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.
git clone --depth 1 https://github.com/s4nec4ke/hr-agent-ruWrote 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/commands/s4nec4ke/hr-agent-ru/hr-collect)<a href="https://agentmods.dev/commands/s4nec4ke/hr-agent-ru/hr-collect"><img src="https://agentmods.dev/badge/commands/s4nec4ke/hr-agent-ru/hr-collect/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/s4nec4ke/hr-agent-ru/hr-collect"><img src="https://agentmods.dev/badge/commands/s4nec4ke/hr-agent-ru/hr-collect.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00108 | $0.03564 |
| Opus 5 | $0.00054 | $0.01782 |
| Sonnet 5 | $0.00022 | $0.00713 |
| Haiku 4.5 | $0.00011 | $0.00356 |
Grade A, and why
hr-collect 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Сборщик и анализатор вакансий
Этот скилл запускает парсер вакансий (Telegram + RSS), оценивает каждую вакансию относительно профиля кандидата и добавляет подходящие в локальное хранилище.
Структура хранилища
vacancies/vacancies.csv— CSV-таблица (10 колонок, минимум текста). Колонки:id,Роль,Компания,Зарплата,Формат,Совпадение,Статус,Вакансия,Дата добавления,язык- Контакт / Тип контакта / Канал / Комментарий НЕ в CSV — они живут в шапке
card.mdсоответствующей вакансии. vacancies/items/{id} {short_role} {company}/— папка на каждую вакансию. В неё кладём:source.md— полный текст вакансии (шапка + raw post)card.md— создаётся ЭТИМ скиллом с шапкой-метаданными (Контакт, Тип контакта, Канал, Комментарий + Зарплата, Формат, Совпадение). Поле**Резюме:**ставится «не указано» —/cv-matchзаполнит ссылкой. Тело карточки (Контекст вакансии + Отклик) добавляет/vacancy-cardпозже.
vacancies/parsing result/— буфер + аудит-лог:{date}_{channel}_{msg_id}.txt— одна вакансия = один файл, создаёт парсер. Этот скилл удаляет файл после обработки (accepted или rejected).{date}.json— лог приёма за день. Скрипт пишет запись соstatus: "pending"при скачивании. Этот скилл обновляет статус на"accepted"(заполняетid) или"rejected"(заполняетreason).
Имя папки в items строится так:
{id}— id из CSV (без zero-padding){short_role}— первые 2-3 значимых слова из Роль (без слешей, скобок, спецсимволов FS:\ / : * ? " < > |){company}— имя компании (если пусто →Unknown)
Пример: vacancies/items/40 Product Manager VOICE/
Шаг 1: Запусти парсеры
Используй инструмент PowerShell (не Bash — кириллические символы в пути ломаются под WSL/Git Bash). Запусти обе команды (Telegram и RSS) последовательно. Если одна из них падает по сети — продолжай, обработаешь то что есть.
Telegram-парсер:
Push-Location "engine"; & ".\venv\Scripts\python.exe" -m tg_collector.main; Pop-Location
RSS-парсер (WWR, remoteok и другие фиды из config/rss_sources.py):
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.
- 11d ago First seen · 242 lines · 108 tokens per session scan A 29a3dbb6a15e
hr-collect is a command published in the GitHub repository s4nec4ke/hr-agent-ru (2 stars, last pushed 3mo ago), licensed MIT. It adds 108 tokens to every session and 3,564 once invoked, about $0.0005 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 2026-08-31.
Other commands, from other repositories
workflow-classify
Classify task size (S/M/L/XL) and recommend the appropriate workflow pipeline.
security-review
A security review procedure based on CWE, a list of common software weaknesses, and STRIDE, a method for identifying threats to a system.
spreadsheet-audit
Perform a 6-step audit of an Excel spreadsheet for formula correctness, formatting consistency, data integrity, boss-auditable simplicity, and spec compliance. Uses the excel-screenshot MCP server tools — no Excel installation required.
research-perplexity
Run a deep research query using Perplexity's /research mode via Playwright browser automation. This is an alternative to /export-to-council that uses Perplexity's dedicated research mode instead of multi-model council.
update-counts
Update all hardcoded counts (skills, agents, marketplace repos/skills) across documentation from filesystem.
handoff
Create a comprehensive handoff document for the current work session.