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 ourobx/agent-ebpf --skill xai-apigit clone --depth 1 https://github.com/ourobx/agent-ebpfWrote 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/ourobx/agent-ebpf/xai-api)<a href="https://agentmods.dev/skills/ourobx/agent-ebpf/xai-api"><img src="https://agentmods.dev/badge/skills/ourobx/agent-ebpf/xai-api/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/ourobx/agent-ebpf/xai-api"><img src="https://agentmods.dev/badge/skills/ourobx/agent-ebpf/xai-api.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 | $0.00145 | $0.01716 |
| Opus 5.5 | $0.00058 | $0.00686 |
| Sonnet 5.5 | $0.00029 | $0.00343 |
| Haiku 4.5 | $0.00015 | $0.00172 |
Grade B, and why
xai-api scanned grade B with 1 finding 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 1mo 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
const res = await fetch("https://api.x.ai/v1/chat/completions", { method: "POST", How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
xAI API (Grok)
When XAI_API_KEY is present in the environment, this app has real xAI API
access — use it for AI features instead of mocking responses or reaching for
another provider. The same variable is injected into the deployed app at
publish, so code built against it works identically in preview and production.
The key is the app owner's personal key: every call spends their quota and credits. Be deliberate about usage — see Spend responsibly before wiring AI calls into anything that runs automatically or is open to visitors.
The key unlocks the full API surface, not just chat:
- Chat / LLM — latest model:
grok-4.5; default to it unless the user asks otherwise. - Imagine (images & video) — generate and edit images, generate video, at runtime inside the app.
- Voice — text-to-speech with expressive voices (and transcription).
- Official docs: docs.x.ai — endpoints, models, parameters, streaming, tool use. Don't guess API shapes; check the docs.
- The API is OpenAI-compatible (
https://api.x.ai/v1), so any OpenAI-style client works by switching the base URL and key.
Env vars — do not create a .env file
| Var | Where | Purpose |
|---|---|---|
XAI_API_KEY |
server | Injected by the platform (preview and deploy). Never write, hardcode, or ask the user for it. |
The key is server-only: read it with process.env.XAI_API_KEY inside
createServerFn handlers / server code, never in client components, and never
expose it via a VITE_-prefixed variable or an API response.
It can be absent (rollout-gated). Degrade gracefully — check for it and show a friendly "AI features are unavailable" state instead of crashing:
const apiKey = process.env.XAI_API_KEY;
if (!apiKey) throw new Error("AI is not available in this environment");
Calling the API (server-only)
No SDK needed — plain fetch from a server function:
import { createServerFn } from "@tanstack/react-start";
export const askGrok = createServerFn({ method: "POST" })
.validator((input: { prompt: string }) => input)
.handler(async ({ data }) => {
const apiKey = process.env.XAI_API_KEY;
if (!apiKey) return { ok: false as const, error: "AI is not available" };
const res = await fetch("https://api.x.ai/v1/chat/completions", {
method: "POST",
headers: {
"Content-Type": "application/json",
Authorization: `Bearer ${apiKey}`,
},
body: JSON.stringify({
model: "grok-4.5",
messages: [{ role: "user", content: data.prompt }],
}),
});
if (!res.ok) {
return { ok: false as const, error: `xAI API error ${res.status}` };
}
const body = (await res.json()) as {
choices: { message: { content: string } }[];
};
return { ok: true as const, text: body.choices[0]?.message.content ?? "" };
});
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.
- 1mo ago First seen · 153 lines · 145 tokens per session scan B 56acdf3895ae
xai-api is a skill published in the GitHub repository ourobx/agent-ebpf (1 stars, last pushed 1mo ago), licensed MIT. It adds 145 tokens to every session and 1,716 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it B with 1 finding (sends data to an external url). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and designs an end-to-end governed agentic analytics solution using Knowledge Catalog and Managed Service for Apache Spark (Lightning Engine). Use when designing data science and analytics workflows across structured and unstructured distributed data (including in S3, Azure Blob, AlloyDB, and…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
finetuning
Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file…