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/go)<a href="https://agentmods.dev/rules/zenbase-ai/llml/go"><img src="https://agentmods.dev/badge/rules/zenbase-ai/llml/go/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/go"><img src="https://agentmods.dev/badge/rules/zenbase-ai/llml/go.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 | $0.01187 |
| Opus 5.5 | $0.00000 | $0.00475 |
| Sonnet 5.5 | $0.00000 | $0.00237 |
| Haiku 4.5 | $0.00000 | $0.00119 |
Grade A, and why
go 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Go Coding Rules for LLML Project
Project Structure
The project follows a standard and clean structure for a Go library.
go.mod,go.sum: Reside at the root of the Go project (go/). All dependency management should be handled here.pkg/: Contains the core library code. The main package isllml(go/pkg/llml/). Any new library code should be placed within thepkg/directory.tests/: Contains the integration and unit tests. Tests are in a separate_testpackage (e.g.,llml_test), which is a best practice for testing only the exported API of a package.README.md: A dedicated README for the Go implementation exists and should be updated with any new features, API changes, or usage instructions.
Dependencies
- Main Library: The core library in
pkg/has zero external dependencies and relies only on the Go standard library. This should be maintained to keep the library lightweight and easy to integrate. - Testing: Tests use
github.com/stretchr/testify/assertfor assertions. This is the only development dependency and should be used for all new tests to maintain consistency.
Coding Style and Conventions
- Formatting: All code must be formatted with
gofmt. - Naming:
- Packages should be named in lowercase (e.g.,
llml). - Exported identifiers (functions, types, variables) must start with a capital letter (e.g.,
LLML,Options). - Internal (private) identifiers must start with a lowercase letter (e.g.,
formatMap,toKebabCase). - Variable names should use
camelCase(e.g.,kebabKey,anyMap).
- Packages should be named in lowercase (e.g.,
- Comments:
- All exported functions and types must have a doc comment explaining their purpose, parameters, and return values.
- Use comments to explain complex or non-obvious logic. Avoid comments that just restate what the code does.
- Imports: Imports should be organized into two blocks: standard library packages first, followed by third-party packages.
Patterns and Idioms
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 · 69 lines · 0 tokens per session scan A cde30624f4e1
go 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 1,187 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
gonavi-go
A Go coding rule set for the GoNavi repository, based on common Go style guides and the project's own conventions. It covers file structure, errors, context, concurrency, logging, and tests.
backend
You are an expert in Go, Gin, Gorm, Gen, Cosy (https://cosy.uozi.org/) with a deep understanding of best practices and performance optimization techniques in these technologies.
code-style
Formatting, lint, comments language.
go-grpc-service-rule
A set of Chinese-language rules for implementing gRPC services in Go. gRPC is a way for software services to communicate using defined messages and procedures.
05-go-helpers
In a module whose go.mod requires x/rkit, use rkit before writing a small helper — and over the standard library when both have it (rkit.Contains not slices.Contains, rkit.Coalesce not cmp.Or, rkit.IntToStr not strconv.Itoa). Task → helper map and edge cases: x/rkit/README.md.
go
Go conventions for all Zapstore Go projects (zsp, server, zindex, zapstore-cli).