What is gsd-browser AGENTS.md?

A browser-automation tool for AI agents that controls Chrome or Chromium. MCP, the Model Context Protocol, lets compatible AI tools call its browser actions.

Opening pages, clicking and typing, filling forms, checking page content, extracting structured data, testing different devices, mocking network requests, and recording browser sessions.

It removes the need to manually operate a browser or build one-off scripts for navigation, form interaction, page checks, data extraction, and test evidence.

How open-gsd/gsd-browser configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to open-gsd/gsd-browser. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/open-gsd/gsd-browser/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/open-gsd/gsd-browser

Made for: Codex, OpenCode.

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/instructions/open-gsd/gsd-browser/agents-md/github.svg)](https://agentmods.dev/instructions/open-gsd/gsd-browser/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/open-gsd/gsd-browser/agents-md"><img src="https://agentmods.dev/badge/instructions/open-gsd/gsd-browser/agents-md/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/instructions/open-gsd/gsd-browser/agents-md"><img src="https://agentmods.dev/badge/instructions/open-gsd/gsd-browser/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 559 This file is loaded in full into every session.

When invoked 559 The same file — it is already loaded in full.

Security scan C 2 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	$0.00559	$0.00559
Opus 5.5	$0.00224	$0.00224
Sonnet 5.5	$0.00112	$0.00112
Haiku 4.5	$0.00056	$0.00056

Measured 2mo ago against content hash d0512769030a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

gsd-browser AGENTS.md scanned grade C with 2 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 2mo 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://raw.githubusercontent.com/open-gsd/gsd-browser/main/install.sh | bash

Makes network callslowCapability

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

curl -fsSL https://raw.githubusercontent.com/open-gsd/gsd-browser/main/install.sh | bash

AGENTS.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

gsd-browser

Native Rust browser automation CLI for AI agents. Controls Chrome/Chromium via CDP with a persistent background daemon. Supports navigation, element interaction (click, type, fill), snapshots with versioned refs, assertions, form analysis, structured data extraction, visual regression testing, network mocking, device emulation, auth vault, prompt injection scanning, live viewer collaboration, recording/evidence bundles, and self-healing via action cache.

Primary path for AI agents (2026+): gsd-browser mcp — the stdio MCP server exposing 50+ tools, live resources, and executable prompts. All the unique strengths (refs, viewer + human handoff + annotations + recordings, semantic intents, evidence, batch, self-healing, etc.) become automatically available to Cursor, Claude Desktop, VS Code + Copilot, and other MCP clients.

Quick Start (CLI)

gsd-browser navigate https://example.com
gsd-browser snapshot
gsd-browser click-ref @v1:e1

Quick Start (MCP — Recommended for Agents)

gsd-browser mcp

Then point your MCP client at the command. Run ./scripts/mcp-quickstart.sh cursor (or claude/vscode) for tailored config snippets.

See:

docs/mcp.md
docs/AGENT-BEST-PRACTICES.md (essential — golden rules, workflows, "When to Use What")
Root SKILL.md (full semantics backing every MCP tool)
gsd-browser-skill/ (curated pack for coding agents)

Installation

curl -fsSL https://raw.githubusercontent.com/open-gsd/gsd-browser/main/install.sh | bash

# install the Codex Plugin integration too
curl -fsSL https://raw.githubusercontent.com/open-gsd/gsd-browser/main/install.sh | bash -s -- --codex-plugin

# or from a repo checkout
cargo install --path cli

Requires Chrome or Chromium. The installer reuses a system browser when present and downloads Chromium automatically where Chrome for Testing is available. It also offers to install the gsd-browser-skill/ pack.

Full Reference

See SKILL.md for complete command reference (90+ CLI commands), workflow patterns, configuration, and examples.

Read the full file on GitHub · 50 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.

2mo ago First seen · 50 lines · 559 tokens per session scan C d0512769030a

Subscribe to this mod's changes

gsd-browser AGENTS.md is an instructions file published in the GitHub repository open-gsd/gsd-browser (57 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 559 tokens to every session, about $0.0022 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Browser automation

gsd-browser AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
gsd-browser AGENTS.mdopen-gsd/gsd-browser	Instructions file	57	1mo ago	Apache-2.0	C	559	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

gsd-browser: Instructions file for Codex