Borrowing it
Nothing to install: this file belongs to ndthanhdev/mcp-browser-kit. 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/ndthanhdev/mcp-browser-kit/main/AGENTS.mdgit clone --depth 1 https://github.com/ndthanhdev/mcp-browser-kitWrote 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/ndthanhdev/mcp-browser-kit/agents-md)<a href="https://agentmods.dev/instructions/ndthanhdev/mcp-browser-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/ndthanhdev/mcp-browser-kit/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/ndthanhdev/mcp-browser-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/ndthanhdev/mcp-browser-kit/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 | $0.00430 | $0.00430 |
| Opus 5.5 | $0.00172 | $0.00172 |
| Sonnet 5.5 | $0.00086 | $0.00086 |
| Haiku 4.5 | $0.00043 | $0.00043 |
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 2mo 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.
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,
targetES2024), 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
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.
- 2mo ago First seen · 51 lines · 430 tokens per session scan A f032834fab6a
mcp-browser-kit AGENTS.md is an instructions file published in the GitHub repository ndthanhdev/mcp-browser-kit (55 stars, last pushed 6d ago), licensed MIT. It adds 430 tokens to every session, about $0.0017 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.
mcp-browser-kit AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-browser-kit AGENTS.mdndthanhdev/mcp-browser-kit | Instructions file | 55 | 6d ago | MIT | A | 430 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |