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 vibeeval/vibecosystem --skill browser-debugginggit clone --depth 1 https://github.com/vibeeval/vibecosystemWrote 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/vibeeval/vibecosystem/browser-debugging)<a href="https://agentmods.dev/skills/vibeeval/vibecosystem/browser-debugging"><img src="https://agentmods.dev/badge/skills/vibeeval/vibecosystem/browser-debugging.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 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 MCP Rug Pull · line 16 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 17 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00022 | $0.02956 |
| Opus 5 | $0.00011 | $0.01478 |
| Sonnet 5 | $0.00004 | $0.00591 |
| Haiku 4.5 | $0.00002 | $0.00296 |
Grade A, and why
browser-debugging 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 — 507 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Debugging (Chrome DevTools MCP)
Chrome DevTools MCP Setup
Kurulum
# NPM ile
npm install -g @anthropic/chrome-devtools-mcp
# veya npx ile (kurulum gerektirmez)
npx @anthropic/chrome-devtools-mcp
MCP Config (~/.mcp.json)
{
"mcpServers": {
"chrome-devtools": {
"command": "npx",
"args": ["-y", "@anthropic/chrome-devtools-mcp"],
"env": {
"CHROME_DEVTOOLS_PORT": "9222"
}
}
}
}
Chrome'u Debug Modunda Baslat
# macOS
/Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome \
--remote-debugging-port=9222 \
--user-data-dir=/tmp/chrome-debug
# Linux
google-chrome --remote-debugging-port=9222 --user-data-dir=/tmp/chrome-debug
# Headless mod
google-chrome --headless --remote-debugging-port=9222
Console Log Okuma ve Analiz
Console Mesajlarini Yakala
devtools.get_console_logs({
level: "error", // log | warn | error | info | debug
limit: 50,
clear_after: false
})
Console Mesaj Analizi
| Seviye | Anlam | Aksiyon |
|---|---|---|
| error | Runtime hatasi | HEMEN fix et |
| warn | Potansiyel sorun | Incele, gerekiyorsa fix |
| info | Bilgi mesaji | Debug icin kullan |
| log | Debug output | Temizle (production'da olmamali) |
Yaygin Console Hatalari
// TypeError: Cannot read properties of undefined
→ Null check eksik, optional chaining kullan: obj?.prop
// CORS error
→ Backend'de Access-Control-Allow-Origin header eksik
// Uncaught Promise rejection
→ async/await'te try/catch eksik
// React: Each child should have a unique key
→ map() icinde key={unique_id} ekle
// React: Maximum update depth exceeded
→ useEffect dependency array'de sonsuz dongu
Network Request Izleme
Request'leri Listele
devtools.get_network_requests({
url_filter: "/api/",
method: "POST",
status_code: 500,
limit: 20
})
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 · 507 lines · 22 tokens per session scan A a38d8fcbc8fe
browser-debugging is a skill published in the GitHub repository vibeeval/vibecosystem (530 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 2,956 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 2026-09-03.
Other skills, from other repositories
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
shepherd-triage
Launch parallel agents to check whether old bugs still reproduce on the live site, turning a stale backlog into a prioritized verified list. Use when a bug backlog needs cleaning without reading code.
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.linkedin-automation
Read before automating LinkedIn with browser tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile…
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…
triage-issue
Analyze a GitHub issue, verify claims against the codebase, and close invalid issues with a technical response.