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/Netcracker/qubership-ai-packagesWrote 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/netcracker/qubership-ai-packages/english-developer-style)<a href="https://agentmods.dev/rules/netcracker/qubership-ai-packages/english-developer-style"><img src="https://agentmods.dev/badge/rules/netcracker/qubership-ai-packages/english-developer-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/netcracker/qubership-ai-packages/english-developer-style"><img src="https://agentmods.dev/badge/rules/netcracker/qubership-ai-packages/english-developer-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 | $0.00000 | $0.00757 |
| Opus 5 | $0.00000 | $0.00378 |
| Sonnet 5 | $0.00000 | $0.00151 |
| Haiku 4.5 | $0.00000 | $0.00076 |
Grade A, and why
english-developer-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 8d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill trigger: english-developer-style
You MUST invoke the english-developer-style skill BEFORE producing, modifying, translating, or critiquing any
English developer-facing text. The skill applies regardless of text length — a one-line error message and a multi-page
README go through the same checklist.
Trigger verbs
The skill fires on any of these tasks. The verb in the user request, not the file size, decides.
- write, draft, author, compose
- edit, rewrite, revise, polish, copy-edit
- translate, localize (to or from English)
- review, proofread, verify, audit, double-check, sanity-check, cross-check
- "check the wording", "does this read well", "is this English natural", "make this sound less AI"
If the user asks about English developer text in any of these modes — even a human-authored draft, even a five-word button label — invoke the skill before answering.
Covered surfaces
- Markdown: README, reference docs, design docs, ADR, runbooks, changelog, release notes.
- Source files (
.go,.js,.ts,.py,.java,.rs,.kt,.cs,.cpp,.rb,.swift,.scala,.php, ...): all English text inside them — code comments, docstrings (Javadoc, KDoc, TSDoc, JSDoc, Python docstrings, Rust doc-comments), and the English identifier names you choose for new functions, types, fields, files, and tests. - Localization files (English source or English target):
.po,.pot,.properties,.resx,.json(i18n),.ftl,.arb. - UI strings: buttons, labels, placeholders, tooltips, empty states, confirmations.
- Error, validation, warning, and log messages (including one-line
msgid/msgstr). - Commit messages, PR / MR descriptions, code-review replies.
Short messages count. A single msgstr "..." in a .po file, a one-line // FIXME: … comment in a .go file, or a
three-word button label is in scope.
When NOT to invoke
- Existing code identifiers, product names, CLI flags, file paths, environment variables — do not translate, restyle, or rename them. (When you choose a new identifier name, that choice is in scope; see Covered surfaces.)
- Generated API references and verbatim third-party quotes.
- Files explicitly marked "do not edit" or covered by a repository-specific style guide — yield to the local guide.
- Casual chat replies to the user.
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.
- 8d ago First seen · 53 lines · 0 tokens per session scan A 77065463f554
english-developer-style is a cursor rule published in the GitHub repository Netcracker/qubership-ai-packages (4 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 757 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 2026-08-31.
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.
cli-error-handling
CLI command error handling patterns.
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.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.