Borrowing it
Nothing to install: this file belongs to TheSmokeDev/taskchad-os. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/TheSmokeDev/taskchad-os/master/.claude/skills/agent-browser/SKILL.mdgit clone --depth 1 https://github.com/TheSmokeDev/taskchad-osWrote 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/thesmokedev/taskchad-os/agent-browser)<a href="https://agentmods.dev/skills/thesmokedev/taskchad-os/agent-browser"><img src="https://agentmods.dev/badge/skills/thesmokedev/taskchad-os/agent-browser.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 5.1 | $0.00065 | $0.01422 |
| Opus 5 | $0.00032 | $0.00711 |
| Sonnet 5 | $0.00013 | $0.00284 |
| Haiku 4.5 | $0.00006 | $0.00142 |
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 6d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Browser
Use this skill when browser state matters and the workflow needs the user's logged-in, visible browser.
Prime And Upstream Sources
Read the local deployment manual and load the installed CLI's version-matched core skill before acting:
Get-Content docs\browserops-agent-browser-manual.md
agent-browser skills get core --full
Use the official sources when commands, CDP behavior, sessions, bundled skills, or known bugs may have changed:
- https://agent-browser.dev/
- https://agent-browser.dev/commands
- https://agent-browser.dev/skills
- https://agent-browser.dev/cdp-mode
- https://github.com/vercel-labs/agent-browser
- https://github.com/vercel-labs/agent-browser/releases
Check version drift without changing the machine:
agent-browser --version
npm view agent-browser version
agent-browser skills list --json
Review intervening releases and get operator authority before running
npm install -g agent-browser@latest. Do not run agent-browser install for
this attach-only deployment; it downloads an Agent Browser-managed Chrome.
After an authorized update, reload core, run BrowserOps tests, and prove one
read-only --cdp 18222 attachment.
Contract
- Use one persistent visible browser per deployment.
- Attach through CDP. Do not launch a separate headless or test browser.
- Put
--cdp 18222on every direct local command. Never use bareopen, auto-connect, or upstream example port9222on this machine. - Use current snapshot refs or allowlisted selectors and real Agent Browser
click/fillcommands. Never substituteeval,HTMLElement.click(), injected JavaScript, blind coordinates, or address-bar typing. - Re-snapshot after navigation or DOM mutation and verify the resulting URL, selected state, or visible confirmation.
- Do not copy cookies, profiles, raw tokens, tabs,
.envfiles, or service credentials between machines. - Do not scrape or print secrets from browser storage.
- Do not perform external writes such as posts, DMs, connection requests, purchases, or profile edits unless the user explicitly asks for that exact action.
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.
- 6d ago First seen · 149 lines · 65 tokens per session scan A 5b281674864f
agent-browser is a skill published in the GitHub repository TheSmokeDev/taskchad-os (23 stars, last pushed 14d ago), licensed MIT. It adds 65 tokens to every session and 1,422 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
notte
Deploy browser automations as scheduled, API-callable serverless Functions — plus stealth sessions, vault-backed login, captcha solving, and natural-language agent runs via the Notte CLI. Turns any browser flow into a deterministic Bitterbot-callable endpoint, ideal for crystallized skills + dream-engine cron…
browser-use
Control a real browser to navigate pages, click, type, fill forms, inspect rendered UI, take screenshots, or record video. Load only when the user asks to open or automate a browser, interact with or test rendered page UI, scrape a site that needs browser execution, or capture a browser screenshot or video. Do not…
unix_computer_use
Local and remote desktop observation/input tools with coordinate normalization (local macOS/Linux by default; optional OSWorld HTTP and SSH Mac backends).
node-inspect-debugger
Debug Node.js via --inspect + Chrome DevTools Protocol.
browser-actionability-debug
Diagnose browser UI tests or real browser checks where an element appears visible but cannot be clicked, copied, hovered, or focused. Use for Playwright/Chrome/browser automation failures involving overlays, splash screens, opacity transitions, pointer-events, elementFromPoint mismatches, clipboard assertions, or…
e2e-setup
Set up Playwright e2e automation tailored to this team and app. Probes the running app (auth mechanism, API surface, spec availability), interviews with recommendations instead of open questions, scaffolds the playwright/ folder, and records every decision in playwright/AUTOMATION.md for the other e2e skills to read.…