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/crawlio-app/crawlio-browser/monitornpx skills add Crawlio-app/crawlio-browser --skill monitorgit clone --depth 1 https://github.com/Crawlio-app/crawlio-browserWrote 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/crawlio-app/crawlio-browser/monitor)<a href="https://agentmods.dev/skills/crawlio-app/crawlio-browser/monitor"><img src="https://agentmods.dev/badge/skills/crawlio-app/crawlio-browser/monitor.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 | $0.00021 | $0.00634 |
| Opus 5 | $0.00010 | $0.00317 |
| Sonnet 5 | $0.00004 | $0.00127 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
monitor 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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Monitor — Resident Change Detection
Use this skill to watch an HTTP/HTTPS page across time. Crawlio creates a background tab, captures
a compact ARIA baseline, and schedules recaptures with chrome.alarms. Collection lives in the
extension: an MCP disconnect or server restart does not erase the baseline or skip scheduled work.
Start
Call the default-mode observe tool:
{
"action": "monitor_start",
"url": "https://target.example/page",
"label": "pricing page",
"intervalMinutes": 5
}
Retain the returned monitorId. The response includes the initial baseline. Chrome alarms have a
30-second minimum and can run late under browser load; do not promise wall-clock precision.
Query
Status does not touch the page:
{ "action": "monitor_status", "monitorId": "mon_..." }
Read recent diffs without returning the full snapshots:
{
"action": "monitor_results",
"monitorId": "mon_...",
"limit": 10,
"includeSnapshot": false
}
Each result carries changed, additions, removals, unchanged, and diff. Cite changed diff
lines as evidence; there is no sample field. If technology or performance evidence is required,
use execute after a change is detected and call smart.detectTechnologies() or
smart.extractPage() explicitly. The resident monitor itself claims structural/content change
only.
Stop or Delete
Stop future captures but retain history:
{ "action": "monitor_stop", "monitorId": "mon_...", "closeTab": true }
Delete a monitor and its retained snapshots:
{ "action": "monitor_clear", "monitorId": "mon_...", "closeTab": true }
Use monitor_status and monitor_results to inspect retained work, monitor_stop to end future
captures, and monitor_clear to delete a monitor and its snapshots. The extension popup is
status-only and does not manage resident work. Storage is bounded to 25 MiB with oldest completed
runs/snapshots evicted first; no unlimitedStorage or new Chrome permission is used. Compact ARIA
snapshots intentionally retain visible page text in local extension storage, so monitor only pages
whose displayed content the user agrees to retain; the snapshots are not sent to Crawlio by this
lifecycle.
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 · 81 lines · 21 tokens per session scan A 15c29cc5ff5d
monitor is a skill published in the GitHub repository Crawlio-app/crawlio-browser (6 stars, last pushed 24d ago), licensed Apache-2.0. It adds 21 tokens to every session and 634 once invoked, about $0.0001 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
nekoro-browser
浏览器自动化——打开网页、搜索、点击、截图、执行 JS、填表、上传文件、处理对话框。通过 Chrome 扩展的 chrome.debugger API 操控用户日常浏览器,保留登录态,不开调试端口。触发词:"浏览器"、"打开网页"、"搜索"、"截图"、"点击"、"填表"、"上传文件"、"自动化操作"。.
owb
Open Web Bridge (OWB) — drive the user's own real browser with the owb command. Read pages behind their existing logins, gather and cross-check information, fill forms, walk multi-step flows, debug their site, audit responsive/accessibility behavior, and capture or reverse-engineer network traffic. Use this whenever…
browsertap-default
浏览器自动化默认入口。任何打开网页、填表、点击、截图、抓取或复用已登录 Chrome/Edge 的任务,优先使用 browsertap-mcp (BTAP) MCP 工具。.
browsertap-bridge-recovery
恢复 browsertap-mcp (BTAP) 的 CDP 桥连。触发:桥断了 / MCP 浏览器工具挂住 / getsetupstatus 转圈 / listtabs 拿不到 tab / Unknown command: downloads。分层排错:netstat → /link curl → listtabs,别把 MCP 层挂当成桥断。.
browser
Use this skill when the user says browser, /browser, test in Chrome, inspect a webpage, verify a localhost app, capture screenshots, check console/network errors, run browser QA, or automate browser flows with the Mochi browser MCP.
control-chrome-bridge
Drive the user's real Chrome browser — their own profile, tabs, cookies and logged-in sessions — through the chrome-bridge MCP server. Use for tasks that need existing browser state: reading a page behind a login, filling a form on a site the user is signed into, testing a local app in a real browser, or inspecting…