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 rules/toasted-iron-studios/godot-agent-mcp/cursorrulesgit clone --depth 1 https://github.com/toasted-iron-studios/godot-agent-mcpWrote 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/toasted-iron-studios/godot-agent-mcp/cursorrules)<a href="https://agentmods.dev/rules/toasted-iron-studios/godot-agent-mcp/cursorrules"><img src="https://agentmods.dev/badge/rules/toasted-iron-studios/godot-agent-mcp/cursorrules.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 | $0.00894 | $0.00894 |
| Opus 5 | $0.00447 | $0.00447 |
| Sonnet 5 | $0.00179 | $0.00179 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade A, and why
cursorrules 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 5d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cursor Rules for Godot Agent MCP Project
Code Quality Standards
NO INLINE COMMENTS
- NEVER use inline comments (single # comments within function bodies)
- Inline comments indicate poor code quality and lack of experience
- If code needs explanation, refactor it into a well-named function with a docblock
- Code should be self-documenting through clear variable and function names
Commenting Standards
- ONLY use docblock comments (## comments) for function/class documentation
- Docblocks should describe WHAT the function does, not HOW it does it
- Focus on the purpose, parameters, return values, and side effects
- No redundant comments that just repeat what the code obviously does
MANDATORY DOCBLOCKS
- ALL public functions MUST have descriptive docblocks
- Docblocks must explain the function's purpose, parameters, return values, and side effects
- Private functions (starting with _) should have docblocks if their purpose isn't immediately obvious
- Include parameter types and return types in the description when helpful
- Document any exceptions or error conditions the function might encounter
Code Structure
- If logic is complex enough to "need" inline comments, extract it to a separate function
- Use descriptive variable and function names that make the code self-explanatory
- Prefer small, focused functions with clear responsibilities
- Break down complex operations into well-named helper functions
Examples of BAD commenting:
# Parse the request data <-- NEVER DO THIS
var data = parse_request(request)
# Check if user is valid <-- NEVER DO THIS
if user.is_valid():
# Process the user <-- NEVER DO THIS
process_user(user)
Examples of GOOD commenting:
## Validates user credentials and processes authentication request
## Returns true if authentication succeeds, false otherwise
func authenticate_user(credentials: Dictionary) -> bool:
var user = find_user_by_credentials(credentials)
if not user or not user.is_valid():
return false
return process_authentication(user)
## Converts raw HTTP request data into a structured request object
## Parameters:
## - raw_data: The complete HTTP request as a string
## Returns: Dictionary containing parsed headers, body, and method
## Throws: Returns error dictionary if request format is invalid
func parse_http_request(raw_data: String) -> Dictionary:
# Implementation here
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.
- 5d ago First seen · 99 lines · 894 tokens per session scan A 6fec2b9ff6cb
cursorrules is a cursor rule published in the GitHub repository toasted-iron-studios/godot-agent-mcp (11 stars, last pushed 1y ago), licensed MIT. It adds 894 tokens to every session, about $0.0045 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 cursor rules, from other repositories
08-client-server
IF 判断当前环境是否为客户端 → FabricLoader.getInstance().getEnvironmentType() == EnvType.CLIENT → World.isClient(Yarn 字段;yarn 1.14.4 World.mapping)。不要用 MCP/Forge 的 isRemote.
07-datagen
IF 生成物品/方块模型 JSON → 手动编写 JSON 在 src/main/resources/assets/{modid}/models/.
meta-quest-agentic-tools
Use Meta Quest Agentic Tools for Meta Quest and Horizon OS samples.
narrative-writing
游戏叙事写作助手行为约束(game-narrative-mcp).
meta-quest-agentic-tools
Use Meta Quest Agentic Tools for Meta Quest and Horizon OS samples.
visual-and-observational-rules
Defines the visual aspects of the game and how the player observes the world. This includes map color-coding, screen effects, and the overall simulation style.