agentmods.dev

mcp-browser-kit AGENTS.md

Project instructions for MCP Browser Kit, a TypeScript tool that lets an AI assistant observe and control local web browsers through an extension. It describes the project's technologies, commands, checks, and tests.

In plain words
What is it for?
Use it when changing this browser-control project, including building its server or extension, running checks, and running Playwright browser tests.
Why use it?
It gives coding agents the correct commands and project rules, such as using Yarn and Biome instead of other package or formatting tools.

Instructions file for CodexOpenCode

54 7d ago A scan 430 tokens original MIT
View the source file ndthanhdev/mcp-browser-kit
Install

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.

agentmods
npx agentmods add instructions/ndthanhdev/mcp-browser-kit/agents-md
Clone the repo
git clone --depth 1 https://github.com/ndthanhdev/mcp-browser-kit

Made for: Codex, OpenCode.

Per session 430 This file is loaded in full into every session.
When invoked 430 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00430 $0.00430
Opus 5 $0.00215 $0.00215
Sonnet 5 $0.00086 $0.00086
Haiku 4.5 $0.00043 $0.00043

Measured 2d ago against content hash f032834fab6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-browser-kit 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 2d 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.

AGENTS.md · 51 lines

What it actually says

AGENTS.md

MCP Browser Kit: an MCP server that lets AI assistants observe and control local browsers through a companion browser extension.

Tech stack

  • Language: TypeScript (ESM, target ES2024), strict project references
  • Runtime: Node ^26
  • Package manager: Yarn 4.17.1 (Yarn Berry workspaces) — never use npm or pnpm
  • Monorepo orchestrator: moon (moon run, moon check)
  • Toolchain version manager: proto (.prototools)
  • Lint/format: Biome (not ESLint/Prettier)
  • Dependency consistency: syncpack
  • Bundler: tsup; type emit: tsc --build
  • Tests: Playwright (extension E2E in apps/ext-e2e)
  • DI: InversifyJS + reflect-metadata

Commands

Run from the workspace root.

# Install
yarn install

# Full check across all projects (build + biome + syncpack) — mirrors CI
moon check --all

# Lint / format (Biome)
moon run scripts:biome-check        # check only

# Dependency consistency
moon run scripts:syncpack-lint
moon run scripts:syncpack-fix

# Build a project (e.g. server or an extension)
moon run server:build
moon run m3:build

# E2E tests (Playwright)
moon run ext-e2e:test

# MCP inspector against the built server
moon run server:mcp-inspector

CI runs via two workflows: .github/workflows/pr-updated.yml (PRs, moon ci) and .github/workflows/workspace-updated.yml (push to main/release/*, moon check --all). Both build via Dagger then run sharded e2e tests. Make them pass before considering work done.

Constraints

Changes

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.

  1. 2d ago First seen · 51 lines · 430 tokens per session scan A f032834fab6a

Subscribe to this mod's changes

mcp-browser-kit AGENTS.md is an instructions file published in the GitHub repository ndthanhdev/mcp-browser-kit (54 stars, last pushed 7d ago), licensed MIT. It adds 430 tokens to every session, about $0.0022 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 2026-08-30.

Browser automationCode reviewTesting
Related

Other instructions, from other repositories

Browser4 CLAUDE.md

Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.

platonai/Browser4 · 1,205 tokens

spring-ai-agentcore AGENTS.md

Instructions for spring-ai-community/spring-ai-agentcore, covering agents.md, project overview, architecture, key components and artifact store classes.

spring-ai-community/spring-ai-agentcore · 1,370 tokens

flyto-core CLAUDE.md

Instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.

flytohub/flyto-core · 367 tokens

metamask-extension AGENTS.md

AGENTS.md instructions for MetaMask/metamask-extension, covering agents.md, agent instructions summary, critical rules for agents, comprehensive guidelines location and quick setup.

MetaMask/metamask-extension · 14,674 tokens

deckforge AGENTS.md

Instructions for tph-kds/deckforge, covering deckforge agent entry point, code intelligence, read order, default routing and non-negotiable implementation rules.

tph-kds/deckforge · 498 tokens

fast-browser CLAUDE.md

Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.

m4ttstack/fast-browser · 1,446 tokens