Borrowing it
Nothing to install: this file belongs to LvcidPsyche/auto-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/LvcidPsyche/auto-browser/main/AGENTS.mdgit clone --depth 1 https://github.com/LvcidPsyche/auto-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/lvcidpsyche/auto-browser/agents-md)<a href="https://agentmods.dev/instructions/lvcidpsyche/auto-browser/agents-md"><img src="https://agentmods.dev/badge/instructions/lvcidpsyche/auto-browser/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/lvcidpsyche/auto-browser/agents-md"><img src="https://agentmods.dev/badge/instructions/lvcidpsyche/auto-browser/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 | $0.00513 | $0.00513 |
| Opus 5.5 | $0.00205 | $0.00205 |
| Sonnet 5.5 | $0.00103 | $0.00103 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
auto-browser 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 14d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — auto-browser
For coding agents working in this repo. Humans: start with README.md and CONTRIBUTING.md.
Commands
make help # every target
make lint # ruff across the repo (config: ruff.toml)
make test-local # controller suite on the host (Python 3.11+ with ./controller[dev])
make test # same suite in Docker
make release-audit # launch-prep audit; run before any release PR
- Use a virtualenv for the host suite (
python -m pip install -e ./controller[dev]) and pointAUTO_BROWSER_PYTHON_BINat it if several interpreters exist. The controller's FastAPI floor conflicts with other projects' pins, so don't share a global interpreter. make test-localruns fromcontroller/on purpose: pydantic-settings reads.envfrom the working directory, and a developer's root.envturns on auth the tests don't send (~138 false 400s). If you invoke the tests yourself, run them fromcontroller/too.- Test-suite defaults belong in
controller/tests/__init__.py, notconftest.py: the controller image shipstests/__init__.py, so a conftest-only default passes on the host and fails in Docker.
Invariants CI enforces
- Version parity: every version string in the repo must match (
scripts/check_version_parity.pylists them). A release bumps all of them together withpython scripts/bump_version.py X.Y.Z. - Playwright pin parity: the controller (pip) and
browser-node(npm) Playwright versions must be identical (scripts/check_playwright_pins.py). - Security-sensitive changes (auth, isolation, witness receipts, PII scrubbing) follow
SECURITY.md.
Releases
A v* tag runs .github/workflows/release.yml, which publishes only three packages: client/,
integrations/langchain/ and packaging/auto-browser-mcp/. Cut a release only when
git diff <last-tag>..main -- client/ integrations/langchain/ packaging/auto-browser-mcp/ is
non-empty. main is protected: changes land through a PR with green CI, one merge at a time.
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.
- 14d ago Changed · +11 tokens per session ef2810097533
- 20d ago First seen · 39 lines · 502 tokens per session scan A 215ea951d113
auto-browser AGENTS.md is an instructions file published in the GitHub repository LvcidPsyche/auto-browser (905 stars, last pushed 3d ago), licensed MIT. It adds 513 tokens to every session, about $0.0021 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 2026-09-26.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).