worker

worker is a command for Claude Code from Flagler-County-BoCC/mcp-forge. It costs 0 tokens per session (608 once invoked), scanned A, original, MIT.

A template for the entry point and job scheduler of a worker process, a program that runs background tasks instead of serving direct user requests.

In plain words
What is it for?
Use it when rewriting a worker-based project to organize process startup, scheduled job registration, job handlers, and predictable execution.
Why use it?
It provides a defined place to start the process, register jobs, handle shutdown signals, and respond to unhandled failures.

Command for Claude Code

Written for Claude Code: installed under .claude/.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import { validate } from '../../lib/validate.js';.

Good fit Use it when rewriting a worker-based project to organize process startup, scheduled job registration, job handlers, and predictable execution.

Compare 6 commands 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/Flagler-County-BoCC/mcp-forge
agentmods
npx agentmods add commands/flagler-county-bocc/mcp-forge/worker

Made for: Claude Code.

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 worker

README.md
[![agentmods](https://agentmods.dev/badge/commands/flagler-county-bocc/mcp-forge/worker/github.svg)](https://agentmods.dev/commands/flagler-county-bocc/mcp-forge/worker)
Your own site
<a href="https://agentmods.dev/commands/flagler-county-bocc/mcp-forge/worker"><img src="https://agentmods.dev/badge/commands/flagler-county-bocc/mcp-forge/worker/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 worker

Your own site · 80×15
<a href="https://agentmods.dev/commands/flagler-county-bocc/mcp-forge/worker"><img src="https://agentmods.dev/badge/commands/flagler-county-bocc/mcp-forge/worker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 608 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00000 $0.00608
Opus 5.5 $0.00000 $0.00243
Sonnet 5.5 $0.00000 $0.00122
Haiku 4.5 $0.00000 $0.00061

Measured 1mo ago against content hash 5fb009a11029, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

worker 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.

.claude/commands/entrypoints/worker.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Entrypoint — worker

This file is consumed by Step 8 of the rewrite process. Apply when AUDIT_MANIFEST.projectType === "worker".

src/worker.ts — Process Entry

import { config } from './config/index.js';
import { logger } from './lib/logger.js';
import { startScheduler, stopScheduler } from './scheduler.js';

async function main(): Promise<void> {
  logger.info({ env: config.env }, 'Worker starting');
  await startScheduler();
  logger.info('Worker ready — consuming jobs');
}

async function shutdown(signal: string): Promise<void> {
  logger.info({ signal }, 'Shutting down worker');
  await stopScheduler();
  process.exit(0);
}

process.on('SIGTERM', () => void shutdown('SIGTERM'));
process.on('SIGINT',  () => void shutdown('SIGINT'));
process.on('unhandledRejection', (reason) => {
  logger.fatal({ reason }, 'Unhandled promise rejection');
  process.exit(1);
});

void main();

src/scheduler.ts — Job Registration

export async function startScheduler(): Promise<void> {
  // Register each job from AUDIT_MANIFEST job handlers
  // e.g. queue.process('<job-name>', concurrency, <job-name>Handler);
}

export async function stopScheduler(): Promise<void> {
  // Gracefully close queue connections
}

src/jobs//.handler.ts

import { validate } from '../../lib/validate.js';
import { <JobName>PayloadSchema } from './<job-name>.schema.js';
import { <jobName>Service } from '../../lib/container.js';
import { createLogger } from '../../lib/logger.js';

const log = createLogger({ module: '<job-name>Handler' });

export async function <jobName>Handler(job: Job): Promise<void> {
  const payload = validate(<JobName>PayloadSchema, job.data);
  log.info({ jobId: job.id }, '<job-name> started');
  await <jobName>Service.<method>(payload);
  log.info({ jobId: job.id }, '<job-name> completed');
}

Rules:

  1. Every handler validates its payload with validate() before processing.
  2. Handlers must be idempotent — running the same job twice must not cause double side-effects.
  3. Log job start and completion with jobId in context.
  4. Handlers throw AppError subclasses on business failures; the queue library handles retries.
  5. Never call process.exit() inside a handler.

Read the full file on GitHub · 76 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 · 76 lines · 0 tokens per session scan A 5fb009a11029

Subscribe to this mod's changes

worker is a command published in the GitHub repository Flagler-County-BoCC/mcp-forge (1 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 608 tokens. 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.