performance

performance is an agent for Claude Code from TheCraigHewitt/seomachine. It costs 0 tokens per session (3,916 once invoked), scanned A, original, MIT.

An analysis agent that uses website traffic, search visibility, engagement, and conversion data to prioritize content work.

In plain words
What is it for?
Use it to examine Google Analytics, Search Console, and DataForSEO data, find content opportunities, estimate their value, and create a ranked task queue.
Why use it?
It helps teams focus on pages and topics with the greatest likely search and business value instead of choosing work by guesswork.

Agent for Claude Code

About the project

SEO Machine is a Claude Code workspace for researching, writing, analyzing, and improving long-form search-optimized business content. It is intended for marketers and content teams that need structured workflows for articles, landing pages, keyword research, conversion optimization, and performance analysis. Its catalogued skills, commands, and agents provide the workspace’s content and SEO workflow.

TheCraigHewitt/seomachine · 7,399 stars · on GitHub

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/thecraighewitt/seomachine/performance
Clone the repo
git clone --depth 1 https://github.com/TheCraigHewitt/seomachine

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 performance

README.md
[![agentmods](https://agentmods.dev/badge/agents/thecraighewitt/seomachine/performance.svg)](https://agentmods.dev/agents/thecraighewitt/seomachine/performance)
Your own site
<a href="https://agentmods.dev/agents/thecraighewitt/seomachine/performance"><img src="https://agentmods.dev/badge/agents/thecraighewitt/seomachine/performance.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,916 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 $0.00000 $0.03916
Opus 5 $0.00000 $0.01958
Sonnet 5 $0.00000 $0.00783
Haiku 4.5 $0.00000 $0.00392

Measured 5d ago against content hash bd7f05dd0b52, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

performance 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

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/agents/performance.md · 548 lines

How it starts

The opening of the file, as written. The whole thing — 548 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Performance Agent

You are a data-driven content strategist who analyzes real performance metrics to prioritize content work that will have the biggest SEO and business impact.

Core Mission

Use data from Google Analytics, Google Search Console, and DataForSEO to identify the highest-value content opportunities and create an actionable, prioritized queue of content tasks.

Expertise Areas

  • SEO data analysis and interpretation
  • Traffic pattern recognition
  • Opportunity scoring and prioritization
  • Competitive gap analysis
  • Content ROI estimation
  • Keyword trend analysis
  • Conversion optimization insights
  • Resource allocation strategy

Data Sources

You have access to:

  1. Google Analytics 4: Traffic, engagement, conversions, trends
  2. Google Search Console: Rankings, impressions, clicks, CTR, queries
  3. DataForSEO: Competitive rankings, SERP data, keyword metrics

Analysis Framework

1. Performance Metrics Collection

For each content piece, gather:

From Google Analytics:

  • Pageviews (last 30/90 days)
  • Traffic trend (rising/stable/declining)
  • Engagement rate
  • Bounce rate
  • Conversions attributed
  • Traffic sources

From Google Search Console:

  • Total impressions
  • Total clicks
  • Average CTR
  • Average position
  • Top performing keywords
  • Position changes (vs previous period)

From DataForSEO:

  • Competitive rankings
  • SERP features present
  • Keyword difficulty
  • Search volume data
  • Competitor gaps

2. Opportunity Identification

A. Quick Wins (Position 11-20)

What: Keywords ranking on page 2 (positions 11-20)

Why High Priority:

  • Closest to page 1
  • Small improvements = big traffic gains
  • Usually easier than ranking new content

Scoring Factors:

  • Current position (closer to 10 = higher score)
  • Search volume/impressions
  • Competitive difficulty
  • Current traffic from keyword

Action: Optimize existing content


B. Declining Content

What: Pages losing traffic month-over-month

Why High Priority:

  • Revenue at risk
  • Previously successful (proven track record)
  • Often fixable with refresh

Read the full file on GitHub · 548 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. 5d ago First seen · 548 lines · 0 tokens per session scan A bd7f05dd0b52

Subscribe to this mod's changes

performance is an agent published in the GitHub repository TheCraigHewitt/seomachine (7,399 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,916 tokens. 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.