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.
git clone --depth 1 https://github.com/paulpham157/paul-s-cursor-rulesWrote 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/rules/paulpham157/paul-s-cursor-rules/core-game-mechanics-rule)<a href="https://agentmods.dev/rules/paulpham157/paul-s-cursor-rules/core-game-mechanics-rule"><img src="https://agentmods.dev/badge/rules/paulpham157/paul-s-cursor-rules/core-game-mechanics-rule/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.
<a href="https://agentmods.dev/rules/paulpham157/paul-s-cursor-rules/core-game-mechanics-rule"><img src="https://agentmods.dev/badge/rules/paulpham157/paul-s-cursor-rules/core-game-mechanics-rule.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.00692 |
| Opus 5 | $0.00000 | $0.00346 |
| Sonnet 5 | $0.00000 | $0.00138 |
| Haiku 4.5 | $0.00000 | $0.00069 |
Grade A, and why
core-game-mechanics-rule 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 11d 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.
This is a copy
86% identical to ascii-simulation-game-cursorrules-prompt-file — 150 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
- The game is based on a 10x10 grid, each square has a 10x10 grid inside of it. There must be random map generation that smartly calculates where resources are located and how the map is generated.
- The player does not control anything in the game; the player is simply an observer. Therefore, there should be logs for almost everything in the game, and it should be turn-based.
- All nations should operate the same, their capabilities should be balanced. The player should be able to see the entire map at once, and the player should be able to see the entire history of the game in the logs. There should be a way to zoom in on a specific square to see more detail.
- Nations should be able to trade resources with each other. Nations should be able to go to war with each other. Nations should be able to make peace with each other.
- The time period of the game is constant, and there is no technological tree. It takes place in ancient times.
- Nations should spawn a minimum distance away from each other.
- The entire game should be colored ASCII-based in terms of graphics.
- There should be neutral land that can be claimed by any nation. Neutral land should be randomly generated each game.
- There should be a way to view the current owner of a square. There should be a way to view the current resources of a square.
- Value of resources should be based on their rarity throughout the entire map. Nations can use gold to either buy resources or armies.
- Armies are the primary way that nations can expand their territory.
- There should be no talent tree or technology tree; nations should be balanced without the need for such a tree.
- Population should collect in towns and cities.
- Roads should connect towns and cities.
- Resources are spread throughout nations through roads.
- Nations attempt to spread their resources evenly over their territory.
- Gold is not omnipresent and must be transported using roads to the location where it is spent to build armies or develop land.
- Oceans should be randomly generated to separate continents.
- Rivers should be randomly generated to connect oceans and flow across the map vertically or horizontally.
- Rivers are a food source for the land, and farms can be built on them.
- Mountains should be randomly generated throughout the map.
- Mountains should be impassable by armies.
- Mines in mountains provide metal at 20% efficiency.
- Nations should expand towards resources that they have a low amount of and away from resources that they have a high amount of.
- Armies should spawn at the town or city that issued the order.
- Towns can only spawn a max level 3 army.
- Towns have a 3-square radius for gathering resources.
- As towns grow, their radius grows; there are 3 levels of towns and cities.
- A Nation's largest city is its capital.
- Population can only live in towns and cities.
- Resources should be spread throughout the map in a way that encourages nations to expand into new squares.
- Armies can travel across oceans at .25x speed.
- Armies can travel on rivers to move across the map at 3x speed.
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.
- 11d ago First seen · 37 lines · 0 tokens per session scan A b090df129397
core-game-mechanics-rule is a cursor rule published in the GitHub repository paulpham157/paul-s-cursor-rules (27 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 692 tokens. A static security scan graded it A with 0 findings. It is 86% identical to ascii-simulation-game-cursorrules-prompt-file, differing in 150 lines, and is treated as a copy.
Other cursor rules, from other repositories
ascii-simulation-game-cursorrules-prompt-file
Cursor rules for ASCII simulation game development.
gamemaker-gml
GameMaker Language (GML) rules for scripts, objects, events, rooms, data structures, and performance-minded game code.
dragonruby-best-practices-cursorrules-prompt-file
Cursor rules for DragonRuby development with best practices integration.
drawscape-factorio-usage
A set of coding rules for using the drawscape_factorio Python module to turn exported entity data into SVG output. It specifies the required functions, configuration values, and JSON input.
scoring-and-ranking-rules
A set of rules for scoring and ranking entries in a game or competition. Entries advance after a win, leave the pool after a loss, and receive individual rankings.
weekly-scoring-process-pseudocode
Pseudocode for a weekly scoring process, written in Chinese, that takes game results and updates the status of entries.