Borrowing it
Nothing to install: this file belongs to anomalyco/browser-control. 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/anomalyco/browser-control/main/AGENTS.mdgit clone --depth 1 https://github.com/anomalyco/browser-controlWrote 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/anomalyco/browser-control/agents-md)<a href="https://agentmods.dev/instructions/anomalyco/browser-control/agents-md"><img src="https://agentmods.dev/badge/instructions/anomalyco/browser-control/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/anomalyco/browser-control/agents-md"><img src="https://agentmods.dev/badge/instructions/anomalyco/browser-control/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 | $0.02031 | $0.02031 |
| Opus 5.5 | $0.00812 | $0.00812 |
| Sonnet 5.5 | $0.00406 | $0.00406 |
| Haiku 4.5 | $0.00203 | $0.00203 |
Grade A, and why
browser-control 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 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.
How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Control
Browser Control is a local browser driver for trusted agents. It controls the user's existing Chromium-family browser through a small MV3 extension shim and a local Node relay.
Private Kit Tool
Commit and push straight to main, no PRs. Merge any open PR without asking.
After pushing, update the installed copy. See ~/code/control/AGENTS.md.
Source Of Truth
- Keep
PLAN.mdupdated when architecture, scope, install flow, or product preferences change. - Keep
GLOSSARY.mdupdated when domain language changes. - Keep
skills/browser-control/SKILL.mdupdated when the agent-facing workflow, commands, setup steps, or troubleshooting behavior changes, and sync it to~/.config/opencode/skills/browser-control/skill.md. browser-control skillmust print the currentskills/browser-control/SKILL.mdtext so another agent can fetch the installed workflow instructions.
Architecture Invariants
Driver & Relay Lifecycle
- Browser Control is a driver, not an LLM agent. Prefer the code-first
execute(code)interface over adding narrow action commands. - Use Effect v4 (
4.0.1) for Node-side code, keepingeffect,@effect/platform-node, and@effect/platform-node-sharedpinned to the exact same version. Check/Users/kit/code/open-source/effectfor Effect v4 patterns. PreferEffect.fn/Effect.fnUntracedand scoped lifecycles (Effect.acquireRelease,Effect.scoped). Read runtime configuration through EffectConfig. - Relay HTTP wire shapes live in
src/relay-schema.ts(Effect Schema). The CLI, MCP server, and SDK talk to the relay only throughsrc/relay-client.ts(RelayClient.Service), usingNodeHttpClient.layerNodeHttpwithrequestTimeout = 0on the relay server so longhandoff()andsecrets runcalls never hitundici's 5-minute header timeout. - Relay-backed CLI and MCP commands auto-start a detached relay when needed.
status,doctor,skill, andsession_currentnever contact or auto-start an absent relay. - Ordinary CLI, MCP, and SDK calls never replace a running relay. Replacement
requires
browser-control relay restart, an exact managed instance, and safe shutdown protocol 2 (RelayShutdown). Record bounded attribution inlifecycle.jsonlwithout URLs, expressions, or credentials.
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 Changed · +1 tokens per session e15aa2fceb54
- 6d ago Changed · +6 lines · +105 tokens per session c624a895d5ae
- 9d ago Changed · +5 lines · +42 tokens per session 0820c1e4ad10
- 22d ago Changed · +10 lines · +164 tokens per session e68dd0aaf6d4
- 23d ago Changed · -263 lines · -3,905 tokens per session 4762f5142fef
- 1mo ago Changed · +8 lines · +134 tokens per session c79002b74a5a
- 1mo ago Changed · +10 lines · +162 tokens per session 9e0a71d40878
- 1mo ago Changed · +11 lines · +159 tokens per session e440b6c14442
- 1mo ago Changed d69bab94881b
- 1mo ago First seen · 365 lines · 5,169 tokens per session scan A 9836e87910d2
browser-control AGENTS.md is an instructions file published in the GitHub repository anomalyco/browser-control (467 stars, last pushed 4d ago), licensed MIT. It adds 2,031 tokens to every session, about $0.0081 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 2026-08-30.
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.
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).
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.