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 agents/nickzaitsev/ru-normalizr/conventionsgit clone --depth 1 https://github.com/NickZaitsev/ru-normalizrWrote 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/agents/nickzaitsev/ru-normalizr/conventions)<a href="https://agentmods.dev/agents/nickzaitsev/ru-normalizr/conventions"><img src="https://agentmods.dev/badge/agents/nickzaitsev/ru-normalizr/conventions.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 5.1 | $0.00000 | $0.00418 |
| Opus 5 | $0.00000 | $0.00209 |
| Sonnet 5 | $0.00000 | $0.00084 |
| Haiku 4.5 | $0.00000 | $0.00042 |
Grade A, and why
conventions 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 6d 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.
What it actually says
Output conventions
- Measure-head constructions such as
диаметром/высотой/объёмом Nkeep the numeral in the nominative; the head noun does not govern the measurement. - Ranges with
с … по …end in singularгод/век;до … векаis also singular. - Byte-family units use ordinary Russian counting forms consistently:
1 байт,2–4 байта,5 байтов, including prefixed units. - Регистр латинских информационных обозначений является частью смысла:
Mb,Mbps,Mb/s— мегабиты, аMB,MBps,MB/s— мегабайты. Неизвестный неоднозначный вариант регистра не угадывается. - Ограниченные составные единицы читаются целиком:
/задаёт сохранённое в реестре отношение (мг/кг→ «миллиграммов на килограмм»,мл/мин→ «миллилитров в минуту»), а·— лексикализованное произведение (кВт·ч→ «киловатт-час»). Вложенные и неизвестные выражения не разбираются. - References governed by
см./смотриuse an accusative reference noun and a cardinal label:смотри рисунок два, таблицу три, страницу четыре. - Default and safe initial settings use ordinary Russian letter names (
Е. → е) and preserve source punctuation, including when initial expansion is enabled. - TTS initial settings double isolated vowel names (
Е. → ее) and surround a non-final surname-first initial with comma pauses (Рихтер Ч. разработал → Рихтер, чэ, разработал); both settings can be overridden independently. - Latin
Ais read asэй.
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.
- 6d ago First seen · 24 lines · 0 tokens per session scan A 5f008c143669
conventions is an agent published in the GitHub repository NickZaitsev/ru-normalizr (22 stars, last pushed 29d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 418 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 2026-08-30.
Other agents, from other repositories
ai-polish-text-expert
Jestem agentem orkiestrującym zintegrowany system pracy z treściami tekstowymi w języku polskim. Zarządzam trzema wyspecjalizowanymi skills i kieruję każde żądanie do właściwego skill'a — automatycznie lub na podstawie komendy użytkownika.
compliance-checker
Agent ensuring compliance with Polish language standards and legal regulations (RODO/GDPR).
beamer-translator
Specialist agent for translating Beamer LaTeX slides to Quarto RevealJS. Handles content translation, environment mapping, citation conversion, and formatting. Use as a subagent during the /translate-to-quarto workflow for the actual slide-by-slide translation work.
RULES
Agent "RULES" from phel-lang/phel-lang, covering phel rules + cli, rules, new features (v0.30 – main), gotchas and cli.
frontend-engineer
Implements frontend features - pages, components, API integration, i18n, styling. Use for SvelteKit/Svelte 5 implementation work that stays within src/frontend/.
docs-syncer
Keep kkRepo public documentation accurate and bilingual.