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 scalixworld/scalix-cloud-mcp --skill scalix-functionsgit clone --depth 1 https://github.com/scalixworld/scalix-cloud-mcpWrote 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/scalixworld/scalix-cloud-mcp/scalix-functions)<a href="https://agentmods.dev/skills/scalixworld/scalix-cloud-mcp/scalix-functions"><img src="https://agentmods.dev/badge/skills/scalixworld/scalix-cloud-mcp/scalix-functions/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/scalixworld/scalix-cloud-mcp/scalix-functions"><img src="https://agentmods.dev/badge/skills/scalixworld/scalix-cloud-mcp/scalix-functions.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 | $0.00067 | $0.00407 |
| Opus 5.5 | $0.00027 | $0.00163 |
| Sonnet 5.5 | $0.00013 | $0.00081 |
| Haiku 4.5 | $0.00007 | $0.00041 |
Grade A, and why
scalix-functions 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 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.
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
Scalix Functions
Serverless functions that scale to zero when idle. A cold start provisions an isolated environment, so the first invocation after idle is meaningfully slower than a warm one — for latency-sensitive endpoints, keep the function warm with regular traffic.
Runtimes — the rule that prevents wasted work
Supported runtimes are node and python only. Do not attempt to deploy Go, Rust, Ruby, or anything else as a function runtime — for other languages, package a container image instead (--image).
Write a handler
// handler.ts
export default async function handler(req: Request) {
const body = await req.json();
return new Response(JSON.stringify({ result: body.x + body.y }), {
headers: { "Content-Type": "application/json" },
});
}
Deploy
fn deploy requires either --source <path> or --image <image>:
scalix-cloud fn deploy api --source ./api --runtime node # from source
scalix-cloud fn deploy api --image registry/img:v1 # from a container image
Invoke and manage
scalix-cloud fn list
scalix-cloud fn invoke api --data '{"x": 1, "y": 2}'
scalix-cloud fn delete <function-id>
The same operations exist over REST (POST https://api.scalix.world/v1/functions) and as MCP tools — prefer MCP tools when this plugin's server is connected.
Full reference: https://docs.scalix.world/functions
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 Changed bbf77a329e0c
- 2mo ago First seen · 46 lines · 67 tokens per session scan A 3b8e4b08d350
scalix-functions is a skill published in the GitHub repository scalixworld/scalix-cloud-mcp (2 stars, last pushed 20d ago), licensed MIT. It adds 67 tokens to every session and 407 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
spring-boot
Spring Boot 4.x development - REST APIs, JPA, Security, Testing, and Cloud-native patterns. Use for building enterprise Java applications with Spring Boot.
java-modern
Java 21+ features for Spring Boot - records, sealed classes, pattern matching, virtual threads, text blocks. Use when user asks about modern Java, Java 21 features, or when modernizing existing code.
conventions
Spring Boot project conventions and mandatory rules. Auto-loads when working with Spring Boot, Java, or Maven projects. Enforces No-Lombok, constructor injection, RestClient, Flyway for relational databases, Problem Details errors, and other standards; adds OpenAPI contract rules when the API is built for a UI.
webiny-api-cms-custom-field-type
How to implement a custom CMS field type that integrates with the model builder's fluent API. Covers extending DataFieldBuilder, composing validator interfaces, creating a FieldTypeFactory, registering via DI, and module augmentation for TypeScript autocomplete on the fields() registry.
functions-development
Build serverless Go or Python functions for Falcon Foundry apps. TRIGGER when user asks to "create a function", "write a serverless function", "build backend logic", runs foundry functions create, or needs help with FDK handler patterns, function testing, or collection integration from functions. Also TRIGGER when…
vector-backend-operations
Select and connect the right vector-store backend for the vector-mcp MCP server — chromadb, postgres/pgvector, qdrant, couchbase, or mongodb — and supply the correct dbtype/connection parameters that every collection and search call needs. Use when the agent must decide which engine to target, wire up…