cinematic-3d-battle-engine: Instructions file for Codex

AGENTS.md

cinematic-3d-battle-engine AGENTS.md is an instructions file for Codex, OpenCode from keithligh/cinematic-3d-battle-engine. It costs 2,809 tokens per session, scanned A, original, MIT.

Project instructions for creating historically accurate, self-playing documentary battles in the cinematic-3d-battle-engine. They require real sources for dates, places, forces, commanders, and events, and record uncertainty instead of guessing.

In plain words
What is it for?
Use them when forking the template to create a new historical battle, including its researched data, direction, languages, fonts, and visual style.
Why use it?
They prevent an AI coding agent from inventing historical details while filling in a battle scenario. A validator also requires sources before the battle can start.

Instructions file for CodexOpenCode

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

This is keithligh/cinematic-3d-battle-engine's own configuration. It tells Codex and OpenCode how to work on cinematic-3d-battle-engine 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 cinematic-3d-battle-engine configures →

Reuse

Borrowing it

Nothing to install: this file belongs to keithligh/cinematic-3d-battle-engine. 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/keithligh/cinematic-3d-battle-engine/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/keithligh/cinematic-3d-battle-engine

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 cinematic-3d-battle-engine AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/keithligh/cinematic-3d-battle-engine/agents-md.svg)](https://agentmods.dev/instructions/keithligh/cinematic-3d-battle-engine/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/keithligh/cinematic-3d-battle-engine/agents-md"><img src="https://agentmods.dev/badge/instructions/keithligh/cinematic-3d-battle-engine/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,809 This file is loaded in full into every session.
When invoked 2,809 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 $0.02809 $0.02809
Opus 5 $0.01404 $0.01404
Sonnet 5 $0.00562 $0.00562
Haiku 4.5 $0.00281 $0.00281

Measured 8d ago against content hash a74edf41bd26, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

cinematic-3d-battle-engine 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 8d 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 · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md: forking a new battle with an AI agent

This file is the runbook for an AI coding agent (and the human directing it) to fork this template into a new historical battle. Read it fully before starting. The companion references are PLAYBOOK.md (the field-by-field data schema) and data.example.js (a minimal working skeleton to copy).


The one rule that overrides everything: do not fabricate history

This template renders a self-playing documentary. A documentary's worth is its truth. So:

  • Research and cite real sources first. Before writing any data, gather the real date window, the opposing sides and their forces/commanders, the real geography (place names + coordinates), and the sequence of events, each tied to a source you can name.
  • Never invent a unit, a date, a movement, or a position to fill a gap. If a fact is unknown or disputed, say so in notes.caveats. Do not paper over it with a plausible-sounding guess. A beautiful fabricated battle is worthless.
  • The engine enforces this: notes.sources is a required field, and the boot validator refuses to start a battle without it. That is a floor, not a substitute for honest sourcing.

If you cannot source a battle to this standard, stop and tell the human. Do not proceed.

Fictional battles: welcome, and held to the same standard

The engine renders fictional battles too (the bundled Example Battle is one), and a fiction does not break the rule above. The line is simple: the rule forbids passing invention off as real history, not invention itself. A fictional battle is fine as long as it is honest about being fictional and is built with the same care as a real one:

  • Declare it fictional. Say so plainly in notes (the Example Battle's notes.sources reads "FICTIONAL DEMONSTRATION SCENARIO", which also satisfies the required non-empty sources). Never dress a fiction up as real history, and never attach a real battle's name, date, or place to invented events.
  • Stay true to the source material. A fiction still has a source: a novel, a film, a game, an alternate-history premise, or its own established canon. Be accurate to THAT. This is fictional historical accuracy: period-plausible, internally consistent, and faithful to the world it depicts, with the same craft a real battle gets. A lazy, self-contradicting fiction is as worthless as a fabricated history.

Read the full file on GitHub · 155 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. 8d ago First seen · 155 lines · 2,809 tokens per session scan A a74edf41bd26

Subscribe to this mod's changes

cinematic-3d-battle-engine AGENTS.md is an instructions file published in the GitHub repository keithligh/cinematic-3d-battle-engine (11 stars, last pushed 2mo ago), licensed MIT. It adds 2,809 tokens to every session, about $0.0140 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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens