OpenHive is a runtime for groups of specialized AI agents that collaborate on long-running business processes. A persistent lead agent, called the Queen, creates and coordinates worker agents while the system manages state, recovery, observability, costs, and human oversight. The catalogue entries provide agent skills, instructions, and integrations for working with this harness.
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 skills add aden-hive/hive --skill telegram-notifications-setupgit clone --depth 1 https://github.com/aden-hive/hiveWrote 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/aden-hive/hive/telegram-notifications-setup)<a href="https://agentmods.dev/skills/aden-hive/hive/telegram-notifications-setup"><img src="https://agentmods.dev/badge/skills/aden-hive/hive/telegram-notifications-setup.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 | $0.00121 | $0.02226 |
| Opus 5 | $0.00060 | $0.01113 |
| Sonnet 5 | $0.00024 | $0.00445 |
| Haiku 4.5 | $0.00012 | $0.00223 |
Grade A, and why
hive.telegram-notifications-setup scanned grade A with 1 finding 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
decrypt the stored token, curl `getUpdates`, or otherwise debug the API by hand: How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Telegram Notifications Setup (Sentinel)
Sentinel pings the user on Telegram when a colony stalls and lets them reply to
keep it going. It needs one thing: a Telegram bot token (123456:ABC-…),
created via @BotFather and stored under credential id telegram. The same token
sends alerts and reads the user's replies.
You do the whole thing end to end with the sentinel_setup tool (the same API
the desktop connector uses): create the bot, store the token, detect the chat,
point Sentinel at it, and send a test — without making the user paste anything.
Activate hive.browser-automation first — this skill assumes you know the
lifecycle rules (the bridge attaches to the user's own Chrome; never launch or kill
a browser), the screenshot + viewport-fraction coordinate workflow, and
hive-browser interact. Telegram Web is a heavy SPA with custom rendering, so prefer the
screenshot + coordinate path over selectors when the snapshot is unclear.
Telegram Web specifics (verified)
- Telegram Web defaults to the K version at
https://web.telegram.org/k/. The selectors below are verified there; fall back to screenshot + coordinates if a selector doesn't match (e.g. the older/a/version). - Message composer:
#editable-message-text— click it,typeyour text, send with the Enter key. Used for/newbot,/start, etc. - Global search: the search box is top-left (around
[0.13, 0.04]). Click it, type a name, then click the result row to open that chat. - Read a bot's reply as text (don't OCR a screenshot): run
hive-browser page text ".chat-message:last-child" --jsonin the terminal — it returns the latest message verbatim — this is how you capture the token without transposing characters.
Before you start — check what already exists
- Run
sentinel_setup({"action": "status"}). If it showstelegramalready configured, the token's stored — skip to Step 3 (detect the chat) (or straight to Step 4 if the colony config is already set), don't make a new bot. - Confirm the user is signed into Telegram: run
hive-browser open/hive-browser navigate https://web.telegram.org/k/ --jsonin the terminal. You cannot log in for them — you don't have their phone or SMS code. If it shows a QR / phone-number login, STOP and ask the user to log into Telegram Web in their Chrome, then continue. Don't fight the login screen or try to switch login methods yourself.
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.
- 7d ago First seen · 163 lines · 121 tokens per session scan A 36877925ba30
hive.telegram-notifications-setup is a skill published in the GitHub repository aden-hive/hive (11,018 stars, last pushed yesterday), licensed Apache-2.0. It adds 121 tokens to every session and 2,226 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
article-writer
Multi-style article creation skill. Supports 5 writing styles (deep analysis, practical guide, story-driven, opinion, news brief), including complete workflow: material collection → outline → content → formatting. Activated when users mention "write article", "write post", "create", or "draft".
develop-web-game
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.
skin-creator
Create and apply a two-asset LobsterAI visual skin from the user's style description. Use only when the AI Skin Designer kit supplies the structured skinpack workflow marker; do not use for ordinary theme or image requests.
content-planner
WeChat Official Account topic planning and content calendar management. Based on WeChat article search and trending analysis, generates differentiated topic recommendations and outputs structured content calendars. Activated when users mention "topic", "planning", "content calendar", "trending", or "what to write next…
music-search
Search cloud drives for downloadable music resources (songs, albums, lossless audio). Use this skill when the user wants to download a specific song or album. Do NOT use for general music information, lyrics, or recommendations.
skill-vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.