Tools and kits for shipping with Claude Code

I build with Claude Code every day and publish what it costs, what breaks and what holds up. Price your own prompts for free, read how the systems work, then take the files.

Open the token counter See the kits →

Chudi Nnorukam. AI systems engineer in the San Francisco Bay Area. Data Science at UC Berkeley.

Start where you are

I want to know what Claude will cost me Token counter and cost calculator. Free, runs in your browser.
I want Claude Code to stop forgetting my project Kits with the CLAUDE.md, skills and prompts I use. From $29, paid once. Kits from $29, paid once.
I want to see how it works before I buy anything 80 posts on Claude Code, ADHD systems and AI search, newest first. 80 posts, newest first.

Measured, not guessed

2.3x Fable 5.1 cost per turn against Opus 5.5, replaying one measured working day at list prices. Sep 26, 2026 15% vs 5% AI citation rate of a site with domain authority under 10, against Ahrefs at 92. Apr 7, 2026 1 in 30 Top-three Google results that an AI answer also cited, ten questions, same day. Sep 8, 2026

Every receipt, with its method →

Published elsewhere

Guides for developers on freeCodeCamp and QuantVPS.

How to measure your AI citation rate, on freeCodeCamp
A developer's guide to WebMCP, on freeCodeCamp
Best LLMs for quant trading, on QuantVPS

What is AI-visible web architecture?

AI-visible web architecture is the practice of structuring a website so it serves three audiences simultaneously: human readers through editorial design, large language models through machine-readable content surfaces (llms.txt, structured data, FAQ schema), and AI agents through callable tool interfaces (WebMCP, ai.txt). This site is the reference implementation.

Frequently asked questions

How do I run the AVR Framework on my own site?

Clone github.com/Citability/ai-visibility-readiness, install scripts/requirements.txt, and run python3 scripts/run_audit.py YOUR_URL --skip-lighthouse --full-v11. The free audit covers infrastructure plus the three v1.1.0 sections at zero API cost.

Where is the full methodology documented?

The canonical AVR v1.1.0 framework page lives at /framework. It documents all eight audit sections, the three verdict tiers, the example output for chudi.dev, the v1.0 to v1.1.0 changelog, and the verified citation numbers behind every claim.

What is the difference between chudi.dev and citability.dev?

chudi.dev DEMONSTRATES AVR. citability.dev IMPLEMENTS AVR. The framework was authored on this site as a case study; the audit tool that scores any URL against the framework lives at citability.dev. Both sites land AGENT-READY 3 of 3 on Section 6 as of 05/23/2026.

Where do I see chudi.dev's own audit results?

The live JSON snapshot is at /api/webmcp/avr-self-audit?format=full. The reproducible source files live in the avr-pipeline repo under sample-audits.

Who is the author and what is the operator stack?

Chudi Nnorukam is an AI Systems Engineer who builds AI-native growth systems. The operator stack is the AVR Framework on top of an AI-Visible Web Architecture pattern. The full bio with cross-platform sameAs links, affiliations, and Entity Authority Tier signals lives at /about.

Plain-language glossary: AVR, fact-block density, entity graph, crawlability

AVR: AI Visibility Readiness - a score for whether AI tools like ChatGPT or Perplexity recommend your site or skip it. See how it is scored →
Fact-block density: How much of your page is written as direct, citable answers an AI can extract and quote rather than background filler prose.
Entity graph: A structured map of who you are and what you cover, so AI systems can place you in the right knowledge context without guessing.
Crawlability: Whether AI crawlers can access, parse, and trust your content enough to include it in their training and retrieval pools.