ru-normalizr AGENTS.md

ru-normalizr AGENTS.md is an instructions file for Codex, OpenCode from NickZaitsev/ru-normalizr. It costs 1,397 tokens per session, scanned A, original, MIT.

Repository instructions for ru-normalizr, a Russian-text normalization library used in text-to-speech and language-processing systems.

In plain words
What is it for?
Use them when changing Russian text normalization, documentation, changelogs, version files, dependencies, or contribution practices.
Why use it?
They keep normalization rules general instead of adding fragile one-off replacements, while also setting documentation, changelog, security, and release rules.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

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.

agentmods
npx agentmods add instructions/nickzaitsev/ru-normalizr/agents-md
Clone the repo
git clone --depth 1 https://github.com/NickZaitsev/ru-normalizr

Made for: Codex, OpenCode.

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 ru-normalizr AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nickzaitsev/ru-normalizr/agents-md.svg)](https://agentmods.dev/instructions/nickzaitsev/ru-normalizr/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/nickzaitsev/ru-normalizr/agents-md"><img src="https://agentmods.dev/badge/instructions/nickzaitsev/ru-normalizr/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,397 This file is loaded in full into every session.
When invoked 1,397 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01397 $0.01397
Opus 5 $0.00698 $0.00698
Sonnet 5 $0.00279 $0.00279
Haiku 4.5 $0.00140 $0.00140

Measured 6d ago against content hash c1c8d84c4b85, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ru-normalizr AGENTS.md 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.

AGENTS.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ru-normalizr — Russian text normalization for TTS/NLP

Core principle

Generalizable, morphology-aware rules. Never add a one-off replacement for a single token or phrase — if a bug reproduces, fix the rule, not the string. Target production-ready quality: no quick hacks or fragile workarounds unless explicitly requested.

Changelog and versions

  • Any user-visible change goes to CHANGELOG.md under ## Unreleased.
  • Never bump the version outside explicit release tasks. On release, keep __init__.py, pyproject.toml, and CHANGELOG.md in sync (see VERSIONING.md).

General rules

Write README.md, documentation, MRs and UI text in Russian. Target production-ready quality: no quick hacks, temporary workarounds, or fragile solutions unless explicitly requested. Never commit secrets or .env files; never print secrets to logs, error messages, events, or API responses. YAGNI: Do not add infrastructure or integrations nobody asked for (monitoring, metrics, tracing, admin panels). Propose first; add only after explicit approval. Whenever you identify a workaround, defect, or reliability risk, please highlight it and suggest a proper fix.

Commits and branches

  • Commit completed work yourself when a task or phase is finished — atomic conventional commits.
  • Before every commit, run the project's lint, type-check, and test commands. Defaults when none are configured: Python — uv run ruff check . && uv run pyright (plus uv run pytest if tests exist); TypeScript — npm run check, otherwise the project's lint/type-check scripts plus relevant tests. Fix all errors caused by your changes.
  • Commit messages and MR titles follow Git Atomic Conventional Commits: keep the type and scope in English (feat(auth):, fix(db):), write the description after the colon in Russian — e.g. feat(consent): интегрировать Яндекс.Метрику.
  • Maintain .gitignore yourself: add generated, local, temporary, cache, build, and environment files as they appear.
  • In the Bash tool, pass multi-line commit messages via -m with a regular double-quoted string (or heredoc), NOT PowerShell @'...'@ syntax — the @ leaks into the message text.
  • Do not create new branches without explicit user confirmation. Work in the current branch; сreate a branch only on explicit request.
  • On a push request: (1) run lint/type-check/tests; (2) push the current branch; (3) create annotated tag tested-N (next N from git ls-remote --tags origin) on the pushed commit and push it. Skip step 3 if 1 or 2 failed. Never move or delete existing tags.

Read the full file on GitHub · 83 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. 6d ago First seen · 83 lines · 1,397 tokens per session scan A c1c8d84c4b85

Subscribe to this mod's changes

ru-normalizr AGENTS.md is an instructions file published in the GitHub repository NickZaitsev/ru-normalizr (22 stars, last pushed 29d ago), licensed MIT. It adds 1,397 tokens to every session, about $0.0070 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.

Related

Other instructions, from other repositories

pipelex CLAUDE.md

Claude Code instructions for Pipelex/pipelex, covering pipelex coding rules, commands, linting, keyword-only arguments check and cleaning derived files.

Pipelex/pipelex · 4,125 tokens

Shark AGENTS.md

Instructions for kaandedeoglu/Shark, covering agents.md, positioning (keep docs/marketing consistent with this), build and development commands, building the project and build in debug mode.

kaandedeoglu/Shark · 2,319 tokens

morloc CLAUDE.md

Claude Code instructions for morloc-project/morloc, covering claude.md, project overview, general rules, checking code and other rules.

morloc-project/morloc · 633 tokens

copy-tuner-ruby-client CLAUDE.md

Claude Code instructions for SonicGarden/copy-tuner-ruby-client, covering claude.md, コマンド, アーキテクチャ, 開発スタイル and gotchas.

SonicGarden/copy-tuner-ruby-client · 1,005 tokens

python-docs-zh-tw CLAUDE.md

Claude Code instructions for python/python-docs-zh-tw, covering python documentation traditional chinese translation, build commands, translation conventions, punctuation and cjk-latin spacing.

python/python-docs-zh-tw · 413 tokens

editorial-skill-for-natural-russian-business-writing AGENTS.md

Instructions for ValentinAvramko/editorial-skill-for-natural-russian-business-writing, covering инструкции для агента, язык и документация, границы документов, источник правды and git.

ValentinAvramko/editorial-skill-for-natural-russian-business-writing · 348 tokens