Vibium is a browser automation tool that lets coding agents navigate web pages, fill forms, click controls, and capture screenshots. It can be used through a command-line skill, an MCP server, or client libraries for JavaScript/TypeScript, Python, and Java. The catalogue add-ons give agents access to Vibium's browser verification workflows.
Borrowing it
Nothing to install: this file belongs to VibiumDev/vibium. 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/VibiumDev/vibium/main/CLAUDE.mdgit clone --depth 1 https://github.com/VibiumDev/vibiumWrote 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/vibiumdev/vibium/claude-md)<a href="https://agentmods.dev/instructions/vibiumdev/vibium/claude-md"><img src="https://agentmods.dev/badge/instructions/vibiumdev/vibium/claude-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/vibiumdev/vibium/claude-md"><img src="https://agentmods.dev/badge/instructions/vibiumdev/vibium/claude-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 | $0.00521 | $0.00521 |
| Opus 5.5 | $0.00208 | $0.00208 |
| Sonnet 5.5 | $0.00104 | $0.00104 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
vibium CLAUDE.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 8d 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.
CLAUDE.md
Browser automation for AI agents and humans.
Key Docs
- ROADMAP.md — Future features (not yet prioritized)
- docs/reference/WebDriver-Bidi-Spec.md — BiDirectional WebDriver Protocol spec
Current Goal
V1 shipped. Focus on fixing critical bugs and issues reported by users.
See open issues: https://github.com/VibiumDev/vibium/issues
Tech Stack
- Go (vibium binary)
- TypeScript (JS client)
- Python (Python client)
- WebDriver BiDi protocol
- MCP server (stdio)
Design Philosophy
Optimize for first-time user/developer joy. Defaults should create an "aha!" moment:
- Browser visible by default (see what the AI is doing)
- Screenshots save to a sensible location automatically
- Zero config needed to get started
Power users can override defaults (headless mode, custom paths, etc.) when needed.
Rules
- Client library launch code must not shell out to vibium subcommands other than
pipe—pipeensures the browser is installed itself (#312). User-facing CLI install passthroughs are the one exception. - Prioritize bug fixes over new features
- Run tests before committing:
make test - Always fix flaky tests immediately when they show up — never dismiss them as "pre-existing"
- The browser under test is a parameter, never a literal in a test. Suites read
ENGINEfrom tests/helpers.js (VIBIUM_ENGINE, threaded through the Makefile asENGINE=), and CI runs each suite once per engine job. Naming an engine inside a case in the default suite runs it in the chrome job, which installs no other browser. Adding an engine should be a new job, not a new branch in a test. - When adding new command line options to the vibium binary, add a simple example and sample output (or short description)
- A CLI command whose positional values can be negative or numeric (coordinates, offsets, durations) must be built with
lateParse(cmd/clicker/helpers.go). Never setDisableFlagParsingby hand; the flag drift test rejects it.
Writing Style
- Write short sentences.
- Use RFC 2119 keywords (MUST, SHOULD, MAY) for obligations.
- Commits MUST have an imperative subject. The body MUST carry only facts the diff cannot show.
- Comments MUST only clarify code that needs it. Comments MUST NOT narrate. Existing long comment blocks are not license to add more.
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.
- 8d ago Changed · +7 lines · +74 tokens per session c2b0fe721f1f
- 1mo ago Changed · +1 lines · +52 tokens per session 423e42933f1a
- 1mo ago Changed · +1 lines · +91 tokens per session bd3972ef11af
- 2mo ago First seen · 40 lines · 304 tokens per session scan A e2ab17fd60e4
vibium CLAUDE.md is an instructions file published in the GitHub repository VibiumDev/vibium (2,947 stars, last pushed yesterday), licensed Apache-2.0. It adds 521 tokens to every session, about $0.0021 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.
vibium CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vibium CLAUDE.mdVibiumDev/vibium | Instructions file | 2.9k | yesterday | Apache-2.0 | A | 521 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | 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 |