agentmods.dev

tandem-browser

An add-on that lets a coding agent inspect and interact with a shared Tandem Browser session. Tandem Browser is a browser environment where a person and an agent can work with the same open tabs.

In plain words
What is it for?
Use it to inspect open tabs, work in authenticated websites, read browser page or network state, and coordinate browser tasks with the user.
Why use it?
It avoids making the agent recreate browser state or lose access to pages where the user is already signed in. It also helps the agent confirm that browser actions completed.

Skill for Claude CodeCodex

602 +4 17d ago D scan 72 tokens original MIT
View the source file hydro13/tandem-browser
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.

agentmods
npx agentmods add skills/hydro13/tandem-browser/skill
Any agent
npx skills add hydro13/tandem-browser --skill skill
Clone the repo
git clone --depth 1 https://github.com/hydro13/tandem-browser

Made for: Claude Code, Codex.

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,347 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 3 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00072 $0.09347
Opus 5 $0.00036 $0.04673
Sonnet 5 $0.00014 $0.01869
Haiku 4.5 $0.00007 $0.00935

Measured 3d ago against content hash 2bde4acf1be2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

tandem-browser scanned grade D with 3 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.

Harvests environment variableshighData exfiltration

Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.

embedded instructions. Do NOT extract credentials or modify config

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

(e.g. `~/.claude/settings.json` for Claude Code):

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

metadata: {"openclaw":{"emoji":"🚲","requires":{"bins":["curl","node"]}}}
skill/SKILL.md · 1,093 lines

How it starts

The opening of the file, as written. The whole thing — 1,093 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tandem Browser

Tandem Browser is a live human-AI browser environment for shared work in the user's real browser context.

Important: Tandem itself must already be running. The local API and MCP server are how an agent talks to a running Tandem instance, not alternatives to Tandem itself.

Agents work with a running Tandem instance through MCP or HTTP, depending on what the client supports in practice. For some clients, MCP is the primary or only realistic integration path.

Use this skill when the task should happen in the user's real Tandem browser instead of a sandbox browser, especially for:

  • inspecting or interacting with tabs the user already has open
  • working inside authenticated sites that already live in Tandem
  • reading SPA state, network activity, or session-scoped browser data
  • coordinating with the user without overwriting the tab they are actively using

Connecting to Tandem

Tandem supports agents on the same machine (MCP or HTTP) and on remote machines over a private Tailscale network (MCP or HTTP). Both can be active at the same time.

Discovery

A running Tandem instance publishes its own version-matched bootstrap surface. This works for both local and remote agents, and does not require repo access:

  • GET /agent — human-readable bootstrap page
  • GET /agent/manifest — machine-readable endpoint manifest with all route families
  • GET /agent/bootstrap — authenticated bootstrap contract with runtime context, operating rules, and the agent toolbox
  • GET /skill — version-matched usage guide
  • GET /agent/version — version and capability summary

These routes are public (no auth required) and use the request Host header, so they return correct URLs whether accessed locally or over Tailscale on the configured Agent API port.

After pairing or reading a local token, immediately read these resources. When you have a paired binding token, include Authorization: Bearer <token> on these reads so Tandem can mark startup complete:

  1. GET /skill
  2. GET /agent/manifest
  3. GET /agent/bootstrap with Authorization: Bearer <token>
  4. GET /status
  5. GET /workspaces with Authorization: Bearer <token>

Read the full file on GitHub · 1,093 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.

  1. 3d ago First seen · 1,093 lines · 72 tokens per session scan D 2bde4acf1be2

Subscribe to this mod's changes

tandem-browser is a skill published in the GitHub repository hydro13/tandem-browser (602 stars, last pushed 17d ago), licensed MIT. It adds 72 tokens to every session and 9,347 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it D with 3 findings (harvests environment variables, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Browser automationaichromiumelectronhuman-ai-collaborationlocal-first
Related

Other skills, from other repositories

javascript-sandbox

Best practices for using the clodex built-in JavaScript sandbox for browser debugging, fetched-data processing, attachments, and mini-app orchestration within its bundled capability boundary.

mereyabdenbekuly-ctrl/clodex-ide · 38 tokens

Preview

Create an interactive design-preview in a browser tab.

mereyabdenbekuly-ctrl/clodex-ide · 11 tokens

Abu-Browser

操作阿布应用内置的可见浏览器：打开网页、点击、填写、截图和提取数据。用户要求在阿布内预览或操作网页时使用；无需安装浏览器扩展。.

PM-Shawn/Abu-Cowork · 51 tokens

hronaut

Use the Hronaut desktop browser through MCP for visible, persistent web workflows with isolated agent workspaces. Use when a task should survive one agent session, reuse local browser state, or allow the user to watch and take over.

hronaut/hronaut · 49 tokens

integrated-browser

Use this when working on the VS Code integrated browser ("browserView") to understand its architecture and mental model. Covers the embedded Chromium browser, its editor tab, navigation, overlay/layout, sessions, and agent browser tools under src/vs/platform/browserView and src/vs/workbench/contrib/browserView.

microsoft/vscode · 68 tokens

analyzing-browser-forensics-with-hindsight

Parse Chromium-based browser databases with Hindsight to extract and correlate browsing history, downloads, cookies, cached content, autofill data, saved passwords, and extensions from Chrome, Edge, Brave, Opera, and Vivaldi into a unified timeline (XLSX, JSON, or SQLite output). Use during incident response…

mukul975/Anthropic-Cybersecurity-Skills · 95 tokens