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/williamisnotdefined/rubiks-cube-solver/cube-enginegit clone --depth 1 https://github.com/williamisnotdefined/rubiks-cube-solverWhat 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 | $0.00000 | $0.02936 |
| Opus 5 | $0.00000 | $0.01468 |
| Sonnet 5 | $0.00000 | $0.00587 |
| Haiku 4.5 | $0.00000 | $0.00294 |
Grade A, and why
cube-engine 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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generated from ai/registry.json. Do not edit manually.
Canonical skill: ../../ai/skills/cube-engine.md.
Referenced context:
../../ai/rules/cube-engine-rules.md../../ai/rules/testing-rules.md../../ai/architecture/project-architecture.md../../ai/architecture/cube-engine.md../../ai/glossary/cube-terms.md
This file is compiled from canonical AI knowledge files. Edit canonical files under ai, then run npm run ai:sync.
Compiled AI Skill: cube-engine
Canonical Skill: ai/skills/cube-engine.md
Cube Engine
Use this skill when adding or changing the Rust cube representation, moves, notation, scrambles, or cube validation.
Goal
Build the pure Rust engine first, using cubie representation and deterministic behavior that later search algorithms can trust.
Read First
ai/rules/cube-engine-rules.mdai/rules/testing-rules.mdai/architecture/project-architecture.mdai/architecture/cube-engine.mdai/glossary/cube-terms.md
Workflow
- Keep work inside
crates/cube-engineunless a current boundary requires otherwise. - Start with cubie state invariants before adding higher-level algorithms.
- Keep notation parsing and state mutation separate.
- Add tests for solved state, move/inverse behavior, and invalid notation as behavior appears.
- Fail explicitly for bootstrap placeholders rather than silently producing incorrect cube states.
Expected Output
- Primary state remains corner/edge permutation and orientation.
- Move behavior is reversible and tested when implemented.
- No JavaScript visualization dependency enters the Rust engine.
Verification
- Run
cargo test -p cube-enginewhen Rust is installed. - If Rust is unavailable, state the environment blocker clearly.
Referenced Context
Reference: ai/rules/cube-engine-rules.md
Cube Engine Rules
Rules for the Rust cube engine.
Always
- Use cubie representation as the primary state model: corner permutation, corner orientation, edge permutation, and edge orientation.
- Keep move application pure and deterministic.
- Make every implemented move reversible and test the inverse path.
- Validate state invariants before solver algorithms depend on them.
- Keep notation parsing separate from state mutation.
- Keep serialization explicit and stable once external consumers exist.
- When adding puzzles beyond 3x3, keep each puzzle's state representation, move model, notation parser, validator, and solver strategy puzzle-specific.
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 · 275 lines · 0 tokens per session scan A 8639dd825816
cube-engine is a cursor rule published in the GitHub repository williamisnotdefined/rubiks-cube-solver (4 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,936 tokens. 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
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.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.