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.
curl -O https://raw.githubusercontent.com/modakbul-gongbang/chromux/main/AGENTS.mdgit clone --depth 1 https://github.com/modakbul-gongbang/chromuxWrote 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.
[](https://agentmods.dev/instructions/modakbul-gongbang/chromux/agents-md)<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.
<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>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 | $0.01420 | $0.01420 |
| Opus 5 | $0.00710 | $0.00710 |
| Sonnet 5 | $0.00284 | $0.00284 |
| Haiku 4.5 | $0.00142 | $0.00142 |
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 10d 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.
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.mjsover new abstraction layers. - New browser actions should usually be expressed through
runorcdpbefore 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 andskills/chromux-work/for browser-work orchestration. Keep installation/runtime setup ininstall.md. - Keep repo-local helper runner material under
snippets/_builtin/. - Command responses are an agent-facing product surface, not just data:
openreturnsinteractive/next/hints/scripts/replay, actions return anextverification 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 extendbenchmarks/chromux-doc-check.mjsneedles 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 bothopenresponses 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 withbenchmarks/chromux-token-benchmark.mjs, and the README Token Footprint table refreshed when numbers move materially.
High-Risk Change Scope
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.
- 10d ago First seen · 123 lines · 1,420 tokens per session scan A b0bdb5c3db31
chromux AGENTS.md is an instructions file published in the GitHub repository modakbul-gongbang/chromux (40 stars, last pushed 15d ago), licensed MIT. It adds 1,420 tokens to every session, about $0.0071 per session on Opus 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.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.