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.
curl -O https://raw.githubusercontent.com/keithligh/cinematic-3d-battle-engine/main/AGENTS.mdgit clone --depth 1 https://github.com/keithligh/cinematic-3d-battle-engineWrote 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/keithligh/cinematic-3d-battle-engine/agents-md)<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>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 | $0.02809 | $0.02809 |
| Opus 5 | $0.01404 | $0.01404 |
| Sonnet 5 | $0.00562 | $0.00562 |
| Haiku 4.5 | $0.00281 | $0.00281 |
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.
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.sourcesis 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'snotes.sourcesreads "FICTIONAL DEMONSTRATION SCENARIO", which also satisfies the required non-emptysources). 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.
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.
- 8d ago First seen · 155 lines · 2,809 tokens per session scan A a74edf41bd26
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.
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.
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.
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).
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).
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.
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.