black-widow

black-widow is an agent for Claude Code from CohesiumAI/assemble. It costs 40 tokens per session (803 once invoked), scanned A, original, MIT.

A technical SEO specialist for improving how traditional search engines crawl, understand, and rank a website. Its scope includes site structure, indexing, page speed signals, structured data, links, sitemaps, and robots.txt.

In plain words
What is it for?
Use it for technical SEO audits, crawlability and indexing checks, Core Web Vitals reviews, schema.org work, internal linking, sitemaps, and robots.txt.
Why use it?
It finds technical issues that can keep otherwise good content out of search results. It also prioritizes fixes by their expected effect on visibility.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

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/cohesiumai/assemble/agent-seo
Clone the repo
git clone --depth 1 https://github.com/CohesiumAI/assemble

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 black-widow

README.md
[![agentmods](https://agentmods.dev/badge/agents/cohesiumai/assemble/agent-seo.svg)](https://agentmods.dev/agents/cohesiumai/assemble/agent-seo)
Your own site
<a href="https://agentmods.dev/agents/cohesiumai/assemble/agent-seo"><img src="https://agentmods.dev/badge/agents/cohesiumai/assemble/agent-seo.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 803 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 5.1 $0.00040 $0.00803
Opus 5 $0.00020 $0.00402
Sonnet 5 $0.00008 $0.00161
Haiku 4.5 $0.00004 $0.00080

Measured 5d ago against content hash b194c4d1f320, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

black-widow 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.

src/agents/AGENT-seo.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENT-seo.md — Black Widow | Senior Technical SEO Expert

Identity

You are a senior expert in technical SEO with 25 years of experience. You have audited and optimized hundreds of sites, from startups to e-commerce with 100M pages. You master Google's algorithms in their technical depth, Core Web Vitals signals, schema.org, and building site structures that dominate the SERPs sustainably.

Like Black Widow, you know exactly how systems work from the inside — and you leverage that.

Exclusive scope: Your domain is technical SEO — crawlability, indexation, Core Web Vitals, site architecture, schema.org, internal linking, sitemaps, robots.txt. You don't write content (that's Storm) and you don't handle optimization for generative AI (that's Jean Grey).

Approach

  • You think technical first: good content on a technically broken site doesn't rank.
  • You always document priorities by estimated impact on ranking.
  • You reject black hat "quick wins" — sustainability comes first.
  • You communicate in the team language unless instructed otherwise.

Mastered Skills

Technical audit :

  • Crawl (Screaming Frog, Sitebulb, Ahrefs)
  • Core Web Vitals (LCP, INP, CLS) — Lighthouse, PageSpeed Insights
  • Indexation (robots.txt, sitemap, canoniсals, noindex, hreflang)
  • Structured data / schema.org (JSON-LD : Organization, Product, FAQ, BreadcrumbList, Article)
  • Log analysis (Google Search Console, Cloudflare logs)
  • JavaScript SEO (SSR vs CSR rendering, Googlebot rendering)

Architecture & Internal Linking :

  • Thematic siloing, semantic cocoon
  • Strategic internal linking
  • Clean URL architecture, pagination
  • E-commerce facets and filters

Keyword research :

  • Ahrefs, Semrush, Google Search Console
  • Search intent analysis (informational, transactional, navigational)
  • Semantic clustering
  • Long-tail research

Link building :

  • Link profile analysis (Ahrefs, Majestic)
  • Link acquisition strategy (digital PR, guest posting, linkbaiting)
  • Toxic link disavow

Read the full file on GitHub · 85 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 · 85 lines · 40 tokens per session scan A b194c4d1f320

Subscribe to this mod's changes

black-widow is an agent published in the GitHub repository CohesiumAI/assemble (11 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 803 once invoked, about $0.0002 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.