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/mercurievv/scalasemantic/cursorrulesgit clone --depth 1 https://github.com/MercurieVV/ScalaSemanticWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/mercurievv/scalasemantic/cursorrules)<a href="https://agentmods.dev/rules/mercurievv/scalasemantic/cursorrules"><img src="https://agentmods.dev/badge/rules/mercurievv/scalasemantic/cursorrules.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00376 | $0.00376 |
| Opus 5 | $0.00188 | $0.00188 |
| Sonnet 5 | $0.00075 | $0.00075 |
| Haiku 4.5 | $0.00038 | $0.00038 |
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 3d 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.
What it actually says
Project Rules & Context
MUST follow the rules in SCALA_SEMANTIC_RULES.md for working with Scala code. Mandatory, not optional.
Project Description & Startup Context
For detailed instructions, architecture, build/test commands, and conventions, please read CLAUDE.md on startup.
Quick Reference (from CLAUDE.md):
- Project: ScalaSemantic — MCP server for deep semantic analysis on Scala projects via SemanticDB.
- Stack: Scala 3.8.4, sbt 2.0.0, Scalameta 4.13.9, upickle 4.2.1, munit 1.2.3.
- Layout:
core/: Loads and indexes SemanticDB (SemanticIndex).analysis/: Result models and analyzer engine (depends oncore).mcp/: JSON-RPC server and stdio entrypoint (depends onanalysis).
- Core Commands:
- Compile:
sbt compile(regenerates SemanticDB) - Test:
sbt test(unforked tests run with cwd = repo root) - Pre-push check:
sbt prePush(clean, format, fix, test) - Run MCP server:
sbt "mcp/runMain com.github.mercurievv.scalasemantic.mcpServer <root>"
- Compile:
- Conventions:
- Follow Scala Code Rules in SCALA_SEMANTIC_RULES.md.
- Use Conventional Commit titles for squash merging PRs (
feat:,fix:,perf:).
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.
- 3d ago First seen · 25 lines · 376 tokens per session scan A 8a4a33669ce3
cursorrules is a cursor rule published in the GitHub repository MercurieVV/ScalaSemantic (22 stars, last pushed 4d ago), licensed MIT. It adds 376 tokens to every session, about $0.0019 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
infigraph
Infigraph architecture, build/test/lint commands, and cross-cutting invariants.
code-indexing-pipeline
How Infigraph turns source into a graph — adding a language (tree-sitter vs ANTLR grammar-plugin), cross-file call resolution, SCIP compiler-grade enrichment, and file-watch/reindex triage.
analysis-subsystems
How Infigraph's multi-repo/group mode and taint analysis work internally — HTTP contract extraction heuristics, cross-service edge linking, combined-graph merge, remote mode, plus taint's line-based tracking and sanitizer heuristic.
review-pr-against-issue
Workflow for reviewing a PR against the GitHub issue it claims to fix, including fetching PRs when gh CLI can't reach github.com.
agent-rule
Prefer NeuroMesh MCP for codebase context instead of dumping whole files.
kubernetes
This rule provides comprehensive best practices for developing and maintaining Kubernetes applications and infrastructure, covering coding standards, security, performance, testing, and deployment.