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 browser-automationgit 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/browser-automation)<a href="https://agentmods.dev/skills/aden-hive/hive/browser-automation"><img src="https://agentmods.dev/badge/skills/aden-hive/hive/browser-automation.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 194 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 198 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 199 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 200 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 201 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00142 | $0.11213 |
| Opus 5 | $0.00071 | $0.05607 |
| Sonnet 5 | $0.00028 | $0.02243 |
| Haiku 4.5 | $0.00014 | $0.01121 |
Grade A, and why
hive.browser-automation 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 — 479 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GCU Browser Automation
All GCU browser automation drives a real Chrome instance through the Beeline extension and Chrome DevTools Protocol (CDP). You drive it from the terminal: every command is hive-browser <command> ... --json, run through terminal_exec. Always pass --json so the result is machine-readable. That means clicks, keystrokes, and screenshots are processed by the actual browser's native hit testing, focus, and layout engines — not a synthetic event layer. Understanding this unlocks strategies that make hard sites easy.
Browser lifecycle & recovery — read this before "fixing" anything
The bridge attaches to the user's already-running Chrome via the extension. The browser is not yours: it holds the user's logged-in sessions and other agents' work, and the runtime — not you — owns the connection to it. Consequences:
- There is nothing to "start." If no browser is connected,
hive-browser setup --jsontells you and gives the user install steps. Launching Chrome yourself (anygoogle-chrome/chromiumcommand,--remote-debugging-port,--user-data-dir, headless flags) is forbidden and blocked — it opens a browser the bridge can't see, often under the wrong profile. - There is no situation where killing the browser helps. Never use terminal tools to
kill/pkill/killallChrome, the bridge, or gcu processes. These commands are blocked, and attempting them breaks every agent sharing the connection. The same applies to the Hive desktop app andbridge_host. - A timeout is NOT a stuck browser. All
hive-browsercommands share one transport across all agents; one slow call (a heavyhive-browser evaluateon a big page) can make YOUR calls time out while the browser is perfectly healthy. The timeout message tells you whether the server passed its liveness check and whether recovery is already running — believe it. - Allowed recovery, in order: (1) wait ~30s and retry ONCE, with a smaller/simpler request — e.g. split a page-wide
hive-browser evaluatesweep into chunked queries; (2) close YOUR OWN tabs withhive-browser tab close <T> --jsonand reopen; (3) report the failure (report_to_parentor your reporting channel) and move on to work that doesn't need the browser. Escalate to the user; never to the process table. - Keep heavy
hive-browser evaluatescripts cheap: avoidinnerTextover thousands of nodes (each read forces layout). PrefertextContent, scope the selector, and paginate the sweep.
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 · 479 lines · 142 tokens per session scan A 5c7701a17939
hive.browser-automation is a skill published in the GitHub repository aden-hive/hive (11,021 stars, last pushed 2d ago), licensed Apache-2.0. It adds 142 tokens to every session and 11,213 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 2026-08-30.
Other skills, from other repositories
agent-browser
Headless browser automation CLI. Open, browse, interact with, and screenshot web pages. Use when: opening websites, browser-based login, web app testing, taking screenshots, UI verification.
playwright
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via playwright-cli or the bundled wrapper script.
win-computer-use
Drive a live Windows machine through the win-computer-use MCP server. Use when you need to automate a Windows desktop UI - move the mouse, click, type, take screenshots, open or close apps, run OCR, manage windows, read or write files, record the screen, or play back macros. Covers the virtual labeled cursor…
web-validation
Comprehensive web page validation with authentication, screenshot capture, mobile testing, and enhanced error detection.
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".
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.