add-a-service

add-a-service is a skill for Claude Code, Codex from lonormaly/builders-stack. It costs 55 tokens per session (1,050 once invoked), scanned A, original, MIT.

A guide for adding an independently running service to the builders-stack monorepo, a repository that holds multiple related packages. A service is a server or worker with its own process and deployment.

In plain words
What is it for?
Use it when adding an HTTP server, webhook receiver, background worker, queue consumer, or scheduled process. It covers the service directory, package scripts, entrypoint, Tilt setup, deployment registry, and shared image build path.
Why use it?
It prevents independently deployed work from being mixed into shared library code. It also lists the package, configuration, local-development, and deployment entries needed for a new service.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is "typecheck": "bash ../../scripts/typecheck-native.sh --noEmit".

Good fit Use it when adding an HTTP server, webhook receiver, background worker, queue consumer, or scheduled process. It covers the service directory, package scripts, entrypoint, Tilt setup, deployment registry, and shared image build path.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/lonormaly/builders-stack
agentmods
npx agentmods add skills/lonormaly/builders-stack/add-a-service

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for add-a-service

README.md
[![agentmods](https://agentmods.dev/badge/skills/lonormaly/builders-stack/add-a-service/github.svg)](https://agentmods.dev/skills/lonormaly/builders-stack/add-a-service)
Your own site
<a href="https://agentmods.dev/skills/lonormaly/builders-stack/add-a-service"><img src="https://agentmods.dev/badge/skills/lonormaly/builders-stack/add-a-service/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.

agentmods 80×15 button for add-a-service

Your own site · 80×15
<a href="https://agentmods.dev/skills/lonormaly/builders-stack/add-a-service"><img src="https://agentmods.dev/badge/skills/lonormaly/builders-stack/add-a-service.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,050 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00055 $0.01050
Opus 5.5 $0.00022 $0.00420
Sonnet 5.5 $0.00011 $0.00210
Haiku 4.5 $0.00006 $0.00105

Measured 1mo ago against content hash e784f4bd95e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

add-a-service scanned grade A 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`./tilt_up.sh` shows the new resource green in the dashboard (`localhost:10380`); `curl http://<name>.stack.localhost:1355/health` returns `{ "ok": true }` (skip for a worker and check its log line). `bun run check:deplo
agents/skills/add-a-service/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add a service

A services/* package is anything with a URL or its own deploy — an HTTP server, a webhook receiver, or a background worker (which has no URL but still runs as its own process). Use this when a new surface needs to run independently.

When to use

  • New HTTP endpoint group that deserves its own process/deploy → new service.
  • New background consumer (queue worker, cron) → new service (no URL, still a Tilt resource).
  • Not for shared logic with no runtime of its own — that's a lib.

Steps

  1. Name it. services/<name>, package @stack/<name>. No pinned port — served roles run behind Portless at <name>.stack.localhost:1355 (Portless injects a random PORT). See docs/portless.md.

  2. Files:

    services/<name>/
    ├── package.json
    ├── tsconfig.json
    └── src/
        ├── index.ts        # entrypoint: start the server / worker
        └── <feature>/      # organize BY FEATURE, not by layer
    
  3. package.json — a dev script Tilt will call:

    {
      "name": "@stack/<name>",
      "private": true,
      "type": "module",
      "scripts": {
        "dev": "bun --hot src/index.ts",
        "start": "bun src/index.ts",
        "typecheck": "bash ../../scripts/typecheck-native.sh --noEmit"
      }
    }
    
  4. tsconfig.json: { "extends": "../../tsconfig.base.json", "include": ["src"] }

  5. src/index.ts — Hono for HTTP; read the port from process.env.PORT (Portless injects it — never hardcode). Always expose /health:

    import { Hono } from "hono";
    const app = new Hono();
    app.get("/health", (c) => c.json({ ok: true }));
    const port = Number(process.env.PORT ?? 3003); // fallback only for standalone runs
    export default { port, fetch: app.fetch };
    

    For a background worker there's no server — just start the consumer loop and log readiness. No /health, no port (no Portless wrapper either — see ai-worker in the Tiltfile).

  6. Persistence via @stack/db only. Payments via @stack/payment only. Never import another service's internals — talk over HTTP.

Read the full file on GitHub · 83 lines

Changes

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.

  1. 1mo ago First seen · 83 lines · 55 tokens per session scan A e784f4bd95e0

Subscribe to this mod's changes

add-a-service is a skill published in the GitHub repository lonormaly/builders-stack (42 stars, last pushed 24d ago), licensed MIT. It adds 55 tokens to every session and 1,050 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

better-t-stack

Create or extend an end-to-end type-safe TypeScript project with Better-T-Stack (create-better-t-stack). Use when the user wants to start, scaffold or bootstrap an app, API, fullstack project or monorepo with any of Next.js, TanStack Router or Start, React Router, Nuxt, Svelte, Solid, Astro, React Native, Hono…

AmanVarshney01/create-better-t-stack · 149 tokens

investigate-cloudflare

Investigate deployed Worker failures, regressions, and missing operational signals using Cloudflare Issues, logs, traces, SQL, or Observability MCP. Produce bounded evidence and verify recurrence against the deployed version.

brandhaug/b2b-saas-starter · 45 tokens

configure-cloudflare-monitoring

Configure or reconcile Cloudflare SQL alerts and shared Worker dashboards for a deployment, adapt monitoring to a scenario, and verify thresholds, missing data, and delivery. Use for monitoring setup or changes; use investigate-cloudflare for incident diagnosis.

brandhaug/b2b-saas-starter · 52 tokens

api-fetch-wrapper

Wrap a public HTTP API (Open-Meteo weather as the demo) with credential handling, error normalisation, and a single retry on transient network failures. Demonstrates the production-shaped baseline for any "skill that calls an external service" — env-based secrets, structured error output, no leaked API keys in logs…

ChronoAIProject/Ornn · 121 tokens

sandy-cli

Run TypeScript scripts in sandboxed microVMs or Docker containers with AWS SDK access via IMDS, through the sandy CLI. Use when investigating AWS resources, running read-only queries, or executing TypeScript automation that needs AWS credentials via shell commands.

jamestelfer/sandy · 54 tokens

hono-cloudflare

Hono on Cloudflare Workers - bindings, KV, D1, R2, Durable Objects, and edge deployment patterns.

bobmatnyc/claude-mpm-skills · 29 tokens