topic-classifier

A content-analysis agent that groups posts by topic or category and shows how much coverage each one has.

In plain words
What is it for?
Use it to review a content library, find missing or underserved subjects, compare recent and older topics, and suggest new content opportunities.
Why use it?
It helps reveal topics you cover too little, content with no category, and changes in topic coverage over time.

Agent

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.

agentmods
npx agentmods add agents/animalzinc/claude-plugins/topic-classifier
Clone the repo
git clone --depth 1 https://github.com/animalzinc/claude-plugins
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 204 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00015 $0.00204
Opus 5 $0.00008 $0.00102
Sonnet 5 $0.00003 $0.00041
Haiku 4.5 $0.00002 $0.00020

Measured 2d ago against content hash e764a2981b13, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

topic-classifier 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 2d 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.

plugins/content-library-auditor/agents/topic-classifier.md · 42 lines

What it actually says

Topic Classifier Agent

Analyze topic distribution and identify content opportunities.

Category Analysis

From provided content data:

  • Count posts per category/tag
  • Calculate percentages
  • Identify most/least covered topics
  • Find orphaned content (no category)

Topic Patterns

Look for:

  • Common category combinations
  • Topic evolution over time (early vs recent)
  • Emerging topics (growth in last 6 months)
  • Declining topics (decreased coverage)

Content Gap Identification

Identify opportunities:

  • Underserved topics (<5 posts) that could be expanded
  • Related topics covered but specific angles missing
  • Competitor topics not covered (if competitive data provided)
  • Seasonal gaps (topics not covered in certain periods)

Output Format

Markdown with:

  • Topic distribution table
  • Top 10 categories
  • Content gap analysis
  • Recommendations for content opportunities
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. 2d ago First seen · 42 lines · 15 tokens per session scan A e764a2981b13

Subscribe to this mod's changes

topic-classifier is an agent published in the GitHub repository animalzinc/claude-plugins (15 stars, last pushed 13d ago), licensed MIT. It adds 15 tokens to every session and 204 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-30.