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/EvilFreelancer/zaezdWrote 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/evilfreelancer/zaezd/code-style)<a href="https://agentmods.dev/rules/evilfreelancer/zaezd/code-style"><img src="https://agentmods.dev/badge/rules/evilfreelancer/zaezd/code-style/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/evilfreelancer/zaezd/code-style"><img src="https://agentmods.dev/badge/rules/evilfreelancer/zaezd/code-style.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 | $0.00860 | $0.00860 |
| Opus 5.5 | $0.00344 | $0.00344 |
| Sonnet 5.5 | $0.00172 | $0.00172 |
| Haiku 4.5 | $0.00086 | $0.00086 |
Grade A, and why
code-style 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code style
Language
- Code, comments, identifiers, docstrings, commit messages: English.
- Agent rule files and briefs (
.cursor/rules/*.mdc,.claude/rules/*.md,AGENTS.md,CLAUDE.md): English, unless the project owner asks otherwise; then switch every tree at once so the Rules Sync diff stays reviewable. - User-facing product copy (the trip board, the user guide): Russian, following the
microcopy rules in
specs/05-interfeys.md. - Chat replies to the user: Russian.
TypeScript
- Node >= 22.6, ESM only (
"type": "module"). Relative imports carry the.tsextension; the toolchain runs TypeScript through Node's native type stripping, so only erasable syntax is allowed: noenum, nonamespace, no parameter properties, no decorators. Useconstobjects withas constinstead ofenum. strictis on, together withnoUncheckedIndexedAccess,exactOptionalPropertyTypesandverbatimModuleSyntax. Type-only imports useimport type.anyis forbidden and the linter enforces it. External payloads enter asunknownand are narrowed by an explicit parser insrc/sources/. Everything downstream of that parser is a domain type.- Prefer
typealiases for data, discriminated unions over optional-field soup, and readonly arrays for anything crossing a module boundary. - Named exports only; one clear responsibility per module. A file above roughly 300 lines
is a signal to split, and a single file holding two thousand lines is an explicit
reviewer complaint in
specs/08-repozitoriy.md.
Errors and absence
- A missing field is
undefinedand stays visible as missing all the way to the UI. Never substitute a default, a guess or a web-search answer for data a source did not return. This is the product's core promise, not a style preference. - Throw typed errors carrying the source name and the arguments that failed
(
class SourceError extends Error), not bare strings. - Optional enrichment never throws outward: it resolves to
undefinedafter its timeout and the caller renders the absence.
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 · 80 lines · 860 tokens per session scan A 4c577c1b6c69
code-style is a cursor rule published in the GitHub repository EvilFreelancer/zaezd (1 stars, last pushed 1mo ago), licensed MIT. It adds 860 tokens to every session, about $0.0034 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
global
You are an expert in Golang, TypeScript, and JavaScript development, focusing on scalable, maintainable, and performant code. Follow these principles for all suggestions, code generation, and responses.
typescript-coding-rule
It allows a subset of JSDoc tags. Most tags must occupy their own line, with the tag at the beginning of the line.
typescript-standards
// Good: Typed error handling function loadConfig(): Config { try { // ... loading logic } catch (error) { if (error instanceof yaml.YAMLException) { throw new Error(Invalid YAML in configuration file: ${error.message}); } throw error; } }.
python-code-validator
Validate generated Python at every step, not once at the end.
mcp-tool-structure
The project implements an MCP (Model Context Protocol) tool following the framework's required structure.
typescript-conventions
Cursor rule "typescript-conventions" from VirtusLab-Open-Source/strapi-plugin-mcp, covering typescript and coding conventions, typescript configuration, import/export patterns, code organization and services (server/src/services/).