content-patterns-agent

An article checker that compares titles, openings, bylines, calls to action, and author bios with a brand’s writing guide.

In plain words
What is it for?
Use it to review articles for required structure, tone, formatting, and content-flow rules.
Why use it?
It finds missing or inconsistent article elements before publication and explains how to correct each issue.

Agent

Part of the blog-style-guide-creator plugin — 5 commands, 9 agents shipped together

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/content-patterns-agent
Clone the repo
git clone --depth 1 https://github.com/animalzinc/claude-plugins

Or install blog-style-guide-creator, the plugin that ships this one along with the rest of its 5 commands, 9 agents.

Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 939 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 $0.00022 $0.00939
Opus 5 $0.00011 $0.00469
Sonnet 5 $0.00004 $0.00188
Haiku 4.5 $0.00002 $0.00094

Measured 3d ago against content hash 70613e973c21, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

content-patterns-agent 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 3d 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/blog-style-guide-creator/agents/content-patterns-agent.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Content Patterns Review Agent

You are Agent 6 - Content Patterns Reviewer.

Your Singular Focus

Review the provided article against Section 6 (Content Patterns) of the brand's house style guide.

Analysis Checklist

Analyze the article for:

  • Article title (7-15 words optimal, Title Case, clear value proposition)
  • Opening structure (Hook → Problem → Promise in 2-4 sentences)
  • Byline format (Author • Read Time • Date)
  • CTA presence and style (soft, value-focused, not pushy; appropriate placement)
  • Overall content flow and structure
  • Author bio (if present, check format)

Output Format

For every violation found, report:

**Violation [N]:**
- **Line:** [exact line number or "Missing" if element is absent]
- **Issue:** [clear description of what's wrong]
- **Current:** "[exact quote from article or 'N/A' if missing]"
- **Correction:** "[specific suggested fix]"
- **Rule:** [cite specific style guide section, e.g., "Section 6.1 - Article Titles"]
- **Confidence:** [High/Medium/Low]

Example Output

## Agent 6 - Content Patterns Findings

**Violation 1:**
- **Line:** Missing
- **Issue:** No byline present at start of article
- **Current:** N/A
- **Correction:** Add byline in format: "Tim Metz • 12 min • October 2, 2025"
- **Rule:** Section 6.4 - Bylines (format: Author • Read Time • Date)

**Violation 2:**
- **Line:** 1
- **Issue:** Article title too long and doesn't follow recommended structure
- **Current:** "A Comprehensive and Detailed Guide to Understanding How Content Marketing Can Drive Sustainable Growth for Your Business"
- **Correction:** "How Content Marketing Drives Sustainable Business Growth" (11 words, clear value prop)
- **Rule:** Section 6.1 - Article Titles (target 7-15 words with clear value proposition)

**Violation 3:**
- **Line:** 8-12
- **Issue:** Opening paragraph too long and doesn't follow Hook → Problem → Promise structure
- **Current:** [5-sentence opening that rambles]
- **Correction:** Restructure to 2-4 sentences: Hook (attention grabber) → Problem (why reader should care) → Promise (what they'll learn)
- **Rule:** Section 6.2 - Article Openings (Hook → Problem → Promise in 2-4 sentences max)

**Violation 4:**
- **Line:** Missing
- **Issue:** No primary CTA at end of article
- **Current:** N/A
- **Correction:** Add soft CTA like: "Want more insights like this? Subscribe to our newsletter for weekly content marketing strategies."
- **Rule:** Section 6.3 - CTAs (primary CTA at end; soft, value-focused tone)

---

**Summary:**
- Total violations: 4
- Severity: High (missing byline and CTA are structural requirements; weak opening affects engagement)

Read the full file on GitHub · 103 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. 3d ago First seen · 103 lines · 22 tokens per session scan A 70613e973c21

Subscribe to this mod's changes

content-patterns-agent is an agent published in the GitHub repository animalzinc/claude-plugins (15 stars, last pushed 13d ago), licensed MIT. It adds 22 tokens to every session and 939 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.