What is browsertap-mcp AGENTS.md?

Repository-specific instructions for Browsertap MCP, a tool system that lets an agent control browser tabs through a Chrome extension and supporting processes.

Use them when changing or debugging Browsertap MCP, especially its browser bridge, Chrome extension, tab sessions, alarms, or authenticated HTTP interface.

They document timing and process boundaries that are not obvious from the code, such as when edits take effect and why a long-running process may need restarting.

How LinVireo/browsertap-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to LinVireo/browsertap-mcp. 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/LinVireo/browsertap-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/LinVireo/browsertap-mcp

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/linvireo/browsertap-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/linvireo/browsertap-mcp/agents-md)

Your own site

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

Per session 1,167 This file is loaded in full into every session.

When invoked 1,167 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	$0.01167	$0.01167
Opus 5.5	$0.00467	$0.00467
Sonnet 5.5	$0.00233	$0.00233
Haiku 4.5	$0.00117	$0.00117

Measured 1mo ago against content hash 3d54d185b5d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

browsertap-mcp 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 · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Implementation entry point for agents changing this repository. General setup, coding checks, and release gates live in CONTRIBUTING.md (简体中文). Public tool parameters remain in the ## Tools table in README.md and README.zh-CN.md.

Read the detailed guide for the area being changed before editing that area. The guides preserve implementation constraints and the failures behind them; routine tasks do not need every guide.

1. Three processes, three different ways a change takes effect

Read runtime lifecycle before changing startup, process state, extension identity, or injected page scripts.

MCP Python changes need a fresh MCP process; bridge changes need a bridge restart; extension source changes need the browser's manual extension reload.
Use the reported action and build-stamp verdict to identify stale components. A matching version number alone does not prove matching code.
Preserve the manual-reload and self-disable guards. Page scripts are separate from extension code and keep bare entry-point references, not calls.

2. Changing a tool signature or a default touches four places

Read tool contracts before changing any public tool name, parameter, default, behavior, or packaged caller guidance.

Update the tool description, both README tool tables, and both caller Skills:

src/browsertap_mcp/skills/browsertap-default/SKILL.md
src/browsertap_mcp/skills/browsertap-bridge-recovery/SKILL.md

Run python -m scripts.check_tool_docs. Installed-copy comparison is a separate check and requires an actual mirror directory.

3. Tab ids are not stable -- never remember one

Read tabs and input before changing target resolution, reconnect handling, lifecycle generations, or tab cleanup.

Explicit targets must not silently move to another tab. An omitted dead default can be reselected according to the existing policy. Preserve ownership and generation evidence; an unreadable generation store is not an empty store. Tests use synthetic identities rather than real tab IDs.

Read the full file on GitHub · 112 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 · +12 tokens per session 3d54d185b5d9
1mo ago Changed · -445 lines · -7,001 tokens per session af379b9df65a
1mo ago Changed · +163 lines · +2,700 tokens per session c5ea695896fe
2mo ago First seen · 394 lines · 5,456 tokens per session scan A 0ae6b50d6f2c

Subscribe to this mod's changes

browsertap-mcp AGENTS.md is an instructions file published in the GitHub repository LinVireo/browsertap-mcp (0 stars, last pushed 29d ago), with no licence file. It adds 1,167 tokens to every session, about $0.0047 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.

Python browser-automation chrome-devtools-protocol chrome-extension mcp

browsertap-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
browsertap-mcp AGENTS.mdLinVireo/browsertap-mcp	Instructions file	0	29d ago	none	A	1,167	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

browsertap-mcp: Instructions file for Codex