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 initlabsai/vibekit --skill build-on-vibekitgit clone --depth 1 https://github.com/initlabsai/vibekitWrote 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/initlabsai/vibekit/build-on-vibekit)<a href="https://agentmods.dev/skills/initlabsai/vibekit/build-on-vibekit"><img src="https://agentmods.dev/badge/skills/initlabsai/vibekit/build-on-vibekit/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/initlabsai/vibekit/build-on-vibekit"><img src="https://agentmods.dev/badge/skills/initlabsai/vibekit/build-on-vibekit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 38 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00086 | $0.00970 |
| Opus 5 | $0.00043 | $0.00485 |
| Sonnet 5 | $0.00017 | $0.00194 |
| Haiku 4.5 | $0.00009 | $0.00097 |
Grade A, and why
build-on-vibekit 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 10d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build on VibeKit
VibeKit exposes one ToolDefinition contract through every host. Extend that
contract, compose tools and plugins into a deployment, then select a host. Do
not create a parallel handler or execution path.
The toolkit surface
Beyond tools and plugins, @initlabs/vibekit ships the pieces the web agent is
built from — reach for these before writing your own: @initlabs/vibekit/agent
(createAgent, createAgentHandler: a turn over HTTP as NDJSON), /actions
(the draft → approve → sign → confirm machine, createWalletSignDraft), /pay
(createPaywall: x402 → credit → charge(request)), /rest
(createRestHandler: POST /tools/<tool>), and vibekit add <component>
(copy-paste React whose props are a tool's output type). Runnable examples:
packages/vibekit/examples/{agent-http,rest,signer,stdio,http}.ts and
packages/vibekit/examples/action.ts.
Current distribution boundary
Everything ships as one package, @initlabs/vibekit, with subpath exports
(. is the core contract; ./tools, ./preset, ./mcp, ./agent,
./signer-keystore, ./plugins/<name>). Build against this monorepo using
its workspace:* dependency. Do not invent install, publish, or versioning
instructions for external consumers.
Before changing structure, read the repository AGENTS.md and
docs/CONSTITUTION.md. Ask before adding a dependency, package, app, registry, or
extension point.
Choose the guide
| Task | Guide |
|---|---|
| Select tools and plugins, configure networks or signing, and expose a custom stdio or HTTP MCP | Custom MCP deployment |
| Define tools, integrate an external service, and package them as a reusable plugin | Plugin authoring |
What ships with it
2 files 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.
- 10d ago First seen · 77 lines · 86 tokens per session scan A a880a8ccbd9f
build-on-vibekit is a skill published in the GitHub repository initlabsai/vibekit (27 stars, last pushed 7d ago), licensed MIT. It adds 86 tokens to every session and 970 once invoked, about $0.0004 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
algorand-interaction
Interact with Algorand blockchain via the Algorand MCP server — wallet operations, ALGO/ASA transactions, smart contracts, account info, NFD lookups, atomic groups, Tinyman swaps, Haystack Router best-price swaps, Alpha Arcade prediction markets, Pera asset verification, TEAL compilation, knowledge base. Use when user…
alpha-arcade-interaction
Trade on Alpha Arcade prediction markets on Algorand — browse markets, read orderbooks, place limit/market orders, manage positions, cancel/amend orders, split/merge shares, and claim winnings. Use when user asks about prediction markets, event betting, YES/NO shares, orderbooks, or Alpha Arcade.
algorand-x402-payment
Execute x402 payments at runtime using Algorand MCP tools. Use whenever an HTTP request returns 402 Payment Required (or a PAYMENT-REQUIRED header), the user needs to access a paid API or x402-protected resource, or the user mentions x402, micropayments, paying for an endpoint, or "payment required" — even if they…
haystack-router-interaction
Route and execute optimal token swaps on Algorand using Haystack Router via Algorand MCP tools. Use when getting best-price quotes across multiple Algorand DEXes and LST protocols, executing atomic swaps, and checking asset opt-in — all through the Algorand MCP server.
use-wallet
Integrate Algorand/AVM wallet connections using @txnlab/use-wallet v4.x. Use when building dApps that need wallet connectivity (Pera, Defly, Lute, Kibisis, Exodus, WalletConnect, etc.), transaction signing, data signing (ARC-60/SIWA), network switching, or wallet state management in vanilla JS/TS, React, Vue, SolidJS…
nfd
Work with NFDomains (NFDs), the Algorand Name Service (.algo domains), using the @txnlab/nfd-sdk TypeScript SDK. Use when building features that involve resolving .algo domain names to addresses (or reverse), displaying NFD avatars and metadata, searching for NFDs, minting new NFDs, purchasing NFDs from the…