Borrowing it
Nothing to install: this file belongs to sushiHex/vram-mcp. 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/sushiHex/vram-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/sushiHex/vram-mcpWrote 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/sushihex/vram-mcp/agents-md)<a href="https://agentmods.dev/instructions/sushihex/vram-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sushihex/vram-mcp/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/sushihex/vram-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sushihex/vram-mcp/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 | $0.00749 | $0.00749 |
| Opus 5.5 | $0.00300 | $0.00300 |
| Sonnet 5.5 | $0.00150 | $0.00150 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
vram-mcp 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
vram_mcp/contains the Python package.server.pyexposes MCP tools;core.pycoordinates VRAM decisions. Keep MCP imports confined toserver.py.gpu.py,nvml.py,procinfo.py,ollama.py, andollama_correlate.pycollect and correlate GPU, process, and model data.wddm.pyreads the selected GPU's non-local memory and samples its driver paging on Windows, through ctypes.winproc.pyreads Windows process names and command lines through ctypes.claims.pymanages shared claims/reservations;audit.pyrecords events and samples;_util.pyholds shared helpers.tests/test_*.pymirrors package modules. Design specifications and implementation plans live underdocs/superpowers/. Packaging is configured inpyproject.toml; CI lives in.github/workflows/ci.yml, and publishing a GitHub Release builds, attaches, and uploads to PyPI through.github/workflows/release.yml, whose build also runs on every pull request (seedocs/releasing.md).
Build, Test, and Development Commands
Use Python 3.10+ in a virtual environment.
python -m pip install -e ".[dev]"installs the editable package and pytest.python -m pytest -qruns the full suite, matching CI.python -m pytest tests/test_core.py -qruns a focused module suite.python -m pip wheel --no-deps . -w distbuilds a wheel using Hatchling.vram-mcpstarts the MCP stdio server, normally launched by an MCP client. Local model operations require a reachable Ollama instance.
Coding Style & Naming Conventions
Follow existing Python style: four-space indentation, snake_case functions/modules, PascalCase classes, and UPPER_CASE constants. Use type hints and concise docstrings for contracts and non-obvious behavior. No formatter or linter is configured; avoid unrelated formatting changes.
Keep core logic injectable and testable. MCP tools are asynchronous; dispatch blocking HTTP, subprocess, NVML, and file operations through anyio.to_thread.run_sync. Preserve explicit unknown/null readings when telemetry is unavailable.
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 Changed · +28 tokens per session cb740da7fb59
- 5d ago Changed · +112 tokens per session a861467bd96e
- 12d ago First seen · 36 lines · 609 tokens per session scan A 7b46244f7e8e
vram-mcp AGENTS.md is an instructions file published in the GitHub repository sushiHex/vram-mcp (0 stars, last pushed 4d ago), licensed MIT. It adds 749 tokens to every session, about $0.0030 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 2026-10-08.
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).
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.