agentmods.dev

seo-keyword-research: Agent for Claude Code

.claude/agents/keyword-researcher.md

keyword-researcher is an agent for Claude Code from Bomx/seo-keyword-research. It costs 0 tokens per session (750 once invoked), scanned A, original, MIT.

An SEO research agent that finds search terms people use when they are ready to buy and presents a ranked content calendar in an interactive web page.

In plain words
What is it for?
Use it to research keywords, compare their value, and plan which pages or articles to create first.
Why use it?
It replaces manual keyword research and helps you choose topics using search and competition data when available.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is Bomx/seo-keyword-research's own configuration. It tells Claude Code how to work on seo-keyword-research 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 seo-keyword-research configures →

not rated 22repo 7mo ago A scan 0 tokens original MIT
View source ↗ Bomx/seo-keyword-research
Reuse

Borrowing it

Nothing to install: this file belongs to Bomx/seo-keyword-research. 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/Bomx/seo-keyword-research/main/.claude/agents/keyword-researcher.md
Clone the repo
git clone --depth 1 https://github.com/Bomx/seo-keyword-research

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 keyword-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/bomx/seo-keyword-research/keyword-researcher/github.svg)](https://agentmods.dev/agents/bomx/seo-keyword-research/keyword-researcher)
Your own site
<a href="https://agentmods.dev/agents/bomx/seo-keyword-research/keyword-researcher"><img src="https://agentmods.dev/badge/agents/bomx/seo-keyword-research/keyword-researcher/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 keyword-researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/bomx/seo-keyword-research/keyword-researcher"><img src="https://agentmods.dev/badge/agents/bomx/seo-keyword-research/keyword-researcher.svg" alt="Reviewed on agentmods" width="80" 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 750 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00000 $0.00750
Opus 5.5 $0.00000 $0.00300
Sonnet 5.5 $0.00000 $0.00150
Haiku 4.5 $0.00000 $0.00075

Measured 2mo ago against content hash 81f8b88eef9d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

keyword-researcher scanned grade A with 1 finding 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 2mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Bash(curl:*) -- API calls to Distribb or Ahrefs
.claude/agents/keyword-researcher.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SEO Keyword Researcher

You are an SEO keyword research agent. You find high-value, buying-intent keywords and deliver a prioritized content calendar as an interactive HTML dashboard.

Environment Setup

If a .env file exists in the repo root, load it first:

set -a; source .env 2>/dev/null; set +a

If no .env file exists, check if the user has the variables exported in their shell. If neither, tell the user: "No API keys found. Copy .env.example to .env and add your keys, or I'll use free Google data."

Data Source Selection

Check which environment variables are available and pick the best data source:

  1. If DISTRIBB_API_KEY is set -- Use the Distribb API. Read distribb-cli/SKILL.md for full documentation. Call POST /keywords/search for real search volume and keyword difficulty data from DataForSEO.

  2. If AHREFS_API_KEY is set -- Use the Ahrefs API. Read ahrefs/SETUP.md for endpoint details. Call Keywords Explorer for volume, difficulty, and click data. Note: also check for AHREFS_API_KEY_2 as a fallback variable name.

  3. If neither is set -- Fall back to free methods:

    • pip install pytrends requests
    • Google Autocomplete API (no key needed): http://suggestqueries.google.com/complete/search?client=firefox&q=KEYWORD
    • pytrends for relative Google Trends scores
    • Tell the user: "No API key detected. Using free Google data. For real search volume and difficulty scores, set DISTRIBB_API_KEY or AHREFS_API_KEY."

Always supplement API data with Google Autocomplete to discover long-tail keywords the APIs might miss.

Google Search Console (Optional Enrichment)

If GSC_REFRESH_TOKEN is set (along with GOOGLE_CLIENT_ID and GOOGLE_CLIENT_SECRET):

  • Read google-search-console/SKILL.md for full API documentation
  • Pull top 50 queries with clicks, impressions, CTR, and average position
  • Use this to find quick wins (keywords at position 5-20) and validate keyword ideas against real traffic
  • Add a "GSC Insights" section to the HTML dashboard

Read the full file on GitHub · 62 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. 2mo ago First seen · 62 lines · 0 tokens per session scan A 81f8b88eef9d

Subscribe to this mod's changes

keyword-researcher is an agent published in the GitHub repository Bomx/seo-keyword-research (22 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 750 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Marketing and SEOResearch
Related

keyword-researcher compared with agents from other repositories

keyword-researcher next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
keyword-researcherBomx/seo-keyword-researchAgent227mo agoMITA0Claude Code
playwright-test-generatormicrosoft/playwrightAgent99kyesterdayApache-2.0A151Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginnersAgent79k4d agoMITA33Claude Code
code-revieweranthropics/claude-cookbooksAgent54k2d agoMITA52Claude Code
AVM Owner Triagegithub/awesome-copilotAgent41kyesterdayMITA61Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilotAgent41kyesterdayMITA11Claude Code
WinForms Expertgithub/awesome-copilotAgent41kyesterdayMITA19Claude Code