Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/hkd987/remix-browser/claude-mdgit clone --depth 1 https://github.com/hkd987/remix-browserWrote 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/hkd987/remix-browser/claude-md)<a href="https://agentmods.dev/instructions/hkd987/remix-browser/claude-md"><img src="https://agentmods.dev/badge/instructions/hkd987/remix-browser/claude-md.svg" alt="Measured on agentmods" 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 | $0.00409 | $0.00409 |
| Opus 5 | $0.00204 | $0.00204 |
| Sonnet 5 | $0.00082 | $0.00082 |
| Haiku 4.5 | $0.00041 | $0.00041 |
Grade A, and why
remix-browser CLAUDE.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 5d 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.
What it actually says
Project overview
We are building a better chrome mcp cdp connection and remix-browser is that tool
Web Searches
- Never include the date or year in your web searches, its weird and doesn't help
When planning
- You look first at documentation from the source
- When looking at documentation you will get 3-5 sources only. That should be plenty, if you need to lookup more docs ask
Work as a team
When asked to do work always spin up multiple agents and work as a team to get the job done as fast as possible. High quality code written fast as a team is the goal here. Working together and sharing when needed.
Code Quality
- Always unit test code that we write ALWAYS.
- Always ensure the code is linted and or type checked
- Always ensure the project builds
- Always ensure the code is DRY
When Planning or testing
- Always see how you can validate a change you have made to ensure its correct
- Examples
- When asked to optimize code or make code faster, always have a performance benchmark you can run before and after
- When asked to write a new feature, or extend code write supporting unit test if needed first then add the new feature then add more unit test as needed
- Examples
- If you are unsure about an ask, always use the AskUserQuestion tool and get the answers your need
Browser Automation
When the user asks to use Chrome, use the browser, browse a website, open a URL,
take a screenshot, test a web app, fill forms, scrape content, debug a UI, inspect
the DOM, run JavaScript in the browser, or do anything browser-related — use the
remix-browser MCP tools (mcp__remix-browser__*). Always start with navigate.
When running a build
- Always update the local version on the users machine
~/.local/bin/remix-browseras well when working on new features.
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.
- 5d ago First seen · 35 lines · 409 tokens per session scan A 23cd36625762
remix-browser CLAUDE.md is an instructions file published in the GitHub repository hkd987/remix-browser (6 stars, last pushed 5mo ago), licensed MIT. It adds 409 tokens to every session, about $0.0020 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 2026-08-31.
Other instructions, from other repositories
Browser4 CLAUDE.md
Claude Code instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
cc-websearch CLAUDE.md
Claude Code instructions for Djarvur/cc-websearch, covering project, constraints, technology stack, what not to add and conventions.
fix-quera AGENTS.md
Instructions for AlirezaKeshavarz83/fix-quera, covering agent guidance, project shape, visual style, quera page data findings and compatibility findings.
sniff AGENTS.md
AGENTS.md instructions for Aboudjem/sniff, covering agents.md: sniff, what this repo is, how an agent should use sniff, handling the playwright setup gate and finding output schema.
fast-browser CLAUDE.md
Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.
sendblue-browser-use AGENTS.md
Instructions for sendblue-api/sendblue-browser-use, covering agents.md — sendblue-browser-use, what this repo is, setup, common commands and health (no auth).