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 xonika9/agent-skills --skill x9-browser-sessiongit clone --depth 1 https://github.com/xonika9/agent-skillsWrote 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/xonika9/agent-skills/x9-browser-session)<a href="https://agentmods.dev/skills/xonika9/agent-skills/x9-browser-session"><img src="https://agentmods.dev/badge/skills/xonika9/agent-skills/x9-browser-session.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 | $0.00108 | $0.02594 |
| Opus 5 | $0.00054 | $0.01297 |
| Sonnet 5 | $0.00022 | $0.00519 |
| Haiku 4.5 | $0.00011 | $0.00259 |
Grade B, and why
x9-browser-session scanned grade B 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 yesterday.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- The Codex MCP route uses `~/.codex/config.toml` and the shared focus-safe rules. How it starts
The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser session
Use this skill in OpenCode, Claude Code, and Codex. It owns shared route selection, the verified Edge adapter, runtime-specific extension and in-app surfaces, CDP fallbacks, task-tab isolation, and focus safety. Re-check installed tool instructions and live schemas when a named surface is absent.
chrome-devtools MCP allowlist
Targets in this list bypass the browser extension in every route that offers one. An entry matches the exact hostname and its subdomains; do not infer sibling or look-alike domains.
avito.ru
Avito traffic discipline
Treat one account, browser profile, and public IP as one browsing lane for the whole parent task. Avito work is sequential even when the rest of the research is delegated:
- appoint one Avito operator; subagents may analyze captured data but must not browse
avito.ruconcurrently; - keep only one Avito navigation, search, or listing load in flight. Prefer one task tab; extra tabs may hold queued pages, but interact with only one at a time;
- let the current page finish loading and inspect it before requesting the next page; shortlist from search results and reuse captured data instead of repeatedly reopening or refreshing listings;
- do not bulk-load listings, paginate rapidly, poll availability, or run retry loops;
- when Avito shows an IP or security-check interstitial that requires no user action, keep the same page, controller, and profile. Wait five seconds once without reloading, navigating, or initiating another request, then inspect the same page again. Continue serial browsing if the requested content is visible;
- if the same interstitial remains on the second inspection, or Avito returns a CAPTCHA
requiring user action,
429, timeout, access-denied, or an error page, treat it as site throttling rather than a controller failure. Stop Avito requests across the parent task, preserve collected results, and returnDEGRADED; do not switch controllers, profiles, agents, or IP addresses to continue; - resume only when the user requests another check or ordinary access is already visibly restored. Perform that check serially through the same browser profile.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday Changed · +6 lines a8e370f97150
- 8d ago First seen · 195 lines · 108 tokens per session scan B 8541a75a00a9
x9-browser-session is a skill published in the GitHub repository xonika9/agent-skills (4 stars, last pushed 3d ago), licensed MIT. It adds 108 tokens to every session and 2,594 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
e2e-automator
Build robust end-to-end test suites with Playwright or Cypress. Covers page objects, fixtures, visual testing, and CI integration.
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
opencli-autofix
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
opencli-browser-sitemap
Use when driving a website with opencli browser and sitemap context is available, requested, or needed to avoid blind navigation. Guides agents to consume site sitemap files lazily, choose adapter/browser fallback paths, resume from state signatures, and mark stale sitemap entries without trusting them over live…
pinchtab
Use this skill when a task needs browser automation through PinchTab: open a website, inspect interactive elements, click through flows, fill out forms, scrape page text, reuse a dedicated automation profile with user approval, export screenshots or PDFs, manage multiple browser instances, or fall back to the HTTP API…