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 ohad6k/VibeRaven --skill go-livegit clone --depth 1 https://github.com/ohad6k/VibeRavenWrote 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/ohad6k/viberaven/go-live)<a href="https://agentmods.dev/skills/ohad6k/viberaven/go-live"><img src="https://agentmods.dev/badge/skills/ohad6k/viberaven/go-live/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/ohad6k/viberaven/go-live"><img src="https://agentmods.dev/badge/skills/ohad6k/viberaven/go-live.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 | $0.00043 | $0.01460 |
| Opus 5 | $0.00022 | $0.00730 |
| Sonnet 5 | $0.00009 | $0.00292 |
| Haiku 4.5 | $0.00004 | $0.00146 |
Grade A, and why
go-live 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 9d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Go Live
Use this skill when the user has a local app and asks to put it online, connect it to GitHub, deploy it to Vercel, or make a shareable live URL.
The goal is not a checklist. The goal is a working path from local project to GitHub repo to Vercel production URL, with clear proof of what actually happened. Do every safe step for the user instead of describing it, and stop only for authentication, secrets, destructive git risk, billing, or ambiguous project ownership.
Autopilot Contract
Default to action:
- Run the local inspection commands yourself.
- Run install/build/test commands yourself when they are normal project commands.
- Use authenticated GitHub and Vercel CLIs or MCP tools when available.
- Open official GitHub/Vercel pages when the next step needs user login, repo creation confirmation, project import, env var entry, domain setup, or dashboard proof.
- Continue after the user completes auth or dashboard steps, then verify the live result.
Useful official pages:
- GitHub login: https://github.com/login
- New GitHub repo: https://github.com/new
- GitHub CLI auth docs: https://cli.github.com/manual/gh_auth_login
- Vercel login: https://vercel.com/login
- New Vercel project/import: https://vercel.com/new
- Vercel dashboard: https://vercel.com/dashboard
First Pass
- Inspect repo state before changing anything:
git status --shortgit remote -vgit branch --show-current- package manager and build scripts from
package.json - deployment hints:
vercel.json,.vercel/project.json, framework config, env examples, README deploy notes.
- Identify whether GitHub and Vercel CLIs or MCP tools are available:
gh --versiongh auth statusvercel --versionornpx vercel --versionvercel whoamiornpx vercel whoamiDo not require them if browser/dashboard steps are the only available path.
- If VibeRaven is available, open the Studio with
npx -y viberavenand use Vercel/GitHub provider context, release diff, and access-mode control before running irreversible commands. - Never ask for passwords, cookies, tokens, API keys, or secret values. Ask the user to authenticate through official CLIs or provider dashboards.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 106 lines · 43 tokens per session scan A cf02a5f47091
go-live is a skill published in the GitHub repository ohad6k/VibeRaven (38 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 1,460 once invoked, about $0.0002 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 skills, from other repositories
rollback-state-validation
Validate that the cluster and GitOps repo return to a consistent state after rollback. Use when validating GitOps commit history, cluster state, or checking no drift.
cluster-state-validation
Validate that the cluster matches the desired GitOps state. Use when exporting cluster state, normalizing manifests, or comparing with GitOps repo.
prevu-flows
Use when the user wants to mirror their local dev to a Prevu environment so they can preview changes from their phone while AFK, or when they want to share an in-progress branch as a public preview URL for a teammate, designer, or PM. Mentions: AFK, mobile preview, phone preview, mirror dev, share preview, preview…
land-and-deploy
Land and deploy workflow. (gstack).
cost-optimization
Optimize cloud costs across AWS, Azure, GCP, and OCI through resource rightsizing, tagging strategies, reserved instances, and spending analysis. Use when reducing cloud expenses, analyzing infrastructure costs, or implementing cost governance policies.
istio-traffic-management
Configure Istio traffic management including routing, load balancing, circuit breakers, and canary deployments. Use when implementing service mesh traffic policies, progressive delivery, or resilience patterns.