MCP-Template / rules
Cursor rule1 starsChanged 5 months agoMITView on GitHub
This pattern should apply for all long-running code. Unbundle run() into: Never assume you will call these in order. Always checkpoint and resume from id's. Pass nothing else. This forces you to keep things serializable and therefore loggable, reproducible, parallelizable. by the way try not to name them 'id' if you can add extra detail like 'runId', 'taskId', 'subTask2Id'. Any time you cross a system boundary*: RATE LIMITS, TIMEOUTS, RETRIES, LOG TRACE. NO EXCEPTIONS. *eg call microservice or external api.…
Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.
Of the Cursor rule files we read, the 4,157 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository28 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- .cursor/rules/agent.mdcCursor rule
- .cursor/rules/coding_style.mdcCursor rule
- .cursor/rules/commit_msg.mdcCursor rule
- .cursor/rules/common.mdcCursor rule
- .cursor/rules/deprecated.mdcCursor rule
- .cursor/rules/github_actions.mdcCursor rule
- .cursor/rules/langfuse.mdcCursor rule
- .cursor/rules/llm.mdcCursor rule
- .cursor/rules/makefile-commands.mdCursor rule
- .cursor/rules/package-management.mdCursor rule
- .cursor/rules/tests.mdcCursor rule
- .cursor/rules/typing.mdcCursor rule
- .cursor/rules/uv.mdcCursor rule
- frontend-design-principlesSkill
- goose-gui-e2eSkill
- local-sandboxSkill
- manage-agent-configSkill
- new-agent-ruleSkill
- onboardingSkill
- push-releaseSkill
- cleanupSkill
- code-qualitySkill
- prek-precommit-hookSkill
- thermo-nuclear-code-quality-reviewSkill
- usageSkill
- waitSkill
- gmail-mcpSkill
The file
We split this long_run_code.mdc into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Never assume you will call these in order.
- Distinctive: line 16
Always checkpoint and resume from id's.
- Distinctive: line 32
DO NOT DO ANY OUTPUT FORMATTING UNTIL THE END
≈ “Common” is an estimate: at least 1 in 5 of the 6,668 Cursor rule files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
--- description: globs: alwaysApply: false --- This pattern should apply for all long-running code. Unbundle run() into: - init() - continue(id) - cleanup(id) Never assume you will call these in order. Always checkpoint and resume from id's. Pass nothing else. This forces you to keep things serializable and therefore loggable, reproducible, parallelizable. by the way try not to name them 'id' if you can add extra detail like 'runId', 'taskId', 'subTask2Id'. Any time you cross a system boundary*: RATE LIMITS, TIMEOUTS, RETRIES, LOG TRACE. NO EXCEPTIONS. *eg call microservice or external api. yes, this includes llm APIs, meaning every ai project needs this DO NOT DO ANY OUTPUT FORMATTING UNTIL THE END "its so easy to fstring/template string" DOESNT MEAN YOU SHOULD keep things in structured format all the way basically until the point of reading debugging output formatting its own form of hell
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.