terminal-browser is a web browser that runs inside a terminal window, allowing pages to be viewed and controlled alongside command-line work. It is intended for developers and coding agents that need web access in the same terminal session, including when working over SSH. The catalogue add-ons help agents interact with the browser and use it as part of their workflow.
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/zenbu-labs/terminal-browser/agents-mdgit clone --depth 1 https://github.com/zenbu-labs/terminal-browserWrote 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/zenbu-labs/terminal-browser/agents-md)<a href="https://agentmods.dev/instructions/zenbu-labs/terminal-browser/agents-md"><img src="https://agentmods.dev/badge/instructions/zenbu-labs/terminal-browser/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 | $0.00304 | $0.00304 |
| Opus 5 | $0.00152 | $0.00152 |
| Sonnet 5 | $0.00061 | $0.00061 |
| Haiku 4.5 | $0.00030 | $0.00030 |
Grade A, and why
terminal-browser 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.
What it actually says
- Do not proactively write comments in code. We prefer code to be self explanatory. When we write comments its because there is something locally unintuitive that a future reader should know. But as we write code our goal is to make all code locally intuitive, removing the need for comments. If we ever do need to write comments, we never introduce jargon. Comments should be understandable to someone who was just dropped into the codebase for the first time. Comments should attempt to be concise, on average 1-2 lines. If you are writing a longer comment its likely there is a lot of useless information, which is bad because the information may become stale as the code changes
- Do not leave random markdown files in the codebase that are meant to be some way to deliver information to me. If you want to write a markdown file write it in a temporary file, and give me the path and chat and I can read it
- Never write code that is explicitly backwards compatible. Systems should handle backwards compatibility (like migrations), not logic. If there is some logic that needs to be written otherwise it would appear it would break older users, you MUST make the assumption that no users have ran that code yet and its unreleased, so it would not make sense to consider the side effects that code would produce. This is a safe assumption because the maintainers of this codebase always ensure code that gets shipped is compatbile with the systems that allow for us to not have to explicitly hardcode backwards compatibility
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 · 5 lines · 304 tokens per session scan A 8e9d6d9d86b1
terminal-browser AGENTS.md is an instructions file published in the GitHub repository zenbu-labs/terminal-browser (2,681 stars, last pushed yesterday), licensed MIT. It adds 304 tokens to every session, about $0.0015 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.
Other instructions, from other repositories
dev3000 AGENTS.md
Instructions for vercel-labs/dev3000, covering agents.md, runtime, local ui, production workflows, browser tools and development rules.
warp AGENTS.md
AGENTS.md instructions for warpdotdev/warp, covering agents.md, development commands, build and run, running with local warp-server and connect to server on default port 8080.
moli AGENTS.md
AGENTS.md instructions for lexmount/moli: Before committing changes that modify Rust source code or Rust build metadata (such as Cargo.toml, Cargo.lock, or rust-toolchain), run all of the following from the repository root and ensure they pass.
psmux AGENTS.md
AGENTS.md instructions for psmux/psmux, covering agent instructions and test isolation.
VTCode AGENTS.md
AGENTS.md instructions for vinhnx/VTCode, covering agents.md, rules, detailed guides, workspace and per-module guidance.
pisper AGENTS.md
AGENTS.md instructions for ling-kong-ran/pisper, covering agents.md, project, architecture, commands and setup.