factorio-ai-companion: Instructions file for Codex

AGENTS.md

factorio-ai-companion AGENTS.md is an instructions file for Codex, OpenCode from lveillard/factorio-ai-companion. It costs 180 tokens per session, scanned A, original, MIT.

Repository instructions for an AI companion project that connects Factorio, a factory-building game, to coding-agent tools through RCON, a remote-control interface.

In plain words
What is it for?
Use them when changing commands, settings, gameplay behavior, transport code, or tests in this Factorio project.
Why use it?
They give the coding agent project-specific rules for where changes belong, how to generate shared contracts, and how to test without using a player's save.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions Codex.

This is lveillard/factorio-ai-companion's own configuration. It tells Codex and OpenCode how to work on factorio-ai-companion 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 factorio-ai-companion configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lveillard/factorio-ai-companion. 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/lveillard/factorio-ai-companion/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/lveillard/factorio-ai-companion

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 factorio-ai-companion AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/lveillard/factorio-ai-companion/agents-md"><img src="https://agentmods.dev/badge/instructions/lveillard/factorio-ai-companion/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 180 This file is loaded in full into every session.
When invoked 180 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.00180 $0.00180
Opus 5.5 $0.00072 $0.00072
Sonnet 5.5 $0.00036 $0.00036
Haiku 4.5 $0.00018 $0.00018

Measured 1mo ago against content hash 510a9beaffa4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

factorio-ai-companion 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 1mo 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.

AGENTS.md · 9 lines

What it actually says

Working on this repository

  • Use Bun and the checked-in bun.lock.
  • Add/change tools in config/commands.json, then their named-argument Lua handlers. bun run generate updates the shared contract. Do not add positional commands or compatibility aliases.
  • Environment settings belong in config/settings.ts; gameplay tuning belongs in config/gameplay.json. Release version comes from package.json.
  • Keep game actions in Lua, transport serialization in GameBridge/RCON, and Codex orchestration in CompanionSession. Browser forms and model tools derive from the same schema.
  • Run bun run check and the relevant integration smoke tests. Game tests must use disposable worlds. Never test against a user's save implicitly.
  • Do not commit .local, .env, credentials, runtime logs, generated bundles or personal .claude/settings.local.json changes.
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. 1mo ago First seen · 9 lines · 180 tokens per session scan A 510a9beaffa4

Subscribe to this mod's changes

factorio-ai-companion AGENTS.md is an instructions file published in the GitHub repository lveillard/factorio-ai-companion (14 stars, last pushed 1mo ago), licensed MIT. It adds 180 tokens to every session, about $0.0007 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 2026-09-13.

Related

factorio-ai-companion AGENTS.md compared with instructions from other repositories

factorio-ai-companion AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
factorio-ai-companion AGENTS.mdlveillard/factorio-ai-companionInstructions file141mo agoMITA180Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode