A workflow for applying to jobs on hh.ru, a Russian job-search website, including checking an application before sending it.

Use it to apply for vacancies, inspect an application form, send a cover letter, or manage application steps on hh.ru.

It reduces the risk of sending an incorrect application by requiring a dry run and separate user confirmation before the real submission.

hhru-apply — Skill for Claude Code and Codex by axisrow: A workflow for applying to jobs on hh.ru, a…

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 skills/axisrow/hhru/hhru-apply

Any agent

npx skills add axisrow/hhru --skill hhru-apply

Clone the repo

git clone --depth 1 https://github.com/axisrow/hhru

Made for: Claude Code, Codex.

Or install hhru-cc-plugin, the plugin that ships this one along with the rest of its 4 skills, 1 command.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/axisrow/hhru/hhru-apply.svg)](https://agentmods.dev/skills/axisrow/hhru/hhru-apply)

Your own site

<a href="https://agentmods.dev/skills/axisrow/hhru/hhru-apply"><img src="https://agentmods.dev/badge/skills/axisrow/hhru/hhru-apply.svg" alt="Measured on agentmods" height="20"></a>

Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 972 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5	$0.00079	$0.00972
Opus 5	$0.00039	$0.00486
Sonnet 5	$0.00016	$0.00194
Haiku 4.5	$0.00008	$0.00097

Measured 4d ago against content hash ff1f9f5a1cc2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hhru-apply 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 4d 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.

skills/hhru-apply/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

hhru-apply — воркфлоу отклика

Отклик на вакансии hh.ru — write-команда к hh.ru, самая safety-critical. Строго соблюдай порядок: сначала сухой прогон, потом боевой — и только с подтверждением пользователя.

Этот skill описывает один типовой workflow, но не меняет общий принцип CLI: команды — примитивы, а не отдельная готовая команда под каждую пользовательскую задачу. Нестандартные задачи собирай поэтапно из существующих команд; общий пример с редактированием разделов резюме приведён в skills/hhru/SKILL.md.

Разрешение браузера в Codex

Все браузерные шаги этого workflow (list-resumes, probe, dry-run и боевой apply, при необходимости login) с первого запуска выполняй с sandbox_permissions=require_escalated. Не запускай их сначала в sandbox и не используй --headless как замену разрешению: Chromium требует разрешённого пути в обоих режимах. Обычный локальный whoami разрешения браузера не требует.

Elevated-разрешение — только право запустить Chromium, а не согласие на отклик. Dry-run и отдельное явное подтверждение пользователя перед боевым apply остаются обязательными.

Шаг 1 — проверь готовность

hhru whoami
hhru list-resumes

Если сессия невалидна — login (интерактивный, требует пользователя). Если резюме нет в конфиге — скажи пользователю заполнить resume_url в data/config.yaml.

Шаг 2 — изучи форму отклика (probe, READ)

Для конкретной вакансии — диагностический дамп формы без отправки:

hhru probe --vacancy-id <id>

probe ничего не отправляет на hh.ru (submit не кликается). Полезен, чтобы проверить селекторы формы и AI-письмо до боевого отклика.

Шаг 3 — сухой прогон (dry-run, обязательно)

hhru apply --resume <id> --dry-run --limit 5

--dry-run показывает план откликов без действия на hh.ru. Покажи пользователю, на какие вакансии бот откликнется, и получи подтверждение.

Важно: dry-run-отклики тоже пишутся в локальную историю и считаются «уже откликались» — боевой запуск на Шаге 4 пропустит именно те вакансии, что были показаны в плане Шага 3, и подберёт другие кандидаты (или ни одного, если подходящих вакансий больше нет). Это не баг, а дедупликация по дизайну — предупреди пользователя, что боевой список может отличаться от dry-run-плана.

Read the full file on GitHub · 85 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.

4d ago First seen · 85 lines · 79 tokens per session scan A ff1f9f5a1cc2

Subscribe to this mod's changes

hhru-apply is a skill published in the GitHub repository axisrow/hhru (23 stars, last pushed today), licensed MIT. It adds 79 tokens to every session and 972 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 2026-08-30.

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens