civ6-mcp: Instructions file for Codex

AGENTS.md

civ6-mcp AGENTS.md is an instructions file for Codex, OpenCode from lmwilki/civ6-mcp. It costs 5,814 tokens per session, scanned A, original, MIT.

A set of instructions for an AI agent playing Civilization VI through a game-control server. It explains the map coordinates, how to start, how to inspect game information, and how to take turns.

In plain words
What is it for?
Use it to guide an agent through Civilization VI turns, including reading the empire state, planning actions, moving units, and ending turns.
Why use it?
The agent cannot automatically see everything a human player notices, so the instructions tell it what information to request and check. They reduce mistakes caused by missing game state.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is lmwilki/civ6-mcp's own configuration. It tells Codex and OpenCode how to work on civ6-mcp 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 civ6-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lmwilki/civ6-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.

Copy the file
curl -O https://raw.githubusercontent.com/lmwilki/civ6-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/lmwilki/civ6-mcp

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 civ6-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lmwilki/civ6-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/lmwilki/civ6-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/lmwilki/civ6-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/lmwilki/civ6-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.

agentmods 80×15 button for civ6-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/lmwilki/civ6-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/lmwilki/civ6-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,814 This file is loaded in full into every session.
When invoked 5,814 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 $0.05814 $0.05814
Opus 5 $0.02907 $0.02907
Sonnet 5 $0.01163 $0.01163
Haiku 4.5 $0.00581 $0.00581

Measured 9d ago against content hash 40c32a6e3556, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

civ6-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 9d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 319 lines

How it starts

The opening of the file, as written. The whole thing — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Civ 6 MCP — Agent Reference

An MCP server connecting to a live Civilization VI game via FireTuner. You can read full game state and issue commands. All commands respect game rules.

You only know what you explicitly query. A human player passively absorbs the score ticker, religion lens, unit health bars — you have none of that. Information you don't ask for simply doesn't enter your world model. The patterns below exist to compensate for this.

end_turn now runs empire warnings automatically — alerts for loyalty crises, idle trade routes, gold deficits, resource caps, scoreboard position, and military imbalance. These compensate for the most common blind spots, but don't replace periodic deep checks (victory progress, religion spread, diplomacy).

Coordinate System

Hex grid: (X, Y) where higher Y = visually south.

  • Y increases → south (down). Y decreases → north (up).
  • X increases → east. X decreases → west.
  • Moving from (9,24) to (9,26) is south, not north.

Game Start

Before your first turn:

  1. Read your civ's unique abilities, units, and buildings — what is this civ designed to do?
  2. Identify the tech/civic that unlocks your unique unit; plan a research path to reach it.
  3. Form a working hypothesis for a victory path. Hold it loosely — geography and rivals will clarify things through the Classical era.

Early choices compound. Each decision shapes what's available 20, 40, 60 turns later. A scout reveals the map early; a defensive unit lets your settlers move safely; more cities mean more districts which mean more everything. Religious civs often benefit from Holy Site infrastructure before the Great Prophet pool fills. What you don't build early, you pay for later.

Turn Loop

Each turn in order:

  1. get_game_overview — turn, yields, research, score, era score, difficulty. If resuming after context compaction, call get_diary first.
  2. get_units — positions, HP, moves, charges, nearby threats
  3. get_map_area around cities/units — terrain, resources, enemy units
  4. Move/action each unit
  5. get_cities — queues, growth, pillaged districts
  6. get_district_advisor if placing a new district
  7. set_city_production / set_research if needed
  8. Run Strategic Checkpoints if it's time
  9. end_turn

Read the full file on GitHub · 319 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. 9d ago First seen · 319 lines · 5,814 tokens per session scan A 40c32a6e3556

Subscribe to this mod's changes

civ6-mcp AGENTS.md is an instructions file published in the GitHub repository lmwilki/civ6-mcp (167 stars, last pushed 16d ago), licensed MIT. It adds 5,814 tokens to every session, about $0.0291 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.

Related

Other instructions, from other repositories

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 · 7,296 tokens

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.

openai/codex · 5,153 tokens

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 · 6,785 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 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 · 4,469 tokens

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.

deepseek-ai/deepseek-harness · 3,735 tokens