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/hereon-institutems/oasis/cursorrulesgit clone --depth 1 https://github.com/Hereon-InstituteMS/OASiSWhat 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 | $0.00786 | $0.00786 |
| Opus 5 | $0.00393 | $0.00393 |
| Sonnet 5 | $0.00157 | $0.00157 |
| Haiku 4.5 | $0.00079 | $0.00079 |
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 2d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OASiS — Project Instructions
How to Handle Complex Simulation Tasks
For any non-trivial simulation task, break the work into sub-agents:
-
Research agent: Search online for the specific problem — find literature values, validated setups, correct parameters. Report findings.
-
Setup agent: Using the research findings, build the input files. Use
get_example_inputs()to study real test files from the solver's test suite. Userun_with_generator()for simulations that need programmatic mesh/particle generation. -
Critic agent: Independently review the setup. Check every parameter against what the research agent found. Verify units, discretization, boundary conditions, material properties. Search online to validate. If the simulation fails after multiple attempts with the chosen solver, consider whether an alternative solver might be more suitable —
prepare_simulationshows what alternatives exist. Report any issues. -
Execution agent: Fix any issues the critic found, then run the simulation.
-
Results critic agent: After the simulation completes, independently verify the results. Use
visualize(action='validate')to check for NaN, constant fields, suspiciously large values. Check that field magnitudes are physically reasonable for the problem. Compare against known analytical solutions or literature values where possible. -
Coupling agent (if multi-solver): Transfer fields between solvers, set up the coupling, run the second solver, produce combined output.
Developer Mode: Extending Solvers
When you hit a solver limitation — a missing material model, element type, boundary condition, or physics module — don't just accept it. You have full source access via developer(action='architecture', solver) and the <SOLVER>_ROOT environment variables. Consider:
- Diagnose: Read the solver source to understand why the capability is missing
- Assess: Is it a small addition (new material, new BC) or a major feature? Report this to the user.
- Propose: Tell the user "I could implement X in the solver source to fix this — should I proceed?"
- Implement (if authorized): Modify source files, rebuild, re-run with the fix
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.
- 2d ago First seen · 52 lines · 786 tokens per session scan A 6e920fd0b856
cursorrules is a cursor rule published in the GitHub repository Hereon-InstituteMS/OASiS (18 stars, last pushed 23d ago), licensed MIT. It adds 786 tokens to every session, about $0.0039 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 2026-08-30.
Other cursor rules, from other repositories
frontend-structure
Frontend frameworks, file structure.
use-frontend-api-client
Generated API client usage.
cursorrules
AGENTS.md.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.