english-prose-style

english-prose-style is a skill for Claude Code, Codex from Netcracker/qubership-ai-packages. It costs 0 tokens per session (2,018 once invoked), scanned A, original, Apache-2.0.

A set of conventions for clear written English in software work. It covers documents, README files, code comments, commit messages, pull requests, design notes, and names for code items such as methods and variables.

In plain words
What is it for?
Use it when writing or reviewing documentation, comments, release notes, commits, pull requests, design documents, error messages, and English names in code.
Why use it?
Technical writing can become hard to read through awkward sentence structure, punctuation, or repeated patterns even when the technical facts are correct. These rules provide consistent choices, including British English by default unless a project says otherwise.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md.

Good fit Use it when writing or reviewing documentation, comments, release notes, commits, pull requests, design documents, error messages, and English names in code.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/netcracker/qubership-ai-packages/seed
Install

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.

Any agent
npx skills add Netcracker/qubership-ai-packages --skill seed
Clone the repo
git clone --depth 1 https://github.com/Netcracker/qubership-ai-packages

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for english-prose-style

README.md
[![agentmods](https://agentmods.dev/badge/skills/netcracker/qubership-ai-packages/seed/github.svg)](https://agentmods.dev/skills/netcracker/qubership-ai-packages/seed)
Your own site
<a href="https://agentmods.dev/skills/netcracker/qubership-ai-packages/seed"><img src="https://agentmods.dev/badge/skills/netcracker/qubership-ai-packages/seed/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.

agentmods 80×15 button for english-prose-style

Your own site · 80×15
<a href="https://agentmods.dev/skills/netcracker/qubership-ai-packages/seed"><img src="https://agentmods.dev/badge/skills/netcracker/qubership-ai-packages/seed.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,018 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.02018
Opus 5 $0.00000 $0.01009
Sonnet 5 $0.00000 $0.00404
Haiku 4.5 $0.00000 $0.00202

Measured 5d ago against content hash b60d5f55184a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

english-prose-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 5d 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.

research/english-developer-style/seed_SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

English prose style

Conventions for written English that will be read by humans: docs, javadoc, commit messages, PR descriptions, identifier names. These rules target the mechanical drift patterns LLMs fall into when writing technical prose. They are deliberately scoped to genuine LLM failure modes; basic grammar (subject-verb agreement, possessives, capitalisation, punctuation spacing) is assumed and not repeated here.

When to apply

Apply these rules when producing:

  • Documentation (Markdown, Asciidoc, plain text)
  • README files, CHANGELOG entries, release notes
  • Javadoc, KDoc, docstrings, inline code comments
  • Commit messages, PR titles, PR descriptions, review replies
  • Design docs, RFCs, architecture notes
  • English identifier names (method, variable, class, file, package)
  • Error messages and user-facing log strings

Do not apply for casual chat replies to the user, or for content the user explicitly marked as draft / informal.

Dialect

Default to British English unless the project specifies otherwise (check the project CLAUDE.md or repository conventions). Common project signals: existing prose using behaviour / organisation / colour (British) vs behavior / organization / color (American). Match the existing dialect rather than overriding it.

LLMs tend to drift towards American spelling in long technical documents because the American corpus dominates training data. On edits longer than a few paragraphs, re-read the output and check for consistency before finishing.

Em-dash usage

Em-dash () is the single most-flagged issue in LLM-generated technical prose. The rules below are strict.

  • No em-dash in section headings. Use a colon: ## reWriteBatchedInserts=true: batch INSERT throughput. If the qualifier does not fit a colon cleanly, move it into the intro sentence below the heading.
  • No em-dash in definition lists. Patterns like **Term** — definition (status labels, glossary entries, bullet annotations) should be **Term**: definition.
  • No paired em-dashes for parentheticals. X — qualifier — Y becomes X (qualifier), Y, X, qualifier, Y, or two separate sentences.
  • No em-dash as a paragraph-level connector. We value backward compatibility — upgrading is... should be a period (We value backward compatibility. Upgrading is...), a semicolon, or a colon depending on the relationship between the two clauses.
  • No em-dash to introduce a list. Use a colon: bounded by its own timeout: TCP handshake, optional TLS upgrade, ... (not ... by its own timeout — TCP handshake, ...).
  • Use commas for short asides. "The driver, by default, opens one socket" needs no dash.
  • Reserve the em-dash for genuine sharp emphasis where comma, colon, semicolon, period, and parentheses would all lose the break. Even then, aim for at most one per page.

Read the full file on GitHub · 133 lines

Changes

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.

  1. 5d ago First seen · 133 lines · 0 tokens per session scan A b60d5f55184a

Subscribe to this mod's changes

english-prose-style is a skill published in the GitHub repository Netcracker/qubership-ai-packages (4 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,018 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 2026-09-05.