hub-custom

hub-custom is a command for Claude Code from fiale-plus/fiale-claude-plugins. It costs 15 tokens per session (1,386 once invoked), scanned B, original, MIT.

A setup command for tracking a service that the status hub does not already support. A status hub collects updates from services such as issue trackers or monitoring tools in one place.

In plain words
What is it for?
Use it to set up tracking for services such as Sentry, Linear, or Jira by checking existing integrations or guiding the creation of a refresh method.
Why use it?
It provides a way to monitor a service even when no ready-made integration is available.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths; names the AskUserQuestion tool; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the claude-status-hub plugin — 16 commands shipped together

Good fit Use it to set up tracking for services such as Sentry, Linear, or Jira by checking existing integrations or guiding the creation of a refresh method.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add fiale-plus/fiale-claude-plugins
Claude Code
/plugin install claude-status-hub

Made for: Claude Code.

Or install claude-status-hub, the plugin that ships this one along with the rest of its 16 commands.

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 hub-custom

README.md
[![agentmods](https://agentmods.dev/badge/commands/fiale-plus/fiale-claude-plugins/hub-custom.svg)](https://agentmods.dev/commands/fiale-plus/fiale-claude-plugins/hub-custom)
Your own site
<a href="https://agentmods.dev/commands/fiale-plus/fiale-claude-plugins/hub-custom"><img src="https://agentmods.dev/badge/commands/fiale-plus/fiale-claude-plugins/hub-custom.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,386 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 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 $0.00015 $0.01386
Opus 5 $0.00008 $0.00693
Sonnet 5 $0.00003 $0.00277
Haiku 4.5 $0.00002 $0.00139

Measured 7d ago against content hash 4bdf3ea2d30b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

hub-custom scanned grade B with 2 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 7d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

After generating the skill, automatically detect and add required permissions to `~/.claude/settings.json`.

Makes network callslowCapability

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

- `curl <url>` → `"Bash(curl <domain>:*)"`
plugins/claude-status-hub/commands/hub-custom.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hub Custom - Setup Tracking for Unknown Services

Set up status tracking for any service by finding or creating an appropriate refresh skill.

Parse Argument

Extract <service-name> from the argument (e.g., "sentry", "linear", "jira").

If no service name provided, ask: "What service do you want to track?"

Step 1: Check Existing Skills

Before doing anything, check if a skill already exists:

ls ${CLAUDE_PLUGIN_ROOT}/skills/hub-refresh-<service>*.md 2>/dev/null

If found:

  • Say "Found existing skill: [filename]. Service is ready to track."
  • Ask if they want to add it to monitoring now

Step 2: Present Choice

Use AskUserQuestion:

question: "How would you like to set up tracking for <service>?"
header: "Setup"
options:
  - label: "AI-powered (Recommended)"
    description: "I'll search for integrations and figure out the best approach"
  - label: "Guide me"
    description: "I'll describe what I want to track in my own words"

Path A: AI-Powered Detection

A1. Check Installed MCPs

Look for relevant MCPs in the system:

  • Check ~/.claude/mcp.json for installed servers
  • Check if any MCP name contains the service name
  • If found: "You have [mcp-name] installed. I can use this to track ."

A2. Search for Available Integrations

If no MCP found:

Web search: "<service> MCP server Claude"
Web search: "<service> Claude Code plugin"

If results found:

  • Present options to user
  • Offer to help install
  • After install, create skill that uses the MCP

A3. Browser Integration

If no MCP available or user declines:

  1. Ask: "Do you have open in a browser tab?"
  2. If yes:
    • Get tabs via mcp__claude-in-chrome__tabs_context_mcp
    • Find the service tab
    • Take screenshot: mcp__claude-in-chrome__computer action=screenshot
    • Read page structure: mcp__claude-in-chrome__read_page
  3. Analyze the page:
    • Look for notification badges, counters, status indicators
    • Identify elements that would be useful to track
  4. Present findings:
    • "I found these trackable elements: [list]"
    • "Which would you like to monitor?"
  5. Generate skill file with selected elements

Read the full file on GitHub · 191 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. 7d ago First seen · 191 lines · 15 tokens per session scan B 4bdf3ea2d30b

Subscribe to this mod's changes

hub-custom is a command published in the GitHub repository fiale-plus/fiale-claude-plugins (4 stars, last pushed 5mo ago), licensed MIT. It adds 15 tokens to every session and 1,386 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.