Borrowing it
Nothing to install: this file belongs to PremierStudio/BrowserEngine. 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/PremierStudio/BrowserEngine/master/AGENTS.mdgit clone --depth 1 https://github.com/PremierStudio/BrowserEngineWrote 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/premierstudio/browserengine/agents-md)<a href="https://agentmods.dev/instructions/premierstudio/browserengine/agents-md"><img src="https://agentmods.dev/badge/instructions/premierstudio/browserengine/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 5.1 | $0.00756 | $0.00756 |
| Opus 5 | $0.00378 | $0.00378 |
| Sonnet 5 | $0.00151 | $0.00151 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
BrowserEngine 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 6d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BrowserEngine — agent rules
These rules are binding for every agent working in this repository. They supersede generic habits; when in doubt, follow the letter here.
TypeScript only — no JavaScript anywhere
- Only TypeScript (
.ts) is allowed in this repo. No.js,.mjs, or.cjssource, config, script, or build files. Zero exceptions. - This applies to project configuration too:
eslint.config.ts,stryker.config.ts,vitest.config.ts, andtsconfig*.json. Never reach for.mjs/.js/.cjsvariants "because tools expect them" — the pinned tooling versions here load TypeScript configs natively. - Scripts (anything in
scripts/, plus anything run asnode ...frompackage.json) must be TypeScript, compiled via a dedicated emit build (tsconfig.scripts.json→dist-scripts/) when they need to run as plain Node. Do not write JS helper scripts, prebuild steps, or commit hooks in JavaScript. - The CI gate chain (
npm run ci) enforces this withgit diff --exit-codeafter formatting and with knip/lint — a.js/.mjs/.cjsfile anywhere in the tree (outside the auto-generated and gitignoreddist-scripts/,coverage/,reports/) will fail the gates. - If a tool or upstream example suggests a
.mjs/.jsfile, translate it to TypeScript. Escaping to JavaScript to work around a tooling quirk is not allowed; fix the tooling (pin a version, add a typed wrapper) instead. astype assertions,any,!non-null assertions, and@ts-ignore/@ts-nocheck/@ts-expect-error/@ts-checkare banned byeslint.config.ts— keep the code assertion-free and checkable.
Engineering rules (binding)
- Follow
docs/mvp.mdanddocs/decisions.md; where they conflict,docs/decisions.mdwins. Do not relitigate settled decisions. - Strict TDD: write the failing test first (RED), confirm it fails for the right reason, then implement (GREEN), then refactor. No product code before its test exists. No batching "write code then test."
- Every module must reach 100% coverage and a 100% mutation score from
Stryker, with
typecheck/lint/format/knipclean before it may be committed. The only escape from the mutation gate is a pre-approved entry inmutation-survivors.json, enforced byscripts/survivors.ts— never silence a survivor silently. - Tests must be truthy and mutation-killing, assert real behavior (not mock self-fulfillment), and inject clocks/timers — no sleeps, no flaky timing.
- Use subagents for parallelizable, well-scoped work (per milestone), but the orchestrator enforces the gates on every merge; a subagent may not merge anything that isn't red→green, mutation-clean, and tooling-clean.
- Keep the repo free of dead code, unused exports, and unused dependencies (knip, zero findings).
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.
- 6d ago First seen · 49 lines · 756 tokens per session scan A edd19b455fd7
BrowserEngine AGENTS.md is an instructions file published in the GitHub repository PremierStudio/BrowserEngine (0 stars, last pushed 24d ago), licensed Apache-2.0. It adds 756 tokens to every session, about $0.0038 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 2026-08-31.
Other instructions, from other repositories
CopilotTraining typescript.instructions.md
Instructions for MSBart2/CopilotTraining, covering typescript development standards, type definitions, type safety, generics and union types.
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.
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 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).
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.