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/dgutierrez1/concurrent-playwright-mcp/agents-mdgit clone --depth 1 https://github.com/dgutierrez1/concurrent-playwright-mcpWrote 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/dgutierrez1/concurrent-playwright-mcp/agents-md)<a href="https://agentmods.dev/instructions/dgutierrez1/concurrent-playwright-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/dgutierrez1/concurrent-playwright-mcp/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 | $0.01312 | $0.01312 |
| Opus 5 | $0.00656 | $0.00656 |
| Sonnet 5 | $0.00262 | $0.00262 |
| Haiku 4.5 | $0.00131 | $0.00131 |
Grade A, and why
concurrent-playwright-mcp 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 4d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engineering conventions — concurrent-playwright-mcp
Conventions for humans and AI agents working in this repo. Keep changes consistent with this file.
Cross-cutting principles
- Clean architecture, one direction. Domain logic does not depend on transport. Here:
SessionManager/BrowserSession(domain) know nothing about MCP;server.ts(transport) is a thin delegate. Never leak transport shapes (MCPcontent) into the domain. - Parse, don't validate. Untrusted input is validated and shaped at the edge (
server.tsvia Zod, with.default()for defaults); inner layers receive complete, typed values and keep only genuine domain-state checks (a session/tab lookup miss). Useasonly to bridge external (Playwright) types, never to skip a real check. - Dependency inversion at the seams that need testing. The browser is injected as a
BrowserLauncherso the isolation logic is unit-testable with fakes. Inject only where it buys testability or swappability; do not add abstraction layers a small tool does not need. - Right-size it. SOLID and separation, yes; speculative managers/factories/interfaces, no. Heavy ceremony hurts readability and AI codegen alike.
- TDD the real logic. Write tests first for the logic that matters (session isolation, lifecycle, eviction, error paths). Do not chase coverage on thin pass-throughs to a library.
- Errors are explicit and typed. Named error classes (
SessionNotFoundError, ...), never silent failure. At the transport edge, report failures in-band (isError), never throw across the wire. - Secrets hygiene. No secrets in the repo.
.envis gitignored from commit #1. This server takes none, but the rule stands.
Stack and tooling
- Language/runtime: TypeScript (strict) on Node 20+, ESM only (
"type": "module"). - Imports: extensionless relative imports (
moduleResolution: bundler; the output is bundled by tsup). SDK subpath imports keep their published.js(.../server/mcp.js). - MCP:
@modelcontextprotocol/sdkv1.x with the high-levelMcpServer+registerTool.inputSchemais a raw Zod shape ({ a: z.string() }), notz.object({...}). Transports: stdio (default) and Streamable HTTP. A stdio server must not write to stdout (it is the JSON-RPC channel) — log to stderr. - Browser: Playwright. One shared
Browser, one isolatedBrowserContextper session. Alwaysawaitcloses; clean up onSIGINT/SIGTERM. Bound resources (session cap + idle eviction). - Build: tsup (ESM,
dts, sourcemaps). Types:tsc --noEmit. Lint: ESLint flat config (strictTypeChecked+stylisticTypeChecked) + Prettier (separate step). Tests: Vitest.
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.
- 4d ago First seen · 91 lines · 1,312 tokens per session scan A cd9fc9dfb718
concurrent-playwright-mcp AGENTS.md is an instructions file published in the GitHub repository dgutierrez1/concurrent-playwright-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,312 tokens to every session, about $0.0066 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 2026-09-01.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.