Borrowing it
Nothing to install: this file belongs to dsouza-anush/browser-use-heroku. 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/dsouza-anush/browser-use-heroku/main/CLAUDE.mdgit clone --depth 1 https://github.com/dsouza-anush/browser-use-herokuWrote 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/dsouza-anush/browser-use-heroku/claude-md)<a href="https://agentmods.dev/instructions/dsouza-anush/browser-use-heroku/claude-md"><img src="https://agentmods.dev/badge/instructions/dsouza-anush/browser-use-heroku/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/dsouza-anush/browser-use-heroku/claude-md"><img src="https://agentmods.dev/badge/instructions/dsouza-anush/browser-use-heroku/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 | $0.01453 | $0.01453 |
| Opus 5 | $0.00727 | $0.00727 |
| Sonnet 5 | $0.00291 | $0.00291 |
| Haiku 4.5 | $0.00145 | $0.00145 |
Grade A, and why
browser-use-heroku 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 9d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser-Use is an async python >= 3.11 library that implements AI browser driver abilities using LLMs + playwright. We want our library APIs to be ergonomic, intuitive, and hard to get wrong.
Code Style
- Use async python
- Use tabs for indentation in all python code, not spaces
- Use the modern python >3.12 typing style, e.g. use
str | Noneinstead ofOptional[str], andlist[str]instead ofList[str],dict[str, Any]instead ofDict[str, Any] - Try to keep all console logging logic in separate methods all prefixed with
_log_..., e.g.def _log_pretty_path(path: Path) -> strso as not to clutter up the main logic. - Use pydantic v2 models to represent internal data, and any user-facing API parameter that might otherwise be a dict
- In pydantic models Use
model_config = ConfigDict(extra='forbid', validate_by_name=True, validate_by_alias=True, ...)etc. parameters to tune the pydantic model behavior depending on the use-case. UseAnnotated[..., AfterValidator(...)]to encode as much validation logic as possible instead of helper methods on the model. - We keep the main code for each sub-component in a
service.pyfile usually, and we keep most pydantic models inviews.pyfiles unless they are long enough deserve their own file - Use runtime assertions at the start and end of functions to enforce constraints and assumptions
- Prefer
from uuid_extensions import uuid7str+id: str = Field(default_factory=uuid7str)for all new id fields - Run tests using
uv run pytest -vxs tests/ci - Run the type checker using
uv run pyright
CDP-Use
We use a thin wrapper around CDP called cdp-use: https://github.com/browser-use/cdp-use. cdp-use only provides shallow typed interfaces for the websocket calls, all CDP client and session management + other CDP helpers still live in browser_use/browser/session.py.
- CDP-Use: All CDP APIs are exposed in an automatically typed interfaces via cdp-use
cdp_client.send.DomainHere.methodNameHere(params=...)like so:cdp_client.send.DOMSnapshot.enable(session_id=session_id)cdp_client.send.Target.attachToTarget(params={'targetId': target_id, 'flatten': True})or better:cdp_client.send.Target.attachToTarget(params=ActivateTargetParameters(targetId=target_id, flatten=True))(importfrom cdp_use.cdp.target import ActivateTargetParameters)cdp_client.register.Browser.downloadWillBegin(callback_func_here)for event registration, INSTEAD OFcdp_client.on(...)which does not exist!
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.
- 9d ago First seen · 70 lines · 1,453 tokens per session scan A ec65d6cc239d
browser-use-heroku CLAUDE.md is an instructions file published in the GitHub repository dsouza-anush/browser-use-heroku (1 stars, last pushed 1y ago), licensed MIT. It adds 1,453 tokens to every session, about $0.0073 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
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.