sabx

sabx is a skill for Claude Code, Codex from avivsinai/skills-marketplace. It costs 30 tokens per session (509 once invoked), scanned A, a copy of sabx, MIT.

A command-line tool for controlling SABnzbd, an application that downloads files from Usenet, a discussion and file-sharing network. It connects to SABnzbd using its web address and API key.

In plain words
What is it for?
Use it to view active downloads, add NZB files or URLs, pause and resume the queue, change priorities, retry failures, manage speed limits, and inspect system status.
Why use it?
It lets you manage downloads from a terminal instead of opening the SABnzbd interface. It also puts queue, history, status, speed, and diagnostics commands in one place.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; mentions Codex.

Good fit Use it to view active downloads, add NZB files or URLs, pause and resume the queue, change priorities, retry failures, manage speed limits, and inspect system status.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/avivsinai/skills-marketplace/sabx
Install

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.

Any agent
npx skills add avivsinai/skills-marketplace --skill sabx
Clone the repo
git clone --depth 1 https://github.com/avivsinai/skills-marketplace

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 sabx

README.md
[![agentmods](https://agentmods.dev/badge/skills/avivsinai/skills-marketplace/sabx/github.svg)](https://agentmods.dev/skills/avivsinai/skills-marketplace/sabx)
Your own site
<a href="https://agentmods.dev/skills/avivsinai/skills-marketplace/sabx"><img src="https://agentmods.dev/badge/skills/avivsinai/skills-marketplace/sabx/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 sabx

Your own site · 80×15
<a href="https://agentmods.dev/skills/avivsinai/skills-marketplace/sabx"><img src="https://agentmods.dev/badge/skills/avivsinai/skills-marketplace/sabx.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 509 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 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 $0.00030 $0.00509
Opus 5 $0.00015 $0.00254
Sonnet 5 $0.00006 $0.00102
Haiku 4.5 $0.00003 $0.00051

Measured 5d ago against content hash db78eb752b73, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

sabx 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 5d 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.

Origin

This is a copy

100% identical to sabx — 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.

plugins/sabx/skills/sabx/SKILL.md · 67 lines

What it actually says

SABnzbd CLI

Use sabx for SABnzbd reads and changes. Start with the requested operation; check installation, authentication, or connection settings only when a command fails for that reason. Search references/commands.md for exact flags and less common commands.

Common reads

sabx status
sabx queue list
sabx history list
sabx server list
sabx rss list
sabx schedule list

Prefer --json when another tool will consume the result. Use --profile NAME only when the user selects a non-active profile.

Changes

Resolve the queue item, history item, category, server, feed, or schedule entry before changing it. Commands that add an NZB, reorder or delete items, clear history, pause or resume processing, change limits, edit feeds/schedules, or enable/disable servers change SABnzbd state.

  • Follow the user's authorization for the concrete change.
  • Do not interpret "clean up" as permission to delete queue items or all history; ask what should be removed if the target is not explicit.
  • After an ambiguous timeout, read back queue/history/server state before retrying a mutation.
  • Never expose the SABnzbd API key in output, logs, commands, or messages.

Typical operations:

sabx queue add url URL
sabx queue item pause NZO_ID
sabx queue item resume NZO_ID
sabx queue item priority NZO_ID 2
sabx speed limit --rate 10M

Use the command reference before deletion, RSS, scheduler, server, or configuration changes.

Connection diagnosis

If a command reports no configuration, authenticate with the supported config flow. If it reports connection refused, verify the selected profile URL and that SABnzbd is running. If it reports authentication failure, replace the key through the secure config command; do not print the current key. Do not disable TLS verification unless the user explicitly chooses that risk.

For repository development and release checks, use CLAUDE.md.

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago Changed · -99 lines · -53 tokens per session db78eb752b73
  2. 12d ago First seen · 166 lines · 83 tokens per session scan A fa4a6fbd1543

Subscribe to this mod's changes

sabx is a skill published in the GitHub repository avivsinai/skills-marketplace (2 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 509 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to sabx, differing in 0 lines, and is treated as a copy.