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 haposoft/cafekit --skill agent-browsergit clone --depth 1 https://github.com/haposoft/cafekitWrote 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/haposoft/cafekit/agent-browser)<a href="https://agentmods.dev/skills/haposoft/cafekit/agent-browser"><img src="https://agentmods.dev/badge/skills/haposoft/cafekit/agent-browser/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/haposoft/cafekit/agent-browser"><img src="https://agentmods.dev/badge/skills/haposoft/cafekit/agent-browser.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00038 | $0.02278 |
| Opus 5.5 | $0.00015 | $0.00911 |
| Sonnet 5.5 | $0.00008 | $0.00456 |
| Haiku 4.5 | $0.00004 | $0.00228 |
Grade A, and why
cf:agent-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 2d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
3 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.
- 2d ago Changed 5138580c8fc3
- 1mo ago Changed · -1 tokens per session fffe932fb277
- 1mo ago First seen · 301 lines · 39 tokens per session scan A a90cc03056e2
cf:agent-browser is a skill published in the GitHub repository haposoft/cafekit (54 stars, last pushed 2d ago), with no licence file. It adds 38 tokens to every session and 2,278 once invoked, about $0.0002 per session on Opus 5.5. 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 Automation
Fast Rust-based headless browser automation CLI with Node.js fallback for AI agents, featuring navigation, clicking, typing, snapshots, and structured commands optimized for agent workflows.
visual-recon
Screenshot all live hosts for rapid visual triage and technology fingerprinting.
browser-automation
AI browser automation - navigate, interact, extract, verify via browser-use MCP.
Browser Automation
Use Home23's live browser controller for screenshots, navigation checks, and page extraction.
fuse-browser-usage
Use when about to call any mcpfuse-browser tool. Routes fetch/crawl/SERP vs live browser session vs screenshot capture, and enforces the 4 ZERO-TOLERANCE rules -- read BEFORE the tool call.
use-peek
Use the peek CLI to inspect, debug, and interact with native macOS app windows. Use when the user asks to debug a macOS app, inspect UI elements, take screenshots, click buttons, or automate interactions with native apps.