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 instructions/axisrow/hhru/claude-mdgit clone --depth 1 https://github.com/axisrow/hhruWhat 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 | $0.12446 | $0.12446 |
| Opus 5 | $0.06223 | $0.06223 |
| Sonnet 5 | $0.02489 | $0.02489 |
| Haiku 4.5 | $0.01245 | $0.01245 |
Grade A, and why
hhru CLAUDE.md scanned grade A with 1 finding 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Подтверждено curl-дампом** (без логина): селекторы страницы поиска (`/search/vacancy`) How it starts
The opening of the file, as written. The whole thing — 616 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
О проекте
CLI-инструмент на Playwright для поиска вакансий, откликов и поднятия резюме на hh.ru.
Запускается только вручную из терминала. Каждая команда логирует свои действия,
поддерживает --dry-run и ограничена дневными лимитами + случайными паузами, чтобы
не выглядеть как подозрительная автоматизация для анти-фрод системы hh.ru. При работе
с этим кодом сохраняй этот принцип: не добавляй фоновые/скрытые режимы и не убирай
троттлинг/лимиты.
Интерфейс — только CLI, вывод только текст/ASCII-таблицы, без эмодзи. Эталон набора
команд и формата вывода (сигнатуры, примеры, природа READ/WRITE) — docs/cli-spec.md
(дизайн-документ ишью #21). Новую команду добавляй по образцу из спеки, её вывод должен
соответствовать зафиксированным там форматам (префиксы [OK]/[INFO]/[FAIL]/[DRY-RUN]/[skip],
ASCII-таблицы через report._ascii_table).
Команды
# Установка
pip3 install -r requirements.txt
python3 -m playwright install chromium
# Настройка (вся папка data/ в .gitignore — коммитить не нужно)
./scripts/run.sh account create default
# Все команды запускаются через обёртку run.sh (вызывает установленный entry point `hhru`)
./scripts/run.sh --account default login # ручной вход, сохраняет сессию
./scripts/run.sh --account default search --resume <id> --dry-run # поиск без откликов
./scripts/run.sh --account default apply --resume <id> --dry-run --limit 5 # план откликов
./scripts/run.sh --account default apply --resume <id> --limit 5 # боевой отклик
./scripts/run.sh --account default bump --resume <id> # поднять резюме (не чаще 1 раза в 4 часа)
./scripts/run.sh --account default run # apply + bump для всех резюме
# Общие флаги: --headless, --verbose, --config <path>, --history <path>, --max-pages <n>
# --resume опционален — без него команда идёт по всем резюме из конфига
# --max-pages по умолчанию адаптивный; --limit apply — целевое число УСПЕШНЫХ откликов (#441)
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.
- 2d ago First seen · 616 lines · 12,446 tokens per session scan A a0eca6e7547e
hhru CLAUDE.md is an instructions file published in the GitHub repository axisrow/hhru (22 stars, last pushed 2d ago), licensed MIT. It adds 12,446 tokens to every session, about $0.0622 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
spring-ai-agentcore AGENTS.md
Instructions for spring-ai-community/spring-ai-agentcore, covering agents.md, project overview, architecture, key components and artifact store classes.
flyto-core CLAUDE.md
Instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.
deepseekCLI CLAUDE.md
Instructions for cynchro/deepseekCLI, covering tarea actual, progreso, decisiones clave, próximos pasos and contexto importante.
deckforge AGENTS.md
Instructions for tph-kds/deckforge, covering deckforge agent entry point, code intelligence, read order, default routing and non-negotiable implementation rules.
fast-browser CLAUDE.md
Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.