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/add-vacancy)<a href="https://agentmods.dev/commands/s4nec4ke/hr-agent-ru/add-vacancy"><img src="https://agentmods.dev/badge/commands/s4nec4ke/hr-agent-ru/add-vacancy/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/add-vacancy"><img src="https://agentmods.dev/badge/commands/s4nec4ke/hr-agent-ru/add-vacancy.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 | $0.00144 | $0.02502 |
| Opus 5 | $0.00072 | $0.01251 |
| Sonnet 5 | $0.00029 | $0.00500 |
| Haiku 4.5 | $0.00014 | $0.00250 |
Grade A, and why
add-vacancy 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 10d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Vacancy (manual)
Скилл для ручного добавления одной вакансии. В отличие от /hr-collect, этот не запускает парсер и не работает с parsing result/. Принимает на вход URL и текст вакансии или скриншот вакансии прямо в сообщении пользователя.
Входные данные
Нужен текст вакансии — сообщением или скриншотом (текст со скрина читай сам). URL желателен, но необязателен.
- Нет ни текста, ни скриншота — попроси прислать.
- Нет URL — возьми со скриншота, если виден; иначе работай без него (
Канал: manual, дедуп по Роль+Компания).
Step 1: Read context
Прочитай параллельно:
profile\candidate_context.md— для скорингаvacancies\vacancies.csv— для дедупа по URL и max id
Max id: PowerShell (Get-Content "...\vacancies.csv" -Tail 1 -Encoding UTF8).Split(',')[0] → +1 = next_id.
Step 2: Dedup check
Если URL уже встречается в колонке «Вакансия» CSV → отчитайся «эта вакансия уже добавлена под id={existing_id}» и стоп. Не пересоздавай папку, не дублируй строку.
Step 3: Extract metadata
Из присланного текста извлеки:
- Роль — название позиции (Product Manager, Senior PM, BD Manager, и т.п.)
- Компания — если упоминается; иначе пусто
- Зарплата — если указана; иначе пусто
- Формат — remote / hybrid / office / unknown
- Язык — на каком языке написана вакансия (ru / en)
- Контакт — конкретное значение для связи: telegram-хэндл (
@xxx), email, URL формы/ATS. Если в тексте нет отдельного контакта — используй сам URL вакансии (часто отклик идёт через ту же ссылку) - Тип контакта — telegram / email / форма / linkedin / ATS / notion / агрегатор / другое
Контакт (telegram/email/linkedin) при сохранении заносится в feedback_store.json — см. Step 7d.
Step 4: Определить Канал из URL
Не Telegram → извлекаем домен и приводим к короткому имени:
| URL host | Канал |
|---|---|
linkedin.com |
linkedin |
x.com, twitter.com |
twitter/x |
weworkremotely.com |
weworkremotely |
remoteok.com |
remoteok |
cryptojobslist.com |
cryptojobslist |
notion.site, notion.so |
notion |
*.workable.com, *.ashbyhq.com, lever.co, greenhouse.io, и т.п. ATS |
<companyname> если можно вытащить из субдомена, иначе host |
| любой другой домен | минимально-чистый host (example.com → example) |
Telegram (t.me/...) |
@channelname. |
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.
- 10d ago First seen · 182 lines · 144 tokens per session scan A 20cf331bec0d
add-vacancy is a command published in the GitHub repository s4nec4ke/hr-agent-ru (2 stars, last pushed 3mo ago), licensed MIT. It adds 144 tokens to every session and 2,502 once invoked, about $0.0007 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.