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/vibiumdev/vibium/claude-mdgit clone --depth 1 https://github.com/VibiumDev/vibiumWhat 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 | $0.00304 | $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
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 3d 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
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"
- When adding new command line options to the vibium binary, add a simple example and sample output (or short description)
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.
- 3d 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 (2,926 stars, last pushed yesterday), licensed Apache-2.0. 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
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
agentic-playwright selectors.instructions.md
Instructions for idavidov13/agentic-playwright, covering selector strategy, critical, instructions, phase 1: open and authenticate and phase 2: explore like a user.
scrapai-cli CLAUDE.md
Instructions for discourselab/scrapai-cli, covering claude.md, 1. who you are, 2. hard rules, 3. tools and 4. before you start: confirm the project.
chromeboost CLAUDE.md
Instructions for lordamdal/chromeboost, covering chromeboost — repo-developer guide, what chromeboost is, repository layout, development commands and tests/antibot/ (run locally; not in ci).
skills CLAUDE.md
Instructions for aemcoder/skills, covering claude.md, repository structure, slicc browser automation conventions, stateless tab targeting (since slicc pr #188) and tab-new returns a targetid.
xgrower-extension CLAUDE.md
Instructions for JoyyyceD/xgrower-extension, covering x grower extension — architecture notes, architecture, key files, auth flow and quota system.