Instructions for operating a Chrome browser that is shared live with a person. The agent can inspect pages, forms, network requests, and the page structure, while the person handles tasks such as captchas, two-factor authentication, and anti-bot checks.

Use it to navigate and analyse websites, extract rendered content, fill forms, inspect the DOM or network traffic, and continue after the person clears a login or security checkpoint.

It divides browser work between the agent and the human when a page requires direct human interaction or an existing logged-in browser session.

tandem — Skill for Claude Code by bgmacris/quimera-ai

Install

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.

Any agent

npx skills add bgmacris/quimera-ai --skill tandem

Clone the repo

git clone --depth 1 https://github.com/bgmacris/quimera-ai

Made for: Claude Code.

Or install tandem, the plugin that ships this one along with the rest of its 2 skills, 6 commands, 1 agent, 1 MCP server.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/bgmacris/quimera-ai/tandem/github.svg)](https://agentmods.dev/skills/bgmacris/quimera-ai/tandem)

Your own site

<a href="https://agentmods.dev/skills/bgmacris/quimera-ai/tandem"><img src="https://agentmods.dev/badge/skills/bgmacris/quimera-ai/tandem/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/bgmacris/quimera-ai/tandem"><img src="https://agentmods.dev/badge/skills/bgmacris/quimera-ai/tandem.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,563 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00068	$0.03563
Opus 5.5	$0.00027	$0.01425
Sonnet 5.5	$0.00014	$0.00713
Haiku 4.5	$0.00007	$0.00356

Measured yesterday against content hash 05cc4caca325, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tandem 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 yesterday.

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.

plugins/tandem/skills/tandem/SKILL.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

tandem — shared browser, human + Claude

The human and you share ONE SAME Chrome in real time. The human sees it and drives it with the mouse; you operate it with the browser_* tools of the tandem MCP (Playwright over CDP). What one does, the other sees: state, cookies, and session are the same.

Startup

The browser starts ON ITS OWN: a PreToolUse hook (scripts/autostart.mjs) checks CDP before every browser_* call and, if nothing answers, starts tandem's Chrome and tells you so ("started it"). A fresh Chrome may have lost logins: say so to the human before acting on a walled page.
Where autostart is off (TANDEM_AUTOSTART=0, or WSL by default — the browser may be an external Windows Chrome), the call is DENIED with "no browser answers": ask the human to start it (/tandem:browser-start or their own browser). Check state with /tandem:browser-status.

Division of labor

The human does what requires being human: solving captchas, getting past anti-bot checkpoints (e.g. Vercel Security Checkpoint), 2FA logins, visual decisions.
You do the analysis: browser_snapshot (accessibility tree, better than a screenshot for reasoning and acting), browser_evaluate (JS), browser_network_requests, data extraction, filling forms, clicking by snapshot ref.
Typical unblocking pattern: the human clears the wall → you read the already-rendered DOM and analyze.

Two modes: live vs delegated (don't pollute the context)

There are two ways to navigate; choose by the task, not one by default:

Live (in this context): when there's handoff with the human (walls they clear: captcha, checkpoint, login), interactive navigation, or on-the-fly decisions. The human is in the loop.
Delegated to the web-navigator subagent: when it's HEAVY read/extraction without walls (large snapshots, scraping, walking many pages). The subagent swallows the DOM/snapshots in ITS context and returns to you only the distilled data → this context isn't polluted. You share the SAME Chrome (global state), so the human keeps seeing the window.
Rule: if the task will generate a lot of noise (snapshots of hundreds of KB, multi-page) and does NOT need the human live → delegate. If it needs human handoff or iterating with you → live.
Limit of delegation: the subagent doesn't talk to the human. If it hits a wall, it returns which and where; you tell the human, they clear it, and you relaunch the subagent to continue.

Read the full file on GitHub · 188 lines

Changes

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.

yesterday Changed · +13 lines 05cc4caca325
6d ago Changed · +13 lines 3779d6c63493
15d ago Changed · +9 lines db5bb26b4e52
2mo ago First seen · 153 lines · 68 tokens per session scan A e9eb87f7e94c

Subscribe to this mod's changes

tandem is a skill published in the GitHub repository bgmacris/quimera-ai (12 stars, last pushed 2d ago), licensed MIT. It adds 68 tokens to every session and 3,563 once invoked, about $0.0003 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.

Browser automation ai-agents anthropic browser-automation cdp chrome-devtools-protocol claude

tandem next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
tandembgmacris/quimera-ai	Skill	12	2d ago	MIT	A	68	Claude Code
chrome-agentsderosiaux/chrome-agent	Skill	96	25d ago	MIT	A	44	Claude Code, Codex
scrape-structured-datasderosiaux/chrome-agent	Skill	96	25d ago	MIT	A	111	Claude Code, Codex
cdpilotmehmetnadir/cdpilot	Skill	33	21d ago	MIT	A	93	Claude Code
owbwoniu9524/open-web-bridge	Skill	114	2mo ago	MIT	A	143	Claude Code, Codex
browserDevZonayed/Mochi	Skill	3	3d ago	MIT	A	50	Claude Code
control-chrome-bridgeShalomObongo/chrome-bridge-mcp	Skill	0	3mo ago	MIT	A	114	Claude Code, Codex