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.
git clone --depth 1 https://github.com/zenbase-ai/llmlWrote 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/zenbase-ai/llml/rs)<a href="https://agentmods.dev/rules/zenbase-ai/llml/rs"><img src="https://agentmods.dev/badge/rules/zenbase-ai/llml/rs/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/zenbase-ai/llml/rs"><img src="https://agentmods.dev/badge/rules/zenbase-ai/llml/rs.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.01125 |
| Opus 5.5 | $0.00000 | $0.00450 |
| Sonnet 5.5 | $0.00000 | $0.00225 |
| Haiku 4.5 | $0.00000 | $0.00112 |
Grade A, and why
rs 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 1mo 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rust Coding Rules for LLML Project
These guidelines are designed to maintain the existing quality, style, and architectural patterns of the codebase.
Project Structure & Modules
- Public API (
src/lib.rs): Thesrc/lib.rsfile is the public face of the library. It should only contain the public API (llml,llml_with_options,Optionsstruct) and its associated documentation and unit tests. - Core Logic (
src/formatters.rs): All internal formatting logic should reside in thesrc/formatters.rsmodule. Functions within this module should remain private to the crate (i.e., not marked withpub). - Tests:
- Unit Tests: Place unit tests within the module they are testing, using a
#[cfg(test)] mod tests { ... }block. - Integration Tests: Place integration tests in the
tests/directory. These tests should only call the public API fromlib.rs.
- Unit Tests: Place unit tests within the module they are testing, using a
- Examples: Add new usage examples to the
examples/directory.
Coding Style & Formatting
- Formatting: All code must be formatted with
rustfmtusing the default settings. - Naming Conventions:
- Functions & Variables: Use
snake_case(e.g.,format_value,kebab_key). - Types (Structs, Enums): Use
PascalCase(e.g.,Options). - Constants & Statics: Use
SCREAMING_SNAKE_CASE(e.g.,MULTI_HYPHEN_RE).
- Functions & Variables: Use
- Clarity: Prioritize clear, readable code. Use descriptive variable names.
API Design & Patterns
- Public Functions: The primary public functions are
llml(for default options) andllml_with_options(for custom formatting). Maintain this clear separation. - Configuration: All configuration should be passed via the
Optionsstruct. When adding new configuration, extend this struct. - Optional Configuration: Use
Option<Options>for thellml_with_optionsfunction signature. Useoptions.unwrap_or_default()to handle theNonecase. - Immutability: Prefer immutable variables (
let) over mutable ones (let mut) unless mutability is strictly necessary (e.g., for builders or accumulators). - Performance:
- Pass complex types like
ValueandOptionsby reference (&) to avoid unnecessary clones. - For expensive initializations that can be shared (like
Regex), usestd::sync::OnceLock.
- Pass complex types like
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.
- 1mo ago First seen · 68 lines · 0 tokens per session scan A f4de1e6f04c2
rs is a cursor rule published in the GitHub repository zenbase-ai/llml (73 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,125 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 2026-09-01.
Other cursor rules, from other repositories
rust-module-refactor
Use when splitting Rust modules, moving tests, tightening visibility, or preserving facades during refactors.
rust-architect
PoolAI — Rust Architect workflow: runtime stack, MSYS2, target/ disk, pre-push checks, docs sync.
core
Core STT/TTS abstraction layer documentation.
table-of-contents-standard
Standard section ordering and TOC format for Verus source files.
arc-deref-pattern
When implementing parallel (Mt) algorithms in Verus, do NOT assume.
wrap-vs-specify
When to use externaltypespecification vs wrapper struct for Verus specs.