agentmods.dev

chromux: Instructions file for Codex

AGENTS.md

chromux AGENTS.md is an instructions file for Codex, OpenCode from modakbul-gongbang/chromux. It costs 1,420 tokens per session, scanned A, original, MIT.

Project instructions for chromux, a zero-dependency Node.js command-line tool that controls real Google Chrome browser profiles.

In plain words
What is it for?
Use them when developing chromux commands, raw Chrome DevTools Protocol actions, browser workflows, response messages, or built-in helper snippets.
Why use it?
They give coding agents consistent rules for changing the tool, keeping its commands small, and checking that browser actions work.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is modakbul-gongbang/chromux's own configuration. It tells Codex and OpenCode how to work on chromux itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything chromux configures →

not rated 40repo 2mo ago A scan 1,420 tokens original MIT
View source ↗ modakbul-gongbang/chromux
Reuse

Borrowing it

Nothing to install: this file belongs to modakbul-gongbang/chromux. 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/modakbul-gongbang/chromux/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/modakbul-gongbang/chromux

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.

agentmods badge for chromux AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/modakbul-gongbang/chromux/agents-md/github.svg)](https://agentmods.dev/instructions/modakbul-gongbang/chromux/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/modakbul-gongbang/chromux/agents-md"><img src="https://agentmods.dev/badge/instructions/modakbul-gongbang/chromux/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.

agentmods 80×15 button for chromux AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/modakbul-gongbang/chromux/agents-md"><img src="https://agentmods.dev/badge/instructions/modakbul-gongbang/chromux/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,420 This file is loaded in full into every session.
When invoked 1,420 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01420 $0.01420
Opus 5.5 $0.00568 $0.00568
Sonnet 5.5 $0.00284 $0.00284
Haiku 4.5 $0.00142 $0.00142

Measured 2mo ago against content hash b0bdb5c3db31, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

chromux 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 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.

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 · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

chromux agent guide

chromux is a zero-dependency Node.js CLI for controlling real Google Chrome profiles through raw CDP. Keep the public command surface small and let chromux help be the source of truth for current CLI syntax.

Working Rules

  • Use Node.js >= 22 and avoid adding runtime dependencies unless the tradeoff is explicit and necessary.
  • Prefer existing raw-CDP and daemon/profile patterns in chromux.mjs over new abstraction layers.
  • New browser actions should usually be expressed through run or cdp before adding another top-level verb.
  • Compatibility aliases may remain quiet, but do not expose deprecated aliases in the main help surface.
  • Keep agent-facing instructions under skills/: skills/chromux/ for CLI usage and skills/chromux-work/ for browser-work orchestration. Keep installation/runtime setup in install.md.
  • Keep repo-local helper runner material under snippets/_builtin/.
  • Command responses are an agent-facing product surface, not just data: open returns interactive/next/hints/scripts/replay, actions return a next verification hint, failed runs append repair hints. When changing response fields or workflow guidance, keep the responses, chromux help, README.md, and both skills telling the same story — and extend benchmarks/chromux-doc-check.mjs needles so drift fails validation.
  • Durable per-host agent knowledge has two write surfaces: site notes (chromux note, ~/.chromux/skills/<host>/) for facts, and replay scripts (chromux script, ~/.chromux/scripts/<host>/) for proven flows. Features that touch host knowledge should surface through both open responses and the skills.
  • Observation payload size is a first-class metric (agents pay per byte read). Changes to snapshot, open, or response shapes should be checked with benchmarks/chromux-token-benchmark.mjs, and the README Token Footprint table refreshed when numbers move materially.

High-Risk Change Scope

Read the full file on GitHub · 123 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. 2mo ago First seen · 123 lines · 1,420 tokens per session scan A b0bdb5c3db31

Subscribe to this mod's changes

chromux AGENTS.md is an instructions file published in the GitHub repository modakbul-gongbang/chromux (40 stars, last pushed 2mo ago), licensed MIT. It adds 1,420 tokens to every session, about $0.0057 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
Related

chromux AGENTS.md compared with instructions from other repositories

chromux AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
chromux AGENTS.mdmodakbul-gongbang/chromuxInstructions file402mo agoMITA1,420Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode