Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/praetore/cmo-scenario-generation/agents-mdgit clone --depth 1 https://github.com/praetore/cmo-scenario-generationWrote 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/praetore/cmo-scenario-generation/agents-md)<a href="https://agentmods.dev/instructions/praetore/cmo-scenario-generation/agents-md"><img src="https://agentmods.dev/badge/instructions/praetore/cmo-scenario-generation/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 | $0.09915 | $0.09915 |
| Opus 5 | $0.04958 | $0.04958 |
| Sonnet 5 | $0.01983 | $0.01983 |
| Haiku 4.5 | $0.00992 | $0.00992 |
Grade A, and why
cmo-scenario-generation 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 6d 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 — 512 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CMO scenario generation — agent instructions
Primary guide for generating Command: Modern Operations (CMO) Lua scripts. Use it to produce syntactically correct, tactically coherent scenarios. Cursor loads this file automatically from the repository root.
Language — all generated output is English. Agents and tooling must produce English only for anything that ends up in generated/ or that a player/operator reads in CMO. Do not write Dutch or other non-English prose in generated material — even when the scenario theater is the Netherlands, Norway, or another non-English country.
| English required (no exceptions) | Notes |
|---|---|
| OOB / load-file header comments | Player-visible at top of generated/<name>.lua — §4 Load file header |
Player briefings (*_briefing.txt, *_briefing.html) |
§10 — injected into load file via ScenEdit_SpecialMessage |
print() / init log lines in scenario Lua |
§6 |
New scenario templates and docs under .cursor/rules/ |
|
.cursor/rules/, scripts, Python CLI output |
CMO side names (e.g. België, Nederland) may match in-game ScenEdit_AddSide identifiers — that is not player prose. All descriptive text around them (headers, briefings, logs) stays English.
Source-only tooling lines at the top of *_src.lua (SOURCE, Preflight, CMO load, Bootstrap) are for agents; keep them English too for consistency.
Output path: Bootstrap scenarios use two local files under generated/ (all *.lua gitignored — only .gitkeep placeholders are tracked):
| File | Purpose |
|---|---|
generated/src/<name>_src.lua |
Source — edit this; preflight here; do not load in CMO |
generated/<name>.lua |
CMO load file — built by generate_scenario.py (bootstrap inlined + tree-shaked) |
Mandatory for agents (bootstrap scenarios):
-
Edit
generated/src/<name>_src.luaonly — never hand-editgenerated/<name>.lua(it is overwritten on generate). -
After every
*_src.luachange, run generate before you consider the task done or tell the user to playtest:python scripts/generate_scenario.py generated/src/<name>_src.lua -
Do not ask the user to run generate — the agent runs it.
generate_scenario.pyre-runs preflight; exit code 2 means no load file was written (fix errors first). -
Load in CMO only
generated/<name>.lua— never*_src.lua(no inlined bootstrap, wrong file for the game).
Standalone scenarios (no cmo.* helpers) remain a single generated/<name>.lua pasted into CMO’s Lua console the same way.
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.
- 6d ago First seen · 512 lines · 9,915 tokens per session scan A 7d784b0c0e58
cmo-scenario-generation AGENTS.md is an instructions file published in the GitHub repository praetore/cmo-scenario-generation (6 stars, last pushed 1mo ago), licensed MIT. It adds 9,915 tokens to every session, about $0.0496 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 2026-08-31.
Other instructions, from other repositories
unity-code-style-guide AGENTS.md
Instructions for krogh-jacobsen/unity-code-style-guide, covering agents.md — unity 6 c, project setup — edit this block, never do these — they corrupt the project, deprecated in unity 6 and if you read nothing else.
nes-php-glfw copilot-instructions.md
Instructions for oliverearl/nes-php-glfw, covering github copilot development guidelines for nes emulator, agent document source of truth, project overview, code style & standards and documentation.
game-and-watch-retro-go-sd CLAUDE.md
Claude Code instructions for sylverb/game-and-watch-retro-go-sd, covering claude.md, what this project is, build / flash workflow, architecture and three storage tiers, one elf.
base-building-trap-defense-design-agent-skill CLAUDE.md
Instructions for dungnotnull/base-building-trap-defense-design-agent-skill, covering claude.md — skill 250: base-building-trap-defense-design, skill identity, problem this skill solves, harness flow summary and sub-skills.
trident-mcp AGENTS.md
Instructions for mordor-forge/trident-mcp, covering agents.md, what this is, build and test, single-file verification and e2e tests.
unreal-mcp-additional-tools CLAUDE.md
Claude Code instructions for nodormu/unreal-mcp-additional-tools, covering claude.md, what this is, commands, architecture and transports (src/transports/).