Borrowing it
Nothing to install: this file belongs to gevico/cosim-gpu. 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/gevico/cosim-gpu/main/AGENTS.mdgit clone --depth 1 https://github.com/gevico/cosim-gpuWrote 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/gevico/cosim-gpu/agents-md)<a href="https://agentmods.dev/instructions/gevico/cosim-gpu/agents-md"><img src="https://agentmods.dev/badge/instructions/gevico/cosim-gpu/agents-md/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/gevico/cosim-gpu/agents-md"><img src="https://agentmods.dev/badge/instructions/gevico/cosim-gpu/agents-md.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 | $0.01423 | $0.01423 |
| Opus 5.5 | $0.00569 | $0.00569 |
| Sonnet 5.5 | $0.00285 | $0.00285 |
| Haiku 4.5 | $0.00142 | $0.00142 |
Grade A, and why
cosim-gpu 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 4d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cosim-gpu Agent Rules
Scope
This repository hosts the QEMU + gem5 MI300X GPU co-simulation source tree.
Reusable agent workflows are no longer stored as .claude/commands; they are
vendored in-tree under .agents/skills/ (previously the
gevico/cosim-gpu-skills submodule) and are tracked directly by this repository.
AGENTS.md contains the canonical rules. CLAUDE.md is a symbolic link to
AGENTS.md so Claude-compatible tools read the same rules.
Skill Paths
Load the matching skill before running these workflows:
- Debugging co-simulation failures:
.agents/skills/cosim-gpu-debug/SKILL.md - vHost serial interaction and GPU test runs:
.agents/skills/cosim-gpu-guest/SKILL.md - vHost disk-image edits with
guestmount:.agents/skills/cosim-gpu-disk-image-edit/SKILL.md
Do not add new project-specific command implementations under .claude/commands.
Add reusable workflows under .agents/skills/ instead, then update this mapping.
Build
All build, launch, test and check tasks are recipes in the top-level justfile
(just --list). Use the recipes instead of calling the scripts directly.
The QEMU, gem5, Rust and topology recipes run on the Host OS, or in a
temporary development container when COSIM_ENV=container (the default
outside Linux); just dev-image builds its image.
just build-all
Individual steps when needed:
just dev-image
just build-qemu
just build-gem5
just build-disk
Use just build-gem5 1 for gem5 linking if the Host is OOM-killed.
The documentation site is built with just docs (Chinese primary, English
mirror); just docs-serve previews it at http://127.0.0.1:8010/ and
just docs-check runs the bilingual and site checks.
Launch
just run-topology resources/machines/single-gpu.yaml
just run-launch
just run-launch --gem5-debug MI300XCosim
just test-gpu --all
After vHost boot, cosim-gpu-initialize.service copies the ROM and loads amdgpu.
Manual recovery:
dd if=/root/roms/mi300.rom of=/dev/mem bs=1k seek=768 count=128
modprobe amdgpu ip_block_mask=0x67 ppfeaturemask=0 dpm=0 audio=0 ras_enable=0 discovery=2
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.
- 4d ago First seen · 131 lines · 1,423 tokens per session scan A 26d250c8a90b
cosim-gpu AGENTS.md is an instructions file published in the GitHub repository gevico/cosim-gpu (95 stars, last pushed 4d ago), licensed Apache-2.0. It adds 1,423 tokens to every session, about $0.0057 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 2026-10-25.
Other instructions, from other repositories
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.