Skip to content

The Walkie blog

Measured numbers on tokens, screenshots, and what your coding agent can actually read. Every figure is measured or calculated with the formula shown; sources are linked.

Token Economics

What screenshots, recordings and sessions cost, in numbers you can check.

Token Economics

Why UI work burns more Claude Code tokens than backend work

A screenshot is not paid for once. In a multi-turn session it is re-sent every turn, so 2,691 tokens becomes 26,910 over ten. The math, and the fix.

Updated August 2026 · 6 min read
Token Economics

Why your Claude Max plan runs out faster than you expect

Claude usage limits are token-based, not message-based. Long visual sessions compound fast, and the fixes cost nothing.

Updated August 2026 · 8 min read
Token Economics

What Is a Context Window? (And Why Filling It Hurts)

A context window is everything one request holds. Claude models now run 200,000 or 1M tokens, and one 30-second frame dump costs 80,730 of them.

Updated August 2026 · 6 min read
Token Economics

What does one Claude Code session actually cost?

A line-item breakdown of a Claude Code session: what is fixed, what is not, and why 2,691-token screenshots often dominate the bill.

Updated August 2026 · 8 min read
Token Economics

Video, Screenshots or Words: The Real Cost to an AI

What a frame-dumped video, screenshots and spoken words each cost an AI coding agent to read, worked from Anthropic's published patch formula.

Updated August 2026 · 7 min read
Token Economics

11 Ways to Cut Claude Code Token Costs

Eleven ways to cut Claude Code token costs, ranked by tokens saved per minute of effort. Ten are free; one costs money.

Updated August 2026 · 7 min read
Token Economics

Claude Code token costs: where your context actually goes

A 1080p screenshot costs 2,691 tokens on Claude 4.7 and later. Where the rest of a Claude Code session's tokens actually go, line by line.

Updated August 2026 · 9 min read
Token Economics

Why Your Coding Agent Can't Watch a Screen Recording

Claude accepts images, not video. What actually happens when you frame-dump a screen recording for your agent, and what the frames cost.

Updated August 2026 · 7 min read
Token Economics

How Many Tokens Does a Screenshot Cost Your AI Coding Agent?

A 1080p screenshot costs 2,691 tokens on Claude 4.7 and later, capped at 4,784. The formula, a measured test, and what to send instead.

Updated August 2026 · 11 min read
Token Economics

How Claude Calculates Image Tokens (the Formula, Explained)

Claude prices an image at one token per 28x28-pixel patch, capped at 4,784. The formula worked on a 1920x1080 screen and a measured 1288x811 test.

Updated August 2026 · 7 min read

AI Coding Workflow

How to run a talk-point-draw feedback loop with an agent, and which tools fit which job.

AI Coding Workflow

What is visual feedback for AI coding agents?

Show an AI coding agent what is wrong on screen instead of describing it: the four kinds of tools, what each costs, and why 3,500 tokens beats 80,730.

Updated August 2026 · 9 min read
AI Coding Workflow

AI coding agent glossary: 24 terms, defined

Token, context window, image tokens, MCP, skill, compaction, prompt caching, REVIEW.md, frame dump: 24 terms defined in under 75 words each.

Updated August 2026 · 9 min read
AI Coding Workflow

MCP Explained (For People Who Just Want More)

MCP is an open-source standard, hosted by The Linux Foundation, that lets an AI agent call real tools and data instead of only generating text.

Updated August 2026 · 9 min read
AI Coding Workflow

The vibe coding workflow: a working setup for solo builders

Vibe coding is describe, generate, look, react. The look-and-react half has almost no tooling, and one screenshot costs 2,691 tokens before you speak.

Updated August 2026 · 9 min read
AI Coding Workflow

Vibe Coding Tools in 2026: The Honest Stack

The 2026 vibe-coding stack has four jobs: agents, voice input, review and testing. Every price here was re-read on the vendor page on 16 August 2026.

Updated August 2026 · 7 min read
AI Coding Workflow

Screen Recording for Claude Code: What Works in 2026

Four ways to show Claude Code your screen, priced: raw video it cannot open, a frame dump at 80,730 tokens, screenshots, and a bundle at about 3,500.

Updated August 2026 · 7 min read
AI Coding Workflow

Can you feed a Loom video to an AI coding agent?

Loom's AI reads the transcript, not the pixels. Frame-dumping a 30-second Loom costs 80,730 tokens; a narrated bundle costs about 3,500.

Updated August 2026 · 7 min read
AI Coding Workflow

Best Tools for Giving AI Coding Agents Feedback (2026)

Eleven tools that turn your screen into feedback an AI coding agent can read. Every price re-read on its vendor page on 16 Aug 2026: free to $39 once.

Updated August 2026 · 8 min read
AI Coding Workflow

Give Your AI Agent Visual Feedback Without Burning Tokens

Narrate and point instead of pasting screenshots into Claude Code or Cursor. A spoken review costs about 150 tokens; one 1080p screenshot costs 2,691.

Updated August 2026 · 7 min read

Reviewing AI Code

Seeing, describing and verifying what the agent built.

Reviewing AI Code

How to run a visual review with Claude Code (step by step)

One-click setup and a 30-second loop: connect Walkie, record while you talk and point, hand the bundle to Claude Code, verify the fix.

Updated August 2026 · 7 min read
Reviewing AI Code

Why your AI agent can't see what it built

An agent works in text and sees a render only when a tool hands it one. What Claude Code can and cannot see in 2026, and what each look costs in tokens.

Updated August 2026 · 7 min read
Reviewing AI Code

A 12-Point Checklist for Verifying AI-Built UI

Twelve checks for the states AI coding agents most reliably miss, why each one gets missed, and the fastest way to force it to appear right now.

Updated August 2026 · 8 min read
Reviewing AI Code

How to review AI-generated code you didn't write

Read a generated diff in one order: data shape, then boundaries, then logic. Five failure patterns with the exact strings to grep for, and how deep to go.

Updated August 2026 · 8 min read
Reviewing AI Code

How to review what your AI coding agent built

What the agent already checked, what only you can catch, and a plan-execute-verify loop that closes the gap — with the token cost of every way of looking.

Updated August 2026 · 9 min read
Reviewing AI Code

The plan → execute → verify loop, explained

Plan and execute are easy to automate. Verification is where quality lives — and the one step an AI coding agent can only close if you hand it a check.

Updated August 2026 · 8 min read
Reviewing AI Code

How to Give Feedback to Claude Code That Lands

Feedback lands when it names the location, the expectation, and the gap. Most reports name only the gap. Plus the Claude Code files that make it stick.

Updated August 2026 · 7 min read
Reviewing AI Code

How to describe a visual bug to an AI coding agent

The spacing looks off gives an agent nothing to fix. What to say instead: a ten-row translation table and the three bug types words alone cannot carry.

Updated August 2026 · 8 min read

Product

What a REVIEW.md bundle is and how Walkie builds one.

Comparisons

Priced, sourced side-by-sides.