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.
npx agentmods add skills/rayan55050/progressive-agent/web_searchnpx skills add Rayan55050/progressive-agent --skill web_searchgit clone --depth 1 https://github.com/Rayan55050/progressive-agentWrote 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/skills/rayan55050/progressive-agent/web_search)<a href="https://agentmods.dev/skills/rayan55050/progressive-agent/web_search"><img src="https://agentmods.dev/badge/skills/rayan55050/progressive-agent/web_search.svg" alt="Measured on agentmods" 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 | $0.00008 | $0.00761 |
| Opus 5 | $0.00004 | $0.00380 |
| Sonnet 5 | $0.00002 | $0.00152 |
| Haiku 4.5 | $0.00001 | $0.00076 |
Grade A, and why
web_search 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 5d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Веб-поиск
У тебя есть 3 инструмента для работы с интернетом:
web_search— быстрый поиск. Возвращает AI-саммари + результаты с URL. Стоит 2 кредита. Используй для большинства запросов.web_extract— извлечение контента из конкретных URL. Стоит 1 кредит за 5 URL. Используй когда нужно прочитать конкретную страницу.web_research— глубокий ресёрч на тему. Стоит 4-250 кредитов. Используй ТОЛЬКО когда пользователь явно просит глубокий ресёрч, исследование, или анализ темы.
Когда что использовать
• "найди новости про X" → web_search
• "что нового в AI" → web_search с topic=news
• "прочитай эту статью [url]" → web_extract
• "сделай ресёрч на тему X" / "исследуй тему X" → web_research
• Обычные вопросы → web_search
Параметры web_search
• topic: auto (определяется автоматически), news, finance, general
• time_range: day, week, month, year (для свежих данных используй day или week)
• max_results: сколько результатов (по умолчанию 5)
Формат ответа (КРИТИЧЕСКИ ВАЖНО)
Каждый факт ОБЯЗАН быть подкреплён кликабельной ссылкой на источник. Ссылки спрятаны в тексте (инлайн), НЕ списком внизу.
Правильный формат:
🔥 *Claude Sonnet 4.6*
Anthropic выпустили свежий апгрейд. Перформанс на уровне Opus 4.5, но дешевле (подробнее на [Anthropic Blog](https://anthropic.com/news/...)). Уже доступен через API и Amazon Bedrock.
📌 *GPT-5 вышел*
OpenAI запустили новую модель в августе ([анонс](https://openai.com/blog/...)). Галлюцинации снижены до 1.6% на медицинском бенчмарке.
НЕПРАВИЛЬНЫЙ формат (НЕ ДЕЛАТЬ ТАК):
Claude Sonnet 4.6, Anthropic выпустили обновление.
Источники:
- https://anthropic.com/news/...
- https://openai.com/blog/...
Правила
- Каждый ключевой факт подкреплён инлайн-ссылкой текст
- URL берутся из результатов поиска (поле url или AI Summary), не выдумываются
- Ссылка спрятана в слове или фразе, не голый URL
- Если есть AI Summary в результатах, используй его как основу ответа
- Если результаты противоречивы, скажи об этом
- Отвечай на языке пользователя
- Не выдумывай информацию, только факты из поиска
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.
- 5d ago First seen · 74 lines · 8 tokens per session scan A 89c0fea5f92d
web_search is a skill published in the GitHub repository Rayan55050/progressive-agent (2 stars, last pushed 2d ago), licensed MIT. It adds 8 tokens to every session and 761 once invoked, about $0.0000 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 skills, from other repositories
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
summarize
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
weather
Get current weather and forecasts (no API key required).
github
Interact with GitHub using the gh CLI. Use gh issue, gh pr, gh run, and gh api for issues, PRs, CI runs, and advanced queries.
hive.browser-automation
Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…
hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…