vCFD: Instructions file for Codex

AGENTS.md

vCFD AGENTS.md is an instructions file for Codex, OpenCode from gpu7/vCFD. It costs 2,521 tokens per session, scanned C, original, MIT.

Repository instructions for coding agents working on vCFD, a voice-controlled tool that sets up and runs OpenFOAM fluid simulations and exports results for ParaView. They describe the project's goals, boundaries, security rules, and important paths.

In plain words
What is it for?
Use them when an agent works on case setup, meshing, simulation jobs, result export, authentication, path restrictions, or destructive operations in vCFD.
Why use it?
They give an agent the project context and rules it must follow before changing code or running tools. This reduces work that conflicts with the repository's scope or safety requirements.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions subagents; mentions AGENTS.md.

This is gpu7/vCFD's own configuration. It tells Codex and OpenCode how to work on vCFD itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything vCFD configures →

View source ↗ gpu7/vCFD
Reuse

Borrowing it

Nothing to install: this file belongs to gpu7/vCFD. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/gpu7/vCFD/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/gpu7/vCFD

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for vCFD AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/gpu7/vcfd/agents-md/github.svg)](https://agentmods.dev/instructions/gpu7/vcfd/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/gpu7/vcfd/agents-md"><img src="https://agentmods.dev/badge/instructions/gpu7/vcfd/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.

agentmods 80×15 button for vCFD AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/gpu7/vcfd/agents-md"><img src="https://agentmods.dev/badge/instructions/gpu7/vcfd/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,521 This file is loaded in full into every session.
When invoked 2,521 The same file — it is already loaded in full.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02521 $0.02521
Opus 5.5 $0.01008 $0.01008
Sonnet 5.5 $0.00504 $0.00504
Haiku 4.5 $0.00252 $0.00252

Measured 7d ago against content hash aa30b9380ad4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

vCFD AGENTS.md scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

Grok permission rules in `.grok/config.toml` deny reads of `.env`, keys, and `deploy/aws/out/`. They also deny `rm -rf`, force-push, and a direct push to `master` or `main`. `delete_case` and `clean_case` are ask rules;
AGENTS.md · 259 lines

How it starts

The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — vCFD

Project rules for AI coding agents (Grok, Claude, Cursor, and others) working in this repository. Keep this file actionable. Prefer links to README.md, docs/, and SECURITY.md over duplicating long docs.

Adapted from the agent-bitcoin agent rules. Payment, Lightning, LND, and mainnet-wallet personas are omitted: this repo is an OpenFOAM controller, not a wallet.


1. Project overview and goals

vCFD is a voice-driven CFD controller. A Grok voice agent calls MCP tools that set up and run OpenFOAM cases, then summarize results and export data for ParaView.

Goals

  • Expose a small, speakable MCP tool surface for case setup, meshing, solving, and export.
  • Keep long solver runs async (job_id, then get_job_status).
  • Stay secure by default: no secrets in git, path-jailed cases, confirm flags on destructive tools, bearer auth on remote HTTP MCP.

Non-goals (unless explicitly requested)

  • Forking or patching OpenFOAM. vCFD launches OpenFOAM and edits case dictionaries.
  • Silent EC2 launch, teardown, or security-group changes.
  • Deleting or cleaning a case without confirm=true.
  • New physics templates beyond what the task asks for.

Key paths

Path Role
src/vcfd/mcp_server/server.py FastMCP tools
src/vcfd/mcp_server/foam_runner.py mock / docker / native OpenFOAM
src/vcfd/mcp_server/jobs.py Async job records under .vcfd/jobs/
src/vcfd/config.py VCFD_* settings
src/vcfd/analytics/poiseuille.py Hagen–Poiseuille checks
cases/templates/hagen_poiseuille/ Only built-in case template
cases/workspace/ Runtime cases (gitignored)
tests/ pytest against mock OpenFOAM
deploy/aws/ EC2 launch, Caddy, status, teardown
prompts/ Voice agent system prompt
scripts/ stdio dev server, Docker e2e, ParaView S3 helpers
.grok/config.toml Project MCP server + permission allow/ask/deny
.grok/sandbox.toml Opt-in sandbox profile vcfd

Read the full file on GitHub · 259 lines

Changes

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.

  1. 7d ago First seen · 259 lines · 2,521 tokens per session scan C aa30b9380ad4

Subscribe to this mod's changes

vCFD AGENTS.md is an instructions file published in the GitHub repository gpu7/vCFD (0 stars, last pushed yesterday), licensed MIT. It adds 2,521 tokens to every session, about $0.0101 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-13.

Related

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).

microsoft/vscode · 9,649 tokens

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.

vercel/next.js · 7,384 tokens

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).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

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).

microsoft/vscode · 2,731 tokens

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.

denoland/deno · 3,077 tokens