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 agentmods add skills/talkstream/ru-text/ru-scorenpx skills add talkstream/ru-text --skill ru-scoregit clone --depth 1 https://github.com/talkstream/ru-textWrote 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/talkstream/ru-text/ru-score)<a href="https://agentmods.dev/skills/talkstream/ru-text/ru-score"><img src="https://agentmods.dev/badge/skills/talkstream/ru-text/ru-score.svg" alt="Measured on agentmods" 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 | $0.00075 | $0.01410 |
| Opus 5 | $0.00037 | $0.00705 |
| Sonnet 5 | $0.00015 | $0.00282 |
| Haiku 4.5 | $0.00007 | $0.00141 |
Grade A, and why
ru-score 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 3d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Russian Text Quality Score
Score the text provided in $ARGUMENTS (or the most recent Russian text output if no arguments) using the ru-text scoring rubric.
Procedure
Where the reference files live
This skill reads the corpus that ships with the ru-text skill, which is installed alongside it. Locate that folder once, then read the named files from it:
- Look for a directory named
referenceswhose parent directory is namedru-text, and which containsinfo-style.md. Every file named below sits in that folder. - Search with file tools, never with a shell.
Globon a pattern like**/ru-text/references/info-style.md, or whatever file search the host offers, thenRead. This command has no use for a command line:Bashis on itsdisallowed-toolslist, and hosts that do not implement that field still refuse it — measured in Claude Cowork on 12.08.2026, where an openinglsreturned «Permission to use Bash has been denied» in red before the search found the corpus anyway. The call bought nothing and cost the reader a scare. - In Claude Code the plugin root is also available directly, which saves the search.
- Do not guess a path. If the folder cannot be found, say so and stop — a check run against remembered rules instead of the corpus is not this command, and reporting one as the other is the failure this whole product exists to prevent.
-
Load rubric — read
scoring.mdfor the full rubric with anchors. -
Determine domain — identify whether the text is UI/interface, business email, article, or general:
- UI text → also load
ux-writing.mdfor the Reader Precision dimension - Business email → also load
business-writing.mdfor the Reader Precision dimension - General → use
info-style.mdonly
- UI text → also load
-
Evaluate each dimension separately — score in this order:
- T — Типографика (weight 0.15): quotes, dashes, spaces, special characters per
typography.md - Ч — Чистота языка (weight 0.25): stop-words, bureaucratic language, clichés, passive voice per
info-style.md+anti-patterns.md - Г — Грамотность (weight 0.20): punctuation, agreement, tautology per
editorial-grammar.md+editorial-punctuation.md - С — Структура (weight 0.20): logical flow, paragraphs, transitions, heading use per
info-style.mdstructure section +addenda.md - Ц — Точность для читателя (weight 0.20): facts, evidence, reader benefit, actionability per domain rules
- T — Типографика (weight 0.15): quotes, dashes, spaces, special characters per
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.
- 3d ago First seen · 97 lines · 75 tokens per session scan A 1057f053b01a
ru-score is a skill published in the GitHub repository talkstream/ru-text (222 stars, last pushed 6d ago), licensed MIT. It adds 75 tokens to every session and 1,410 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
article-sketchnote-editorial
把一个概念铸成杂志专题档案——真问题→失败→转折→顿悟→命名, 6 个 layout 模具 + 4 字族对比 + 探案档案细节.
deck-swiss-international
16 列网格 + 单一饱和 accent + 22 个锁死版面 (Klein Blue / Lemon / Mint / Safety Orange).
deck-guizang-editorial
电子杂志 × 电子墨水; 10 个版面 + 5 套调色板 (墨水/靛蓝瓷/森林墨/牛皮纸/沙丘).
doc-kami-parchment
暖羊皮纸底 (#f5f4ed) + 墨蓝单色 accent (#1B365D) + 单一衬线字体, 编辑级排印.
frame-data-chart-nyt
NYT-newsroom 排版 + 错峰揭示动画 + 编辑级图表 (折线/柱/范围带).
deck-magazine-web
电子杂志 × 电子墨水风, WebGL 流体背景 + 衬线 display.