hhru CLAUDE.md

Repository guidance for a command-line Playwright tool that searches hh.ru, a Russian job site, applies for jobs and raises résumé visibility. It runs manually, records actions, supports preview mode and uses daily limits and pauses.

In plain words
What is it for?
Use it when installing the tool, creating an account, adding CLI commands, defining read or write actions, or changing reports and dry-run behaviour.
Why use it?
It helps agents preserve the tool's manual-use, rate-limit and anti-fraud safeguards while following its fixed command and output formats.

Instructions file

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/axisrow/hhru/claude-md
Clone the repo
git clone --depth 1 https://github.com/axisrow/hhru
Per session 12,446 This file is loaded in full into every session.
When invoked 12,446 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.12446 $0.12446
Opus 5 $0.06223 $0.06223
Sonnet 5 $0.02489 $0.02489
Haiku 4.5 $0.01245 $0.01245

Measured 2d ago against content hash a0eca6e7547e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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`)
CLAUDE.md · 616 lines

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)

Read the full file on GitHub · 616 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. 2d ago First seen · 616 lines · 12,446 tokens per session scan A a0eca6e7547e

Subscribe to this mod's changes

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.