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.
npx skills add Netcracker/qubership-ai-packages --skill seedgit 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/seed)<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.
<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>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 | $0.02018 |
| Opus 5 | $0.00000 | $0.01009 |
| Sonnet 5 | $0.00000 | $0.00404 |
| Haiku 4.5 | $0.00000 | $0.00202 |
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.
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 — YbecomesX (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.
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.
- 5d ago First seen · 133 lines · 0 tokens per session scan A b60d5f55184a
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.