Borrowing it
Nothing to install: this file belongs to Netcracker/qubership-ai-packages. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Netcracker/qubership-ai-packages/main/.agents/skills/english-developer-style/SKILL.mdgit 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/skills/netcracker/qubership-ai-packages/english-developer-style)<a href="https://agentmods.dev/skills/netcracker/qubership-ai-packages/english-developer-style"><img src="https://agentmods.dev/badge/skills/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/skills/netcracker/qubership-ai-packages/english-developer-style"><img src="https://agentmods.dev/badge/skills/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 | $0.00227 | $0.03416 |
| Opus 5 | $0.00113 | $0.01708 |
| Sonnet 5 | $0.00045 | $0.00683 |
| Haiku 4.5 | $0.00023 | $0.00342 |
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 11d 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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
English developer style (American)
This skill governs natural-language text written for developers and for users of developer tools: README and reference
pages, code comments and docstrings, commit messages, PR descriptions, changelogs, UI strings, error and log messages,
and localization files. Length does not matter — a one-line msgstr or a three-word button label goes through the same
checklist as a multi-page README. It does not govern code itself, marketing copy, or general end-user product copy
outside developer surfaces.
Defaults: American English, second person, present tense, sentence-case headings, serial (Oxford) comma. Voice model: a knowledgeable colleague who has done this before.
1. When to apply
Engage whenever the task touches English developer-facing text, regardless of length. The verb in the request — not the file size or the "this is just one word" feeling — decides.
Trigger actions:
- Authoring: writing new pages, comments, commit messages, PR descriptions, release notes, UI strings, or error and log messages.
- Translation and localization: translating to or from English; editing
.po,.pot,.properties,.resx, JSON i18n, Fluent, or ARB files. - Editing: rewriting an LLM-generated draft before commit (primary use), polishing someone else's prose.
- Review and verification: "check the wording", "does this read well", "is this English natural", "make this sound less AI", "proofread these strings", "verify the translation", "audit the changelog", "double-check the error messages", "cross-check the docstrings against the code".
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. A one-line// TODO: handle retrybelongs here just as much as a multi-line Javadoc block. - Localization files (English source or English target):
.po,.pot,.properties,.resx, JSON i18n,.ftl,.arb. A one-linemsgstris in scope. - UI strings: buttons, labels, placeholders, tooltips, empty states, confirmations.
- Error, validation, warning, and log messages.
- Commit messages, PR / MR descriptions, code-review replies.
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.
- 11d ago First seen · 238 lines · 227 tokens per session scan A c91fecf2c209
english-developer-style is a skill published in the GitHub repository Netcracker/qubership-ai-packages (4 stars, last pushed yesterday), licensed Apache-2.0. It adds 227 tokens to every session and 3,416 once invoked, about $0.0011 per session on Opus 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…