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/feedback-update)<a href="https://agentmods.dev/commands/s4nec4ke/hr-agent-ru/feedback-update"><img src="https://agentmods.dev/badge/commands/s4nec4ke/hr-agent-ru/feedback-update/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/feedback-update"><img src="https://agentmods.dev/badge/commands/s4nec4ke/hr-agent-ru/feedback-update.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 | $0.00086 | $0.03491 |
| Opus 5 | $0.00043 | $0.01746 |
| Sonnet 5 | $0.00017 | $0.00698 |
| Haiku 4.5 | $0.00009 | $0.00349 |
Grade A, and why
feedback-update 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 8d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/feedback-update — обработка ответов HR
Принципы
- Парсер качает только Telegram. Email/LinkedIn не обрабатываются.
- Файлы из
vacancies/feedback result/обрабатываются по одному, хронологически. - Классификация — через инлайн LLM-интерпретатор (это ты, по промпту в
engine/feedback_store/prompts/interpreter.md). - Изменения применяются тиерно (см. Шаг 4): аппенд в
correspondence.mdи рутинные forward-переходы статуса — автоматически;отказ,назначено интервьюи auto-unarchive — только после подтверждения. Если рискованных изменений в прогоне нет — он проходит молча, без вопросов.
Storage layout
vacancies/feedback result/{ISO-ts}_{channel}_{dialog_id}.json— батчи от парсера. Имя начинается с ISO-времени (ГГГГ-ММ-ДДTчч:мм:сс), поэтому сортировка файлов по алфавиту даёт их в хронологическом порядке (нужно для обработки по очереди в Шаге 3).vacancies/items/{id} ...folder.../correspondence.md— лог переписки этой вакансии. Создаётся при первом сообщении, далее апендится.vacancies/vacancies.csv— CSV активных вакансий. Обновляется одним Write в конце.vacancies/vacancies_archive.csv— архив (создаёт/archive-vacancies). Этот скилл умеет восстанавливать строки из архива обратно при auto-unarchive.vacancies/items_archive/— архив папок вакансий. При auto-unarchive папка возвращается вvacancies/items/.engine/data/feedback_store.json— НЕ редактируется этим скиллом напрямую. Парсер сам зовётfeedback_store mark-fetched(включаяlast_message_utc).engine/feedback_store/prompts/interpreter.md— твоя инструкция для классификации.
Шаг 1. Запусти парсер
cd engine && venv\Scripts\python.exe -m feedback_collector.main
Возможные результаты:
No active Telegram dialogs in feedback_store— store пуст или все вакансии inactive. Ответ: «Нет активных диалогов» и стоп.Wrote 0 files / 0 new messages— ничего нового. Может всё ещё быть необработанные файлы с прошлого раза → переходи к Шагу 2 (если файлы есть, обработай их).Wrote N files / M new messages— есть что обрабатывать.
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.
- 8d ago First seen · 175 lines · 86 tokens per session scan A 45d906520eb4
feedback-update is a command published in the GitHub repository s4nec4ke/hr-agent-ru (2 stars, last pushed 3mo ago), licensed MIT. It adds 86 tokens to every session and 3,491 once invoked, about $0.0004 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
evolve
Cluster related instincts into skills, commands, or agents.
suggest-automation
A command that reviews recent Git commits and project instructions to find work patterns that happen repeatedly.
instinct-import
Import instincts from teammates, Skill Creator, or other sources.
instinct-export
Export instincts for sharing with teammates or other projects.
context-stats
Display context window usage and token statistics.
run
Execute prompt(s) from ./prompts/ with automatic archiving - for structured prompt-based work.