade A, and why
svsm AGENTS.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 7d 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 — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Introduction
SVSM is an in-guest paravisor written in Rust and designed for secure virtualization environments, primarily AMD SEV-SNP and Intel TDX. It operates at the highest privilege level within the Confidential Virtual Machine (VMPL0 on SEV-SNP).
Directory structure
The SVSM runs on bare metal as a ring-0 kernel, with optional userspace components. Important directories:
kernel/: main SVSM kernelboot/: kernel bootloader and definitionssyscall/: SVSM kernel/userspace system call definitionsuser/: SVSM userspace library and example init processtools/: general tools
Building and testing
The SVSM project is organized as a cargo workspace. Some workspace members
are built with the host toolchain and others are built for bare metal. Running
cargo build or cargo test will not necessarily work.
- Build: use
make. - Test: use
make testfor unit tests. ReadDocumentation/docs/developer/TESTING.md. - Linter: run
make clippy. - Format checks:
cargo fmt --checkworks as usual.
All of the above must run cleanly after making a set of changes. Additionally,
all unsafe blocks must have a SAFETY comment detailing why the code is safe
and/or what invariants are assumed.
Additional code documentation guidelines can be found at
Documentation/docs/developer/RUSTDOC-GUIDELINES.md.
Build recipes
The project uses custom build tools to generate an image that may be loaded
by the hypervisor. The top-level orchestrator is the xbuild tool, which is
called from the Makefile. The recipes are located in configs/. Information
about the build recipe format can be found in
Documentation/docs/installation/BUILD_RECIPES.md.
IGVM
IGVM is the image format that the build system generates and that the host
VMM accepts. It describes the memory contents of the guest at startup. The
SVSM generates the IGVM image via tools/igvmbuilder, which is orchestrated
by xbuild.
Formal verification with Verus
This repository integrates formal verification using Verus.
- Verified source files end with
*.verus.rsor*.proof.verus.rs(e.g.,address.verus.rs,alloc_perms.verus.rs). - Verification Invariants: Never bypass, alter, or strip
#![cfg_attr(verus_keep_ghost, ...)]blocks or Verus ghost specifications unless specifically instructed. Any structural change to a verified module requires re-verification by executing the Verus toolchain. - If a compiler flag or configuration change is made, ensure the
verusorverus_allfeature configurations inCargo.tomlremain valid. - Do not run any verification checks unless specifically asked OR if related code was updated.
- Usage documentation is found in
Documentation/docs/developer/VERIFICATION.md.
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.
- 7d ago First seen · 343 lines · 4,005 tokens per session scan A 5c82afeec042
svsm AGENTS.md is an instructions file published in the GitHub repository coconut-svsm/svsm (239 stars, last pushed 5d ago), licensed MIT. It adds 4,005 tokens to every session, about $0.0200 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
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.