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 autohandai/community-skills --skill agent-browser-toolshellgit clone --depth 1 https://github.com/autohandai/community-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/autohandai/community-skills/agent-browser-toolshell)<a href="https://agentmods.dev/skills/autohandai/community-skills/agent-browser-toolshell"><img src="https://agentmods.dev/badge/skills/autohandai/community-skills/agent-browser-toolshell/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/autohandai/community-skills/agent-browser-toolshell"><img src="https://agentmods.dev/badge/skills/autohandai/community-skills/agent-browser-toolshell.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 | $0.00105 | $0.02498 |
| Opus 5 | $0.00053 | $0.01249 |
| Sonnet 5 | $0.00021 | $0.00500 |
| Haiku 4.5 | $0.00011 | $0.00250 |
Grade A, and why
agent-browser scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to agent-browser — 1 line differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic Browser
Browser automation for AI agents via inference.sh. Uses Playwright under the hood with a simple @e ref system for element interaction.
Quick Start
Requires inference.sh CLI (
infsh). Get installation instructions:npx skills add inference-sh/skills@agent-tools
infsh login
# Open a page and get interactive elements
infsh app run agent-browser --function open --input '{"url": "https://example.com"}' --session new
Core Workflow
Every browser automation follows this pattern:
- Open - Navigate to URL, get
@erefs for elements - Interact - Use refs to click, fill, drag, etc.
- Re-snapshot - After navigation/changes, get fresh refs
- Close - End session (returns video if recording)
# 1. Start session
RESULT=$(infsh app run agent-browser --function open --session new --input '{
"url": "https://example.com/login"
}')
SESSION_ID=$(echo $RESULT | jq -r '.session_id')
# Elements: @e1 [input] "Email", @e2 [input] "Password", @e3 [button] "Sign In"
# 2. Fill and submit
infsh app run agent-browser --function interact --session $SESSION_ID --input '{
"action": "fill", "ref": "@e1", "text": "[email protected]"
}'
infsh app run agent-browser --function interact --session $SESSION_ID --input '{
"action": "fill", "ref": "@e2", "text": "password123"
}'
infsh app run agent-browser --function interact --session $SESSION_ID --input '{
"action": "click", "ref": "@e3"
}'
# 3. Re-snapshot after navigation
infsh app run agent-browser --function snapshot --session $SESSION_ID --input '{}'
# 4. Close when done
infsh app run agent-browser --function close --session $SESSION_ID --input '{}'
Functions
| Function | Description |
|---|---|
open |
Navigate to URL, configure browser (viewport, proxy, video recording) |
snapshot |
Re-fetch page state with @e refs after DOM changes |
interact |
Perform actions using @e refs (click, fill, drag, upload, etc.) |
screenshot |
Take page screenshot (viewport or full page) |
execute |
Run JavaScript code on the page |
close |
Close session, returns video if recording was enabled |
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.
- 9d ago First seen · 285 lines · 105 tokens per session scan A a4567b333149
agent-browser is a skill published in the GitHub repository autohandai/community-skills (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 105 tokens to every session and 2,498 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to agent-browser, differing in 1 line, and is treated as a copy.
Other skills, from other repositories
directory-management
Manages project directory setup and artifact organization. Use when starting a new project, resuming an existing one, or when a PLAN.md needs to be associated with a project directory. Creates the project folder structure (specs/, scripts/, notebooks/, manifests/, agentmemory/) and resolves project naming.
finetuning
Generates code that fine-tunes a base model using SageMaker serverless training jobs. Use when the user says "start training", "fine-tune my model", "I'm ready to train", or when the plan reaches the finetuning step. Supports SFT, DPO, RLVR, and RLAIF trainers, including RLVR Lambda reward function and RLAIF custom…
skill-topic-evaluator
A topic-evaluation tool that scores one proposed content idea across audience interest, account fit, competition, timing, revenue potential, effort, and compliance risk.
offer-compare-skill
A decision assistant for comparing two or more job offers across pay, growth, company strength, team risk, promotion, AI exposure, and lifestyle. Total compensation means the combined value of salary, bonuses, shares, and sign-on payments.
skill-news-intelligence
A daily industry-news research workflow that gathers in-depth articles and updates from Chinese technology, business, creator, and AI publications. It filters the results by a creator’s field and turns them into a brief with possible content topics.
style-transfer
A rewriting tool that changes the style of existing copy while keeping its main meaning. It can make text more humorous, conversational, literary, professional, sharp, or suited to social media.