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/adityasasidhar/browsercontrol/agents-mdgit clone --depth 1 https://github.com/adityasasidhar/browsercontrolWrote 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/adityasasidhar/browsercontrol/agents-md)<a href="https://agentmods.dev/instructions/adityasasidhar/browsercontrol/agents-md"><img src="https://agentmods.dev/badge/instructions/adityasasidhar/browsercontrol/agents-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 | $0.00772 | $0.00772 |
| Opus 5 | $0.00386 | $0.00386 |
| Sonnet 5 | $0.00154 | $0.00154 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
browsercontrol 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 3d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
browsercontrol/contains the Python package.server.pycomposes the FastMCP server and registers tool groups;browser.pyowns the Playwright browser lifecycle and Set-of-Marks state;config.pyreads environment configuration.browsercontrol/tools/groups MCP tools by capability (navigation.py,interaction.py,forms.py,content.py,devtools.py,recording.py, andtabs.py).tests/contains pytest tests and shared mocked Playwright fixtures inconftest.py; keep module tests in matchingtest_<module>.pyfiles.docs/is the MkDocs Material documentation site; images and other static assets live inassets/anddocs/assets/.
Build, Test, and Development Commands
Use Python 3.11+ and uv for all project commands:
uv sync
uv run playwright install chromium
uv run fastmcp dev browsercontrol/server.py
uv run pytest tests/test_navigation.py
uv run pytest
uv run mkdocs build --strict
The focused pytest command is useful while iterating; the full suite uses mocks and normally does not launch Chromium. Run the development server through FastMCP's inspector UI.
Coding Style & Naming Conventions
Use four-space Python indentation, double quotes, and a 100-character Ruff target. Prefer explicit type annotations: mypy runs in strict mode. Name modules and functions in snake_case, classes in PascalCase, and tests test_<behavior>. Keep tool docstrings actionable because FastMCP exposes them to clients.
Before submitting code, run:
uv run pre-commit run --all-files
uv run ruff check .
uv run ruff format --check .
uv run mypy browsercontrol/
uv run bandit -c pyproject.toml -r . --exclude ./tests,./.venv
Testing & Tool Changes
Cover both success and graceful-error paths. Tool tests should register against a throwaway FastMCP instance and patch the tool module's imported browser. New browser-changing tools should call await browser.ensure_started() and return a fresh annotated screenshot with an element summary. Element IDs are valid only for the latest screenshot.
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.
- 3d ago First seen · 52 lines · 772 tokens per session scan A 5080ee79a5e6
browsercontrol AGENTS.md is an instructions file published in the GitHub repository adityasasidhar/browsercontrol (10 stars, last pushed 29d ago), licensed MIT. It adds 772 tokens to every session, about $0.0039 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
browser-agent AGENTS.md
Instructions for uiuing/browser-agent, covering agents.md — guide for ai coding agents, setup & commands, tests — run these before claiming done, repository layout and architecture invariants (do not break these).
qa-use CLAUDE.md
Instructions for desplega-ai/qa-use, covering claude.md, project map and tech stack.
claude-browser-test-skills CLAUDE.md
Instructions for Autodesk/claude-browser-test-skills, covering claude.md, what this repo is, layout, conventions when editing skills and validate before publishing.
periscope-mcp CLAUDE.md
Claude Code instructions for segentic-lab/periscope-mcp, covering periscope-mcp - project guide, what this is, how to run, key files and adding a new mcp tool.
obscura AGENTS.md
Instructions for h4ckf0r0day/obscura, covering agents.md, build, rendering and stealth, no rendering, with rustls or stealth and test.
stealth-browser-mcp AGENTS.md
Instructions for vibheksoni/stealth-browser-mcp, covering agent instructions, start here, recommended proxy services, environment and validation.