cron-mcp: Instructions file for Claude Code

CLAUDE.md

cron-mcp CLAUDE.md is an instructions file for Claude Code from globalion/cron-mcp. It costs 733 tokens per session, scanned A, a copy of cron-mcp CLAUDE.md, MIT.

A project instruction file for deploying the cron-mcp service to a Hetzner server and connecting it to the cron.regiq.in web address.

In plain words
What is it for?
Deploying new versions, setting up the subdomain, restarting the service, and managing the required environment variables.
Why use it?
It gives coding agents the repository-specific steps and safety rules needed to deploy updates without disturbing other services on the shared server.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is globalion/cron-mcp's own configuration. It tells Claude Code how to work on cron-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cron-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to globalion/cron-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/globalion/cron-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/globalion/cron-mcp

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 cron-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/globalion/cron-mcp/claude-md.svg)](https://agentmods.dev/instructions/globalion/cron-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/globalion/cron-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/globalion/cron-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 733 This file is loaded in full into every session.
When invoked 733 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 $0.00733 $0.00733
Opus 5 $0.00367 $0.00367
Sonnet 5 $0.00147 $0.00147
Haiku 4.5 $0.00073 $0.00073

Measured 6d ago against content hash ad0ac8bc8768, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

cron-mcp CLAUDE.md 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 6d 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.

curl https://cron.regiq.in/api/admin/health
Origin

This is a copy

100% identical to cron-mcp CLAUDE.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deploying cron-mcp to Hetzner + regiq.in

Deploy pattern for future Claude Code sessions working on this repo.

Server (shared with the rest of the Globalion MCP fleet)

  • SSH: [email protected]
  • Service directory: /opt/cron-mcp/
  • Domain: cron.regiq.in (Cloudflare-tunnelled to cron-mcp-web:3000)
  • Container names: cron-mcp-web, cron-mcp-db
  • NEVER touch other people's folders under /opt/ — see shreyas-onboarding.md §7.

Deploy a new version

From this repo on your dev machine:

tar --exclude=node_modules --exclude=.next --exclude=.git -cf - . \
  | ssh [email protected] "mkdir -p /opt/cron-mcp && tar -xf - -C /opt/cron-mcp/"
ssh [email protected] "cd /opt/cron-mcp && docker compose up -d --build"

First-time subdomain wiring (cron.regiq.in)

  1. Add an ingress rule to /opt/platform/cloudflared/config.yml on the server, BEFORE the final catch-all rule:
    - hostname: cron.regiq.in
      service: http://cron-mcp-web:3000
    
  2. Restart the tunnel: ssh [email protected] "docker restart platform-cloudflared-1"
  3. Create the DNS CNAME via the tunnel's own creds (no API token needed):
    ssh [email protected] "docker exec platform-cloudflared-1 cloudflared tunnel route dns 0caf1caf-59f6-4f36-9ea5-4aa9a9f41d0b cron.regiq.in"
    

Env vars

Populated on the server via /opt/cron-mcp/.env (NOT committed to git). Values live in shreyas-onboarding.md for shared secrets, per-app secrets are generated fresh:

  • GOOGLE_CLIENT_ID / GOOGLE_CLIENT_SECRET — created per-MCP in Google Cloud Console
  • NEXTAUTH_SECRETopenssl rand -base64 32
  • PUBLIC_BASE_URL=https://cron.regiq.in
  • NEXTAUTH_URL=https://cron.regiq.in

Health & debugging

curl https://cron.regiq.in/api/admin/health
ssh [email protected] "docker ps --filter name=cron-mcp --format 'table {{.Names}}\t{{.Status}}'"
ssh [email protected] "docker logs cron-mcp-web --tail 60"

Rules (from shreyas-onboarding.md §7)

  • No LLM in this stack. cron-mcp is a pure transport bridge — the user's agent supplies the model. If a future feature needs inference, route via OpenRouter with the shared Globalion key, never vendor APIs direct.
  • ✅ Expose /api/admin/health (already wired at src/app/api/admin/health/route.ts).
  • ✅ Container names prefixed with cron-mcp- and unique across the fleet.
  • ✅ Container-internal port is any port (3000 here); Cloudflare tunnel handles external HTTPS.

Read the full file on GitHub · 58 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. 6d ago First seen · 58 lines · 733 tokens per session scan A ad0ac8bc8768

Subscribe to this mod's changes

cron-mcp CLAUDE.md is an instructions file published in the GitHub repository globalion/cron-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 733 tokens to every session, about $0.0037 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to cron-mcp CLAUDE.md, differing in 0 lines, and is treated as a copy.

Related

Other instructions, from other repositories