A browser skill for navigating pages, clicking, filling forms, extracting text, and taking screenshots through a managed browser session.

It is for reading and interacting with websites, including navigation, form entry, text extraction, and screenshots.

It gives the agent a defined way to operate a web browser, with different routing rules depending on the session type.

browser — Skill for Claude Code and Codex by aksika: A browser skill for navigating pages, clicking, filling forms…

Install

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.

agentmods

npx agentmods add skills/aksika/abtars/browser

Any agent

npx skills add aksika/abtars --skill browser

Clone the repo

git clone --depth 1 https://github.com/aksika/abtars

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/aksika/abtars/browser.svg)](https://agentmods.dev/skills/aksika/abtars/browser)

Your own site

<a href="https://agentmods.dev/skills/aksika/abtars/browser"><img src="https://agentmods.dev/badge/skills/aksika/abtars/browser.svg" alt="Measured on agentmods" height="20"></a>

Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 689 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00015	$0.00689
Opus 5	$0.00008	$0.00345
Sonnet 5	$0.00003	$0.00138
Haiku 4.5	$0.00002	$0.00069

Measured 3d ago against content hash 3a9696c993ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

browser 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 3d 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.

templates/skills/browser/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Browser Skill

CloakBrowser — stealth Chromium with 58 C++ source-level patches. Passes Cloudflare Turnstile, bot detection, 0.9 reCAPTCHA score.

Role routing

Read your current session type before choosing a path:

If you are Browsie (session type B / W): continue to CloakBrowser actions below.
If the user explicitly requests direct Main browser operation in the current turn: follow Emergency Direct Mode.
Otherwise (Main / any other session): create a B-type kanban card with a detailed goal using kanban_manage (Direct API) or abtars kanban create (ACP), report the card ID, and stop. Do NOT run browser commands inline.

Browsie — CloakBrowser actions

cloakbrowser --action <ACTION> [--url <URL>] [--selector <SEL>] [--value <VAL>] [--session-id <ID>] [--full-page]

Actions

navigate — go to URL (requires --url). Returns title, final URL, status.
click — click element (requires --selector)
fill — fill form field (requires --selector, --value)
extract_text — get visible text (optional --selector to scope, optional --url to navigate first). Truncates at 4000 chars.
screenshot — capture page (optional --full-page, optional --url to navigate first)
get_page_info — list interactive elements with selectors (max 50, optional --url to navigate first)
close_session — close browser session
set_cookie — set a cookie (requires --name, --value, optional --domain)

Sessions

Same --session-id = same browser tab across calls. Auto-close after 5 min idle. Max 3 concurrent.

Emergency Direct Mode (Main only)

Use ONLY when the user explicitly states in the current turn that Main should operate the browser directly.

cloakbrowser --action <ACTION> [--url <URL>] [--...] --session-id main-emergency-$(date +%s)

Rules

Acknowledge that managed tracking/attachment is being bypassed.
Use a unique session ID: main-emergency-<unix-timestamp>.
Perform only the requested bounded operation.
Close the session on success, failure, cancellation, and timeout (close_session).
Always use cloakbrowser directly — abtars does not ship a browser binary or alias.

Read the full file on GitHub · 68 lines

Changes

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.

3d ago First seen · 68 lines · 15 tokens per session scan A 3a9696c993ab

Subscribe to this mod's changes

browser is a skill published in the GitHub repository aksika/abtars (9 stars, last pushed 3d ago), licensed Apache-2.0. It adds 15 tokens to every session and 689 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.

Browser automation agent-security agent-swarm agentic-ai ai-agents ai-assistant ai-framework browse cloak interaction web

seo-crawl

Agent-wide core connector rule: when any connected search console is used, discover its operations with listconnectortools and invoke each selected operation through callconnectortool; naming listsites or an analytics operation without the core invocation is not execution.

Orkas-AI/Orkas · 3 tokens

seo-tech-audit

Judge the technical SEO facts produced by seo-crawl and return falsifiable findings + a health score. This is pure analysis — it does no network I/O and only reasons over the crawl JSON.

Orkas-AI/Orkas · 4 tokens

geo-score

Score how citable/ready a page is for AI answer engines, from crawl facts. Pure analysis — no network, no model calls. Deterministic so it is drift-comparable.

Orkas-AI/Orkas · 2 tokens

seo-content

Heuristic content/GEO-readiness analysis of the visible text from seo-crawl. No network. Judgments are heuristic (marked Estimated); raw counts are Measured.