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/logosdx/monorepoWrote 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/logosdx/monorepo/docs)<a href="https://agentmods.dev/rules/logosdx/monorepo/docs"><img src="https://agentmods.dev/badge/rules/logosdx/monorepo/docs/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/logosdx/monorepo/docs"><img src="https://agentmods.dev/badge/rules/logosdx/monorepo/docs.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 | $0.00008 | $0.01022 |
| Opus 5.5 | $0.00003 | $0.00409 |
| Sonnet 5.5 | $0.00002 | $0.00204 |
| Haiku 4.5 | $0.00001 | $0.00102 |
Grade A, and why
docs 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
📘 Documentation Meta Layout for LogosDX Packages
Each package should have a single file written for a competent but time-starved developer. Prioritize clarity, brevity, and usefulness. Avoid hype language and unnecessary verbosity.
✍️ Tone and Style Guidelines
Personality:
- Calm, clear, senior-dev energy.
- Witty is fine. Condescending is not.
- Be opinionated where it helps. Justify trade-offs.
Avoid:
- Overused buzzwords like robust, intuitive, powerful, comprehensive
- Passive voice
- Words like simply, just, or seamlessly
Prefer:
- Direct sentences
- Honest tradeoffs (“This works well unless you’re doing X.”)
- Short paragraphs, meaningful whitespace, and real-world language
🧱 Sections and Their Purpose
Each doc file should follow this structure (some sections can be optional depending on the package):
1. # Package Name
One-liner summary of what this package does and why it exists.
Keep it human:
“Declarative retry, timeout, and error flow for async JavaScript. Works everywhere. No ceremony.”
2. ## Core Concepts (Required)
A short explanation of the package’s mental model.
- What problem does it solve?
- How does it fit the LogosDX philosophy? (e.g., structure over scaffolding)
- How is it different from what developers might already be using?
3. ## Quick Start (Required)
Show how to install and use it in under 10 lines.
- Installation command
- A real (but minimal) usage snippet
- Zero explanation unless it's essential — this is a “see for yourself” moment
4. ## API Overview (Required)
List of exported utilities, components, or functions with short 1–2 sentence blurbs.
Can be a list or table like:
- `attempt(fn)`: Wraps sync or async logic and returns [result, error]
- `retry(fn, opts)`: Retries a function N times before failing
5. ## Usage (Required)
Detailed explanations and examples for each export.
Each utility/function/module gets a heading:
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 · 195 lines · 8 tokens per session scan A 17039858d93b
docs is a cursor rule published in the GitHub repository logosdx/monorepo (7 stars, last pushed 10d ago), licensed BSD-3-Clause. It adds 8 tokens to every session and 1,022 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-08-31.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).