news

Anthropic quietly nerfed Claude Code's 1-hour cache, and your token budget is paying the price - XDA

Claude Code users reported burning through usage quotas faster after Anthropic shortened the tool’s effective cache window, reducing how much prior context could be reused without re-paying input tokens.

Published 2026-04-20Source: XDA

Why it matters

Caching policy changes can swing the effective cost of agentic coding dramatically. If your workflow depends on long-running projects and repeated context reuse, a cache-window reduction can turn ‘steady’ spend into surprise overages overnight.

Tokenmaxxing read

Tokenmaxxing isn’t just verbosity—it’s cache economics. Track cache hit rates and billed input tokens, budget for cache misses, and design flows to avoid replaying long context (summaries, state files, retrieval, smaller diffs).

Source takeaway

The article points to Claude Code JSONL logs (`~/.claude/projects/`) with cache fields like `ephemeral_5m_input_tokens` vs `ephemeral_1h_input_tokens`, plus a mid-April Anthropic comment on a Claude Code GitHub issue about the shorter cache.

Topic links

tokenmaxxingcoding-agentstopic agentstopicscoreboards

Related projects

Tools that match this angle

#4In spirit

Agents

LangGraph

langchain-ai/langgraph

A framework for building resilient stateful agents with explicit graphs, persistence, human-in-the-loop flows, and controllable execution.

39.9K6.7KMIT

agentsstateworkflows

Project profile GitHub

#5Direct

Evaluation

promptfoo

promptfoo/promptfoo

A CLI and CI workflow for testing prompts, agents, and RAG systems across models, with evals and red-team style checks.

24.3K2.2KMIT

prompt-evalscirag

Project profile GitHub

#6In spirit

Evaluation

DSPy

stanfordnlp/dspy

A framework for programming and optimizing language-model pipelines rather than hand-tuning one prompt at a time.

37.3K3.2KMIT

optimizationprogrammingevals

Project profile GitHub

Related feed

More source-linked context

CNX Software - Embedded Systems News source artwork

newsCS

news2026-08-07

Token Monitor - An ESP32-S3 desktop display that tracks AI coding assistant usage (Crowdfunding) - CNX Software

Fractal Manifold is crowdfunding Token Monitor, a EUR 99 ESP32-S3 desk display with a 4-inch touchscreen that shows quota use, session limits, reset timers and estimated token costs for Claude Code, Codex CLI and Antigravity CLI.

tokenmaxxingcoding-agentsagents

Read note

newsT

news2026-08-05

The real energy use of agentic AI

Climate scientist Zeke Hausfather metered his own Claude Code habit: 1,138 typed prompts fanned out to more than 14,000 model calls and 3.2 billion tokens in eight weeks, drawing roughly 170 kWh of data-center electricity.

tokenmaxxingcoding-agentsagents

Read note

newsH

news2026-07-26medium review

Claude Code Was Burning Tokens Until I Put a Gate in Front of It | HackerNoon

Prateek Kapoor wrapped Claude Code in a PreToolUse hook that rejects unbounded greps and whole-file reads, hands the agent a corrected command, and reports 75% to 80% lower token use on heavy editing tasks.

tokenmaxxingcoding-agentsagents

Read note