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/mutation-windowsgit 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/mutation-windows)<a href="https://agentmods.dev/agents/nickzaitsev/ru-normalizr/mutation-windows"><img src="https://agentmods.dev/badge/agents/nickzaitsev/ru-normalizr/mutation-windows.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 | $0.00000 | $0.00305 |
| Opus 5 | $0.00000 | $0.00152 |
| Sonnet 5 | $0.00000 | $0.00061 |
| Haiku 4.5 | $0.00000 | $0.00030 |
Grade A, and why
mutation-windows 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.
What it actually says
Ограничения mutmut на Windows
Разовый mutation-аудит выполняется только во временном git worktree: mutmut
переписывает исходники на месте, а незавершённый прогон оставляет артефакты и
дочерние процессы.
На Windows mutmut 2.4.5 --use-coverage запускает отдельный pytest для каждого
мутанта и пересобирает окружение. Даже небольшой модуль с двумя файлами тестов
может не завершиться за пять минут; широкий запуск для dictionary.py однажды
разогнал дочерний pytest до десятков гигабайт приватной памяти. Поэтому такие
прогоны нельзя оставлять без контроля: после таймаута нужно остановить дерево
процессов и удалить временный worktree, а новые проверки добавлять по уже
подтверждённым поведенческим случаям.
Проверка 3 августа 2026 года показала дополнительный риск: после запуска из
временного worktree mutmut оставил основной checkout с тем же содержимым файла,
но с изменёнными переводами строк (LF → CRLF). Это было восстановлено до
исходного состояния. Перед каждым таким запуском нужно проверять git status и
в основном checkout, и в worktree; после таймаута — завершать всё дерево
процессов, а не только оболочку.
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 · 21 lines · 0 tokens per session scan A df1b4c57221b
mutation-windows is an agent published in the GitHub repository NickZaitsev/ru-normalizr (22 stars, last pushed 28d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 305 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
RULES
Agent "RULES" from phel-lang/phel-lang, covering phel rules + cli, rules, new features (v0.30 – main), gotchas and cli.
fixture-reviewer
Audits .test integration fixtures under tests/php/Integration/Fixtures for drift against the current compiler output. Use after lexer, parser, analyzer, or emitter changes.
module-docs-sync
Audits and updates CLAUDE.md files in src/php/ modules to match the actual code. Use after large refactors, new modules, or periodic maintenance.
tdd-coach
Guides test-driven development with red-green-refactor discipline. Use when implementing features or fixes with TDD.
quick-syntax
One-screen cheatsheet. For exhaustive rules see RULES.md; for typing details see tasks/typed-defn.md.
owner-judge
Reviews proposed changes to VoiceStudio against the owner's documented standards. Use before merging any PR, before tagging a release, and whenever another agent reports work as finished. Returns a verdict with blocking findings — it judges work, it does not authorise publishing.