Install
$ agentstack add skill-brianv1981-aim-browser-aim-browser-skill ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
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 -- --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 · --use · --close []
Navigate / wait: --url · --wait-ready · --wait-selector · --wait · --scroll-to-bottom · --solve-px
Discover: --elements · --content · --content-ax · --html · --screenshot · --fullpage · --imgsave
Interact: --click · --tap · --tapxy · --taptestid · --type · --textbox · --keytype · --keypress · --keycombo
Env / advanced: --eval "" · --block-media · --spy · --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';
See repo README.md and SECURITY.md. Seamless headed (Xvfb): docs/SEAMLESS_HEADED.md.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: BrianV1981
- Source: BrianV1981/aim-browser
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.