{"slug": "i-put-8-8b-tokens-on-my-cv", "title": "I Put 8.8B Tokens on My CV", "summary": "Victor Antos, a software developer, reported using 8.8 billion tokens with Claude Code over 234 days, including 8.4 billion cache reads and 19.8 million output tokens, and added the figure to his résumé alongside 15+ live products and 2,592 GitHub contributions. He argues that sustained, productive token usage is a skill comparable to flight hours, demonstrating throughput and context engineering, and notes that his context-trimming layer for NestClaw cuts token spend by roughly half.", "body_md": "# I Put 8.8 Billion Tokens on My CV\n\nThis morning I learned Claude Code has a `/cost`\n\ncommand. I ran it, stared at the screen for a second, and [tweeted the screenshot](https://x.com/victorantos/status/2092178289402032294): **8.8 billion tokens** in 234 days.\n\nThen I did something that felt slightly absurd and completely right: I [put the number on my résumé](/resume/).\n\n## How big is 8.8 billion, actually\n\nNumbers with nine zeros stop meaning anything, so let me translate. 8.8 billion tokens is roughly six and a half billion words — more text than the entire English Wikipedia — flowing between me and my coding agents in 234 days. And the odometer says I was only actively driving on 56 of those days, which puts the honest rate around 157 million tokens per active day of specs, diffs, test output, and code review.\n\nThe fine print is a story of its own. 8.4 of those billions are cache reads — agents re-reading their working context on every turn. That's not padding; that's exactly what several long-running sessions with big contexts cost, and the 19.8 million *output* tokens on the same line are the part I reviewed. There are 168 sessions in there, a 17-day streak, and one session that stayed open for 29 days straight.\n\nNo human types that. That's the point. The number isn't measuring my typing — it's measuring how much work I can keep in flight.\n\n## \"Tokens are a cost, not an achievement\"\n\nI can hear the objection, because I made it to myself first: bragging about tokens consumed is like bragging about lines of code written. It's an input metric. Spent badly, 8.8 billion tokens is just an expensive way to heat a server room in Dublin.\n\nThat's true — **on its own**. Which is why the number sits on my CV next to what it produced: [15+ live products](/resume/) built and operated end to end, 2.38 million companies indexed by my job-board agents, 2,592 GitHub contributions in the last twelve months, and a whole [Azure estate migrated to one VPS](/posts/from-azure-to-one-vps-llm-migration/). Input without output is burn rate. Input **with** output is throughput, and throughput is exactly what hiring managers are trying to estimate when they ask \"so, do you use AI tools?\"\n\nEveryone says yes to that question now. It's the \"proficient in Microsoft Word\" of 2026. A measured number is different: it's specific, it's falsifiable, and almost nobody has one, because almost nobody thought to look.\n\n## Spending tokens well is a skill\n\nHere's the claim I actually want to defend: sustaining that volume *productively* is a skill, the way flight hours are a skill. Nobody hires a pilot because sitting in a cockpit is impressive; they hire the hours because you can't fake what they proxy for. Getting through billions of tokens without producing garbage means, concretely:\n\n**Specs an agent can build from.** Every feature I ship starts as a Markdown spec. Vague prompts burn tokens on wrong answers; a good spec converts them into working code on the first or second pass.**Review that keeps up.** Agents produce faster than most people can read. I review like a tech lead — every line, before it ships — and the day I can't keep up, the pipeline stalls no matter how many tokens I throw at it.**Parallelism.** One agent session is autocomplete. Three or four at once — one migrating a schema, one writing tests, one drafting a scraper — is a team, and coordinating a team is the actual job.**Context engineering.** When you also pay API invoices for your own products' users, you learn to care. The context-trimming layer I built for[NestClaw](https://nestclaw.com)cuts token spend roughly in half. High throughput and cost discipline aren't opposites; the second is what makes the first sustainable.\n\nNone of that shows up in \"familiar with AI-assisted development.\" All of it shows up in the odometer.\n\n## What it looks like on the CV\n\nThe metrics strip on [my résumé](/resume/) now reads:\n\n20 yrsC#/.NET in production ·15+live products ·35production services on one VPS ·2,592GitHub contributions in 12 months ·8.8BClaude Code tokens in under 8 months\n\nAnd the skills table says it plainly: *Claude Code and parallel multi-agent workflows daily (8.8B tokens in under 8 months)*.\n\nMaybe in two years this will look as quaint as \"types 80 WPM.\" Fine. Right now, in the middle of the transition, it answers the one question every engineering interview circles around — *can this person actually work the new way, or do they just say they can?* — with a number instead of an adjective.\n\n## Check yours\n\nOpen Claude Code and run `/cost`\n\n. If you've been doing this daily for months, the number will surprise you — mine did, this morning, and I've been watching the invoices.\n\nAnd if it's big: consider writing it down where hiring managers can see it. The odometer only counts if you show it.\n\n*What's your number? Tell me on X — I'm collecting them.*", "url": "https://wpnews.pro/news/i-put-8-8b-tokens-on-my-cv", "canonical_source": "https://victorantos.com/posts/i-put-8-billion-tokens-on-my-cv/", "published_at": "2026-08-25 17:36:53+00:00", "updated_at": "2026-08-25 17:47:35.126682+00:00", "lang": "en", "topics": ["developer-tools", "ai-tools", "ai-agents", "artificial-intelligence"], "entities": ["Victor Antos", "Claude Code", "NestClaw", "GitHub", "Azure"], "alternates": {"html": "https://wpnews.pro/news/i-put-8-8b-tokens-on-my-cv", "markdown": "https://wpnews.pro/news/i-put-8-8b-tokens-on-my-cv.md", "text": "https://wpnews.pro/news/i-put-8-8b-tokens-on-my-cv.txt", "jsonld": "https://wpnews.pro/news/i-put-8-8b-tokens-on-my-cv.jsonld"}}