What is chrome-tab-remote AGENTS.md?

Project instructions for an AI coding assistant working on chrome-tab-remote, a Chrome extension and backend that let a user select one browser tab for an agent to inspect or control.

Use them when changing or reviewing the chrome-tab-remote codebase, especially features involving tab access, screenshots, or publishing.

They give contributors the repository's current goals, security boundaries, and collaboration rules in one place.

How ai-4-you/chrome-tab-remote configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to ai-4-you/chrome-tab-remote. 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/ai-4-you/chrome-tab-remote/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/ai-4-you/chrome-tab-remote

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/ai-4-you/chrome-tab-remote/agents-md/github.svg)](https://agentmods.dev/instructions/ai-4-you/chrome-tab-remote/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/ai-4-you/chrome-tab-remote/agents-md"><img src="https://agentmods.dev/badge/instructions/ai-4-you/chrome-tab-remote/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/ai-4-you/chrome-tab-remote/agents-md"><img src="https://agentmods.dev/badge/instructions/ai-4-you/chrome-tab-remote/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,157 This file is loaded in full into every session.

When invoked 1,157 The same file — it is already loaded in full.

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	$0.01157	$0.01157
Opus 5.5	$0.00463	$0.00463
Sonnet 5.5	$0.00231	$0.00231
Haiku 4.5	$0.00116	$0.00116

Measured 1mo ago against content hash 5cc224abab5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

chrome-tab-remote AGENTS.md 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 1mo 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.

AGENTS.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — chrome-tab-remote

Durable collaboration memory for this repository. Read PROJECT_OVERVIEW.md first for current state and next actions.

What this repo is

A trust-first Chrome extension (plus backend communication) that lets a user explicitly select one tab which a backend/agentic system may then inspect and control. Security and corporate adoptability are the product's core differentiator, not an afterthought. North star: IDEA.md.

Collaboration rules (durable)

Deployment and value bar — non-negotiable

Ship only changes backed by enough evidence that they can be blindly and honestly trusted for deployment without user code review. If deploy safety remains uncertain, deliver no change.
Ship only changes that demonstrably improve the real workflow—not theoretically, possibly, or maybe. If the benefit is unproven, deliver no change.
The agent owns the proof: tests alone are insufficient when material runtime risk remains. Never call work deployable while a consequential uncertainty is unresolved.
Every repository agent must self-organize to keep this bar active during work and persist future clarifications in the narrowest canonical repository-owned document; chat acknowledgment alone is not memory.
2026-08-02: Git commits must NOT carry a Co-Authored-By: Claude … trailer (user decision; overrides the default).

Scope decisions (durable)

2026-08-04: Distribution for v1 is a public Chrome Web Store listing. Managed enterprise force-install by Store ID remains compatible; enterprise certification and signed/cross-platform native-host productisation are a separate delivery track. Canonical execution plan: docs/cws-signed-publishing-plan.md.
2026-08-04: Viewport screenshots are permitted only through a separate, default-off Allow ViewportScreenshot grant capability. It is limited to the granted tab’s already-active visible viewport; it never focuses, scrolls, persists images, or grants full-page capture. Its normal origin pin, session expiry, revocation, call-time validation, and audit all apply.
2026-08-02: Focus is the Chrome extension and its communication with a backend system only. The knowledge-gathering/RAG side of the reference system chrome-tracker is explicitly out of scope.
The extension is purpose-built for interactive tab control — no tracking/knowledge-base machinery bundled in.

Read the full file on GitHub · 63 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.

1mo ago Changed · +7 lines · +151 tokens per session 5cc224abab5e
2mo ago First seen · 56 lines · 1,006 tokens per session scan A 17d7dc8fe081

Subscribe to this mod's changes

chrome-tab-remote AGENTS.md is an instructions file published in the GitHub repository ai-4-you/chrome-tab-remote (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,157 tokens to every session, about $0.0046 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 2026-08-31.

Browser automation ai-agents browser-automation chrome-extension mcp model-context-protocol

chrome-tab-remote AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
chrome-tab-remote AGENTS.mdai-4-you/chrome-tab-remote	Instructions file	1	1mo ago	MIT	A	1,157	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

chrome-tab-remote: Instructions file for Codex