Economic-Modeling-Studio / rules
Cursor rule4 starsChanged 6 days agoMITView on GitHub
GEMPACK and GTAP Code standards
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 4,243 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 repository210 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/ai-ml-code.mdcCursor rule
- .cursor/rules/code-translation.mdcCursor rule
- .cursor/rules/data-pipelines.mdcCursor rule
- .cursor/rules/documentation.mdcCursor rule
- .cursor/rules/dsge-code.mdcCursor rule
- .cursor/rules/econometrics-code.mdcCursor rule
- .cursor/rules/eviews-code.mdcCursor rule
- .cursor/rules/forecasts.mdcCursor rule
- .cursor/rules/lego-manifests.mdcCursor rule
- .cursor/rules/llm-code.mdcCursor rule
- .cursor/rules/model-code.mdcCursor rule
- .cursor/rules/notebooks-and-scripts.mdcCursor rule
- .cursor/rules/r-code.mdcCursor rule
- .cursor/rules/restricted-data.mdcCursor rule
- .cursor/rules/rl-code.mdcCursor rule
- .cursor/rules/sectoral-trade-climate-code.mdcCursor rule
- .cursor/rules/semi-structural-code.mdcCursor rule
- .cursor/rules/stata-code.mdcCursor rule
- .cursor/rules/tests.mdcCursor rule
- .cursor/rules/validation.mdcCursor rule
- adoptSkill
- ai-auditSkill
- backtestSkill
- build-abmSkill
- build-causal-mlSkill
- build-cgeSkill
- build-climate-macroSkill
- build-deep-forecasterSkill
- build-drl-policySkill
- build-dsgeSkill
- build-financial-programmingSkill
- build-fpasSkill
- build-game-modelSkill
- build-hankSkill
- build-io-samSkill
- build-llm-agentsSkill
- build-llm-pipelineSkill
- build-multicountrySkill
- build-neural-solverSkill
- build-rag-kbSkill
- build-semi-structuralSkill
- build-sfcSkill
- build-trade-modelSkill
- calibrate-modelSkill
- calibration-planSkill
- carbon-pricing-analysisSkill
- chart-packSkill
- climate-scenarioSkill
- code-inventorySkill
- code-reviewSkill
- country-typologySkill
- create-exerciseSkill
- data-requirementsSkill
- debt-decompositionSkill
- debt-sustainabilitySkill
- design-trainingSkill
- distributional-analysisSkill
- equivalence-testSkill
- The first 60 shown.
The file
We split this gempack-code.mdc into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
Check the benchmark before any shock: a zero-shock run (homogeneity test with a numeraire shock) reproduces the database
- Distinctive: line 14
Keep the aggregation mapping (GTAPAgg or FlexAgg sectors, regions and endowments) with the model and record the database version and base …
- Very specific: line 18
The GTAP database is licensed: Keep it in data/raw/gtap/ (outside git), never commit, share or upload the database or files derived from it …
- Very specific: line 19
Run in batch from the command line (the compiled model with -cmf, or gemsim) so every experiment reruns with one command
≈ “Common” is an estimate: at least 1 in 5 of the 6,809 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: GEMPACK and GTAP Code standards globs: **/*.tab,**/*.cmf,models/**/gtap*/** alwaysApply: false --- <!-- Generated from .claude/rules/gempack-code.md by tools/sync_agents.py. Edit the source, then run the script. --> # Rules: GEMPACK and GTAP Code - The model code is the TABLO file (`.tab`); record which model and version it is (for example standard GTAP 7, GTAP-E, GTAP-POWER) and every change made to it - One command file (`.cmf`) per experiment holds the files used, the closure, the shocks and the solution method; never run an experiment from settings saved only in RunGTAP or another interface - The closure is written out in the `.cmf` and justified; report results under a second closure where they matter - Solve with a multi-step method (Gragg with extrapolation, for example 2-4-6 steps) and report the extrapolation accuracy; a one-step Johansen solution is for checks only - Check the benchmark before any shock: a zero-shock run (homogeneity test with a numeraire shock) reproduces the database - Keep the aggregation mapping (GTAPAgg or FlexAgg sectors, regions and endowments) with the model and record the database version and base year (for example GTAP 11, 2017) - Elasticities are sourced; report systematic sensitivity on the key ones (Armington, CET, factor mobility) - Report welfare as equivalent variation with its decomposition (allocative, terms of trade, endowment, technical change), and use subtotals to split results by shock - Export results from the solution file (`.sl4`) to CSV with SLTOHT or ViewHAR into `output/<run-id>/`, together with the `.cmf` and the log of the run - **The GTAP database is licensed.** Keep it in `data/raw/gtap/` (outside git), never commit, share or upload the database or files derived from it at full detail, and record the license holder; only aggregated results may leave the studio - Run in batch from the command line (the compiled model with `-cmf`, or `gemsim`) so every experiment reruns with one command
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.

