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/rocketride-org/rocketride-server/cursorrulesgit clone --depth 1 https://github.com/rocketride-org/rocketride-serverWhat 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 | $0.00742 | $0.00742 |
| Opus 5 | $0.00371 | $0.00371 |
| Sonnet 5 | $0.00148 | $0.00148 |
| Haiku 4.5 | $0.00074 | $0.00074 |
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 yesterday.
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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rocket Ride Data Toolchain - AI Assistant Instructions
Read ALL Documentation First
Before ANY Rocket Ride code, read ALL 6 files at docs/agents/:
ROCKETRIDE_QUICKSTART.md← Start here, copy working examplesROCKETRIDE_README.mdROCKETRIDE_python_API.mdorROCKETRIDE_typescript_API.mdROCKETRIDE_PIPELINE_RULES.mdROCKETRIDE_COMPONENT_REFERENCE.mdROCKETRIDE_COMMON_MISTAKES.md
If user request is ambiguous: STOP and ask. Do NOT guess.
✓ Before Submitting Code
- Read ROCKETRIDE_QUICKSTART.md and used as template
- Read all 6 documentation files
- Verified code follows documented patterns
- Quoted relevant documentation in response
Cannot check all boxes? Don't submit code.
Documentation Guide
| Need | File |
|---|---|
| Working examples | ROCKETRIDE_QUICKSTART.md |
| Setup checklist | ROCKETRIDE_README.md |
| Client methods | ROCKETRIDE_python_API.md or ROCKETRIDE_typescript_API.md |
| Pipeline rules | ROCKETRIDE_PIPELINE_RULES.md |
| Components | ROCKETRIDE_COMPONENT_REFERENCE.md |
| Troubleshooting | ROCKETRIDE_COMMON_MISTAKES.md |
The co-located per-package docs — assembled into the docs site by builder docs:build — are the source of truth. The agent integration docs at docs/agents/ are the assistant-facing integration reference within it; read them first before writing any RocketRide integration code.
Co-located documentation rule
Documentation is co-located with the code it documents and is gathered into the
docs site by builder docs:build. When a change alters a public contract, update
the corresponding co-located doc in the SAME change:
- A node's inputs, outputs, or config schema -> prose in
nodes/src/nodes/<name>/doc.md. Never hand-edit content between<!-- ROCKETRIDE:GENERATED:PARAMS START -->and<!-- ROCKETRIDE:GENERATED:PARAMS END -->; it is regenerated fromservices*.jsonbynodes:docs-generate. - A public TypeScript SDK signature ->
packages/client-typescript/docs/. Reference underdocs/reference/is generated byclient-typescript:docs-generate(do not edit). - A public Python SDK signature ->
packages/client-python/docs/(reference generated). - The MCP protocol surface ->
packages/client-mcp/docs/. - The WebSocket (5565) / engine protocol surface ->
packages/server/docs/. - The
.pipeschema (packages/client-typescript/src/client/types/pipeline.ts) -> its reference regenerates to/pipeline-reference. - The VS Code extension surface ->
apps/vscode/docs/. - Spine/landing pages (Home, Quickstart, Concepts, Cloud, Troubleshooting, Glossary,
Cursor/Windsurf stubs) ->
packages/docs/content-static/.
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.
- yesterday First seen · 67 lines · 742 tokens per session scan A 51d7dd4b2ada
cursorrules is a cursor rule published in the GitHub repository rocketride-org/rocketride-server (7,496 stars, last pushed 2d ago), licensed MIT. It adds 742 tokens to every session, about $0.0037 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
python_tests
We use the unit tests to cover internal behavior that can work without the web / backend counterpart. We aim for 95%+ unit test coverage of our Python code in lib/streamlit.
scripts
Utility scripts for development and CI/CD.
zenml-domain-models
How to understand, add or modify ZenML domain models.
mod-000a-reusable-layers-belong-in-nn
Reusable layers and building blocks should be placed in physicsnemo/nn, not physicsnemo/models. Examples include FullyConnected, attention layers, and UNetBlock.
mod-003c-missing-required-class-docstring-sections
Class docstrings must contain three mandatory sections - Parameters, Forward, and Outputs. Optional sections include Notes, Examples, ..important::, and ..code-block::.
mod-003f-callback-functions-must-have-code-block-specification
Callback function parameters must include a ..code-block:: specification showing the required signature and return type, placed outside Parameters/Forward/Outputs sections.