Borrowing it
Nothing to install: this file belongs to hkd987/remix-browser. 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/hkd987/remix-browser/main/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/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/hkd987/remix-browser/claude-md"><img src="https://agentmods.dev/badge/instructions/hkd987/remix-browser/claude-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 | $0.00409 | $0.00409 |
| Opus 5.5 | $0.00164 | $0.00164 |
| Sonnet 5.5 | $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 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.
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.
- 2mo 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 8mo ago), licensed MIT. It adds 409 tokens to every session, about $0.0016 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.
remix-browser CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| remix-browser CLAUDE.mdhkd987/remix-browser | Instructions file | 6 | 8mo ago | MIT | A | 409 | Claude Code |
| 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 | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 279k | yesterday | MIT | A | 4,325 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,086 | GitHub Copilot |