mcp-skillset: Agent for Claude Code

.claude/agents/content-agent.md

content-agent is an agent for Claude Code from bobmatnyc/mcp-skillset. It costs 123 tokens per session (6,185 once invoked), scanned A, original, MIT.

A website-content agent for improving text quality, search visibility, readability, accessibility, and user engagement.

In plain words
What is it for?
Use it to edit website copy, improve grammar and clarity, apply SEO and accessibility practices, and make content more consistent and concise.
Why use it?
It helps turn unclear, error-prone, or poorly structured website copy into text that is easier to read and find.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: positional $N argument.

This is bobmatnyc/mcp-skillset's own configuration. It tells Claude Code how to work on mcp-skillset 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 mcp-skillset configures →

Reuse

Borrowing it

Nothing to install: this file belongs to bobmatnyc/mcp-skillset. 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/bobmatnyc/mcp-skillset/main/.claude/agents/content-agent.md
Clone the repo
git clone --depth 1 https://github.com/bobmatnyc/mcp-skillset

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 content-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/bobmatnyc/mcp-skillset/content-agent/github.svg)](https://agentmods.dev/agents/bobmatnyc/mcp-skillset/content-agent)
Your own site
<a href="https://agentmods.dev/agents/bobmatnyc/mcp-skillset/content-agent"><img src="https://agentmods.dev/badge/agents/bobmatnyc/mcp-skillset/content-agent/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 content-agent

Your own site · 80×15
<a href="https://agentmods.dev/agents/bobmatnyc/mcp-skillset/content-agent"><img src="https://agentmods.dev/badge/agents/bobmatnyc/mcp-skillset/content-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 123 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,185 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 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 $0.00123 $0.06185
Opus 5 $0.00062 $0.03093
Sonnet 5 $0.00025 $0.01237
Haiku 4.5 $0.00012 $0.00619

Measured 9d ago against content hash 0c1fcfe73e36, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

content-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 9d 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.

.claude/agents/content-agent.md · 759 lines

How it starts

The opening of the file, as written. The whole thing — 759 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Content Optimization Agent

You are a specialized website content optimization expert focused on improving text quality, SEO, readability, and accessibility. You combine copywriting expertise with technical knowledge of modern web standards and tools.

Core Mission

Optimize website content with focus on:

  • Quality: Clear, engaging, error-free writing
  • SEO: Search visibility and organic traffic
  • Readability: Easy-to-understand content for target audience
  • Accessibility: WCAG compliance and inclusive content
  • Engagement: Higher conversion and user interaction
  • Performance: Fast-loading, well-structured content

Content Quality Framework

1. Text Quality Assessment

Grammar and Style:

  • Check for grammar, spelling, and punctuation errors
  • Ensure consistent tone and voice throughout
  • Apply Grammarly-style analysis:
    • Clarity: Remove unnecessary words and jargon
    • Conciseness: Target 15-20 words per sentence average
    • Tone consistency: Match brand voice guidelines
    • Active voice preference (aim for 80%+ active)

Readability Optimization:

  • Apply Hemingway Editor principles:
    • Target Grade 8-10 reading level for general audiences
    • Limit complex sentences (15% maximum)
    • Avoid excessive adverbs
    • Use strong, simple verbs
    • Break up dense paragraphs (3-5 sentences max)

Content Structure:

  • Clear hierarchy with descriptive headings (H1-H6)
  • Logical flow with appropriate transitions
  • Scannable format with bullet points and short paragraphs
  • Strategic use of whitespace and visual breaks
  • Key information front-loaded (inverted pyramid)

2. SEO Optimization Strategy

Keyword Research and Implementation:

# Search for current keyword usage
grep -i "target_keyword" content/*.html content/*.md

# Analyze keyword density
grep -io "keyword" file.html | wc -l

On-Page SEO Checklist:

  1. Title Tags: 50-60 characters, keyword at start
  2. Meta Descriptions: 150-160 characters, compelling CTA
  3. H1 Tags: Single H1 per page with primary keyword
  4. Header Hierarchy: Proper H2-H6 structure with keywords
  5. URL Structure: Clean, descriptive, keyword-rich slugs
  6. Internal Linking: Descriptive anchor text, strategic links
  7. Image Alt Text: Descriptive, keyword-relevant
  8. Content Length: Minimum 300 words, optimal 1500+ for pillar content

Read the full file on GitHub · 759 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. 9d ago First seen · 759 lines · 123 tokens per session scan A 0c1fcfe73e36

Subscribe to this mod's changes

content-agent is an agent published in the GitHub repository bobmatnyc/mcp-skillset (20 stars, last pushed 6mo ago), licensed MIT. It adds 123 tokens to every session and 6,185 once invoked, about $0.0006 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.

Related

Other agents, from other repositories

graph-reviewer

Validates knowledge graphs for correctness, completeness, and quality. Runs systematic checks and renders approval or rejection decisions.

Egonex-AI/Understand-Anything · 26 tokens

article-analyzer

Analyzes markdown files using pre-parsed structural data and LLM inference to extract knowledge graph nodes and edges (entities, claims, implicit relationships, topic clustering).

Egonex-AI/Understand-Anything · 36 tokens

design-analyzer

Analyzes Figma structural nodes (pages, screens, components, instances, tokens) from a deterministic manifest and adds semantic enrichment — concise summaries, tags, and a screen's purpose — plus conservative related edges. Does NOT invent structural nodes or edges.

Egonex-AI/Understand-Anything · 56 tokens

impeccable-agent

Autonomous executor for non-interactive impeccable commands. Runs audit, polish, harden, layout, typeset, and other automatable design operations without user interaction.

catlog22/maestro-flow · 39 tokens

metadata-extractor

Extracts paper metadata (authors, date, venue, fields, DOI/arxiv ID) and a paper-quality assessment (credibility, experimental rigor, reproducibility) from a paper's plain text. Invoked alongside lite-drafter and finding-extractor during /paperloom:ingest.

trapoom555/claude-paperloom · 63 tokens

gsd-research-synthesizer

Synthesizes research outputs from parallel researcher agents into SUMMARY.md. Spawned by /gsd-new-project after 4 researcher agents complete.

mrboups/xbrain · 37 tokens