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.
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 skills add VibiumDev/vibium --skill checkgit 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/skills/vibiumdev/vibium/check)<a href="https://agentmods.dev/skills/vibiumdev/vibium/check"><img src="https://agentmods.dev/badge/skills/vibiumdev/vibium/check/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/skills/vibiumdev/vibium/check"><img src="https://agentmods.dev/badge/skills/vibiumdev/vibium/check.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 | $0.00044 | $0.01804 |
| Opus 5.5 | $0.00018 | $0.00722 |
| Sonnet 5.5 | $0.00009 | $0.00361 |
| Haiku 4.5 | $0.00004 | $0.00180 |
Grade A, and why
check 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 2d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Check with Vibium
Use vibium check "<claim>" to hand a specific acceptance claim to a fresh
verifier context. The coding agent builds and fixes the application; Vibium's
verifier investigates the running behavior with constrained browser tools.
Your own browser inspection does not substitute for this invocation.
Setup
Use the project's configured Vibium binary. Otherwise try vibium,
./clicker/bin/vibium, then ./node_modules/.bin/vibium. Confirm
vibium check --help works. Local Chrome is the tested baseline for live checks.
For initial live setup, run vibium ready browser --json with the selected
engine/channel. It inspects browser and driver files without launching them
or touching the current browser; launch and BiDi connectivity remain untested. Follow its install/fix guidance if needed. Saved-input checks do not
require a browser; skip browser readiness for them.
For OpenAI, export VIBIUM_AI_PROVIDER=openai,
VIBIUM_AI_MODEL, and OPENAI_API_KEY.
For xAI, select xai and export XAI_API_KEY (for example --model grok-4).
For Anthropic, select anthropic and export ANTHROPIC_API_KEY; for Google,
select google and export GOOGLE_API_KEY. Set a model available to that
provider. Leave VIBIUM_AI_REASONING_EFFORT unset for Anthropic/Google.
local uses the compatible adapter, defaults to http://127.0.0.1:8080/v1,
and requires no key. Never manage or install a model runtime as part of Check.
An OpenAI-compatible service uses VIBIUM_AI_PROVIDER=openai-compatible
and VIBIUM_AI_BASE_URL. Use the project's existing configuration.
Vibium loads ~/.config/vibium/ai.env for empty AI variables; nonempty process
environment still wins. If none exists, tell the user to run vibium config init
and fill in that file — do not write credentials to it yourself. Never print or
log credentials. Do not choose another provider or model to work around a
missing configuration without the user's direction.
After loading settings, run vibium ready ai --json during initial setup or
when provider configuration changes. Exit 0 and result.ready: true mean the
configuration and provider tool round-trip passed; exit 1 includes failed
checks and fixes. It makes up to two small model requests and does not launch
or change a browser. It does not check the application or replace Check.
Resolve reported setup problems before the browser workflow; do not rerun it
before every claim when the configuration is unchanged.
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.
- 2d ago Changed · -2 tokens per session a2eefbf58924
- 3d ago Changed · +4 lines c4aa1c97138a
- 1mo ago Changed e65533527150
- 1mo ago Changed · -1 lines 76bbfc6ed8d8
- 1mo ago First seen · 136 lines · 46 tokens per session scan A 87ed47f2b116
check is a skill published in the GitHub repository VibiumDev/vibium (2,947 stars, last pushed yesterday), licensed Apache-2.0. It adds 44 tokens to every session and 1,804 once invoked, about $0.0002 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 2026-09-08.
check compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| checkVibiumDev/vibium | Skill | 2.9k | yesterday | Apache-2.0 | A | 44 | Claude Code, Codex |
| browsegarrytan/gstack | Skill | 140k | today | MIT | B | 32 | Claude Code |
| cua-driverdavidondrej/skills | Skill | 4.3k | 3d ago | MIT | A | 68 | Claude Code, Codex |
| create-verification-skillget-bb/bb | Skill | 4.9k | today | MIT | A | 57 | Claude Code, Codex |
| browser-qahashgraph-online/awesome-codex-plugins | Skill | 1.5k | yesterday | Apache-2.0 | A | 58 | Claude Code, Codex |
| webapp-testinganthropics/skills | Skill | 188k | 9d ago | none | A | 35 | Claude Code |
| test-electron-appPostHog/posthog-foss | Skill | 728 | today | MIT | A | 112 | Claude Code |