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 agentmods add skills/brianv1981/aim-browser/aim-browser.skillnpx skills add BrianV1981/aim-browser --skill aim-browser.skillgit clone --depth 1 https://github.com/BrianV1981/aim-browserWrote 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/brianv1981/aim-browser/aim-browser.skill)<a href="https://agentmods.dev/skills/brianv1981/aim-browser/aim-browser.skill"><img src="https://agentmods.dev/badge/skills/brianv1981/aim-browser/aim-browser.skill.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 | $0.00048 | $0.00695 |
| Opus 5 | $0.00024 | $0.00347 |
| Sonnet 5 | $0.00010 | $0.00139 |
| Haiku 4.5 | $0.00005 | $0.00069 |
Grade A, and why
aim-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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aim-browser
Agent CLI on the aim-browser engine. Prefer one-verb skills (google-ai, page-fetch, …) when they fit; use this skill for open-ended exploration.
Defaults
| Policy | Behavior |
|---|---|
| Window | Minimized (--start-visible / --visible to watch) |
| After new tab | Re-minimized (Chrome often un-minimizes) |
| CDP | Loopback only (127.0.0.1) |
| Profile | Sensitive — do not log cookies/secrets |
Prefer the daemon over ad-hoc headless Chrome.
Setup
cd /path/to/aim-browser && npm install
npm run skill -- --start # or: node aim-browser.skill/scripts/run.js --start
npm run skill -- --check
Install into a vessel: npm run install-skills -- <skills-dir> --mode symlink
(or link aim-browser.skill into the host skills path).
Flags (left → right; tab state kept)
Lifecycle: --start · --start-minimized · --start-visible · --show · --minimize · --maximize · --check · --stop
Tabs: --list · --open <url> · --use <index> · --close [<index>]
Navigate / wait: --url <url> · --wait-ready · --wait-selector <css> · --wait <ms> · --scroll-to-bottom · --solve-px
Discover: --elements · --content · --content-ax · --html · --screenshot <path> · --fullpage · --imgsave <path>
Interact: --click · --tap · --tapxy · --taptestid · --type · --textbox · --keytype · --keypress · --keycombo
Env / advanced: --eval "<js>" · --block-media · --spy <pattern> · --dlpath · --upload · --resize · --interactive / --repl
Examples
npm run skill -- --start --open "https://example.com" --elements
npm run skill -- \
--url "https://example.com" \
--type 2 "query" \
--keypress enter \
--wait-selector ".results" \
--screenshot /tmp/results.png
Engine (scripts)
After exploration, permanent jobs import the package:
import { AimBrowser, startDaemon, stopDaemon } from 'aim-browser';
What ships with it
1 file 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.
- 3d ago First seen · 71 lines · 48 tokens per session scan A 54d3d3dac2fe
aim-browser is a skill published in the GitHub repository BrianV1981/aim-browser (4 stars, last pushed 24d ago), licensed MIT. It adds 48 tokens to every session and 695 once invoked, about $0.0002 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.
Other skills, from other repositories
browser-automation
Use browser automation to inspect or interact with websites, test rendered interfaces, capture screenshots, and diagnose console or network behavior.
obscura
Operate and validate Obscura for JavaScript page loading, stealth browsing, anti-fingerprinting, tracker blocking, screenshots and visual comparison, CDP automation with Puppeteer or Playwright, screencasting, PDF export, MCP browser interaction, and web extraction. Use when running Obscura against deterministic…
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…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
pinchtab-stealth-score
Run the PinchTab stealth-score sweep against 15 bot-detection / fingerprint sites (sannysoft, rebrowser, deviceandbrowserinfo, iphey, whoer, browserscan, pixelscan, fingerprint-scan, incolumitas, fvision, amiunique, browserleaks, creepjs, coveryourtracks, fingerprint-demo). Starts a Docker PinchTab container per…
version-upgrade
Prepare, validate, and publish a Rustwright version across the Python/PyPI and Node.js/npm packages. Use when asked to bump or upgrade the Rustwright version, prepare a release PR, tag a release, publish Rustwright, or verify both package registries.