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/ts)<a href="https://agentmods.dev/rules/zenbase-ai/llml/ts"><img src="https://agentmods.dev/badge/rules/zenbase-ai/llml/ts/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/ts"><img src="https://agentmods.dev/badge/rules/zenbase-ai/llml/ts.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 | $0.01103 |
| Opus 5.5 | $0.00000 | $0.00441 |
| Sonnet 5.5 | $0.00000 | $0.00221 |
| Haiku 4.5 | $0.00000 | $0.00110 |
Grade A, and why
ts 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TypeScript Coding Rules for LLML Project
Overall Philosophy
The TypeScript implementation is a minimalist, functional, and robust library with zero production dependencies besides dedent. It prioritizes predictable output and developer experience through a simple API and strict typing, while gracefully handling varied and unpredictable input data.
Project Structure & Conventions
Tooling
- Runtime and Package Management: Use
bunfor all operations (installing dependencies, running scripts, building). The project is configured withbun.lockb. - Testing:
vitestis the testing framework. Usebun testto run the test suite. - Type Checking:
typescriptis used for static analysis. Runbun run tsc --noEmitto check for type errors without generating JavaScript files.
Module System
- The project uses ES Modules (ESM) exclusively, as defined by
"type": "module"inpackage.json. - Use
import/exportsyntax. Do not userequire/module.exports.
File Organization
- Source Code: All core logic resides in the
src/directory. The main entry point issrc/index.ts. - Utilities: Pure, reusable helper functions (like
kebabCase) should be placed insrc/utils.ts. - Tests: All test files are located in the
tests/directory. Maintain the one-to-one mapping of feature-to-test-file (e.g.,nested.tslogic is tested intests/nested.test.ts).
Coding Style & Patterns
- Functional Approach: The core logic is implemented as a set of pure functions. The main
llmlfunction is recursive and delegates formatting tasks to helpers. Avoid classes and stateful logic. - Immutability: Do not mutate input data. Functions should return new, transformed values.
- Dependencies: Maintain the zero-dependency principle for production code. The only exception is
dedent, which is used for cleaning up multiline strings. Do not add new production dependencies without strong justification. - Readability: Use
constby default andletonly when a variable must be reassigned. Code is formatted with a 2-space indent. - Comments: Add JSDoc-style comments to exported functions and complex utility functions to explain their purpose, parameters, and return values, as seen in
src/utils.ts.
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 · 63 lines · 0 tokens per session scan A 981cd9eb8662
ts 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 1,103 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
no-bare-casts
No bare as casts in production TypeScript. Use blindCast (value) from @internal/utils/casts as the auditable escape hatch, castAs (value) for declarative-only assertions, or rewrite to eliminate the cast. as const is exempt. Test files are exempt.
use-ast-factories
Use factory functions for creating AST nodes instead of manual object creation.
test-mocking-patterns
Test-only type assertions and mocking patterns (avoid brittle mocks).
tsdown-dist-layout-in-tests
Use tsdown dist root paths in TS test mappings.
jest-unit-testing-cursorrules-prompt-file
Cursor rules for Jest development with unit testing.
javascript
JavaScript and TypeScript conventions for this ESM monorepo.