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/sruja-ai/sruja/core-enginegit clone --depth 1 https://github.com/sruja-ai/srujaWhat 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 | $0.00374 | $0.00374 |
| Opus 5 | $0.00187 | $0.00187 |
| Sonnet 5 | $0.00075 | $0.00075 |
| Haiku 4.5 | $0.00037 | $0.00037 |
Grade A, and why
core-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 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.
What it actually says
Core Engine Constraints
Patterns for Core Engine crates (language, engine, diagnostics, graph, graph-core, scan).
Scopes
crates/sruja-language/**/*.rscrates/sruja-engine/**/*.rscrates/sruja-diagnostics/**/*.rscrates/sruja-graph/**/*.rscrates/sruja-graph-core/**/*.rscrates/sruja-scan/**/*.rs
Rules
- Pure functions preferred: Core functions should be deterministic and side-effect free. I/O belongs in CLI or scan crates.
- No CLI dependencies: Core crates must never depend on
sruja-cliorclap. - No WASM dependencies: Core crates must never depend on
sruja-wasmorwasm-bindgen. - Error types: Use
thiserrorfor all error enums. Never useanyhowin library crates. - Public API surface: Keep
lib.rsas the public API surface. Implementation details go in submodules. - Serde everywhere: All public types that cross boundaries should derive
Serialize+Deserialize. - Module docs: Every
lib.rsandmod.rsstarts with//!doc comments describing the module's purpose. - Test coverage: Files with non-trivial logic should have a
#[cfg(test)] mod testswith unit tests. Pure re-export or type-definition files are exempt.
Layer Boundary
Core Engine crates have no external dependencies allowed (per classification). They form the foundation that all other layers build upon. If you need functionality from another layer, it belongs here — not pulled in as a dependency.
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 · 27 lines · 374 tokens per session scan A 9a9f28a31722
core-engine is a cursor rule published in the GitHub repository sruja-ai/sruja (22 stars, last pushed 9d ago), licensed Apache-2.0. It adds 374 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
laminar
Use it when user asks about adding instrumentation with Laminar, creating an eval with Laminar or migrating from Langfuse to Laminar instrumentation.
testing
Testing strategies and quality assurance — testing pyramid, unit/integration/E2E testing, TDD/BDD, test automation, and quality metrics. Applied when writing or reviewing tests.
api-design
API design guidelines — REST principles, GraphQL patterns, versioning, pagination, error handling, documentation, security, caching, and testing. Applied when designing or reviewing API endpoints.
owasp-ai-security-privacy
OWASP AI Security & Privacy Guide – PR rules emphasizing data protection, governance, and safety.
cursorrules
Cursor rule "cursorrules" from me2resh/agent-decision-record, covering agent decision records (agdr) — cursor rules, purpose, see: https://github.com/me2resh/agent-decision-record, decision detection and adding a new dependency → stop, document decision first.
agdr
Agent Decision Records - enforces structured documentation of technical decisions before implementation.