CLAUDE LABJP
MODEL — Claude Fable 5.1 and Claude Mythos 5.1 landed on September 1. They are the same underlying model; only the strength of the safeguards differsPRICING — Per-token rates hold at $10/$50 per MTok. What changed is cache reads, cut 75% to $0.25 per MTokCOST — How much that saves depends on your workload: roughly 25% for typical use, up to about 45% for context-heavy agentic work. Worth measuring your own split before quoting a numberBENCH — Terminal-Bench-Science 0.1 climbs from 24.7% on Fable 5 to 52.6%. Anthropic also states a standard error of 3.5-4.5 points, which is worth remembering before reading small gaps as realSAFEGUARDS — Sharper cyber safeguards cut interventions in Claude Code sessions by roughly 60% on average. Finding vulnerabilities is now allowed; developing exploits still is notAPI — New API accounts created from today can no longer edit prior context while preserving Claude's thinking transcript. It is an anti-distillation measure, and existing accounts are unaffected for nowMODEL — Claude Fable 5.1 and Claude Mythos 5.1 landed on September 1. They are the same underlying model; only the strength of the safeguards differsPRICING — Per-token rates hold at $10/$50 per MTok. What changed is cache reads, cut 75% to $0.25 per MTokCOST — How much that saves depends on your workload: roughly 25% for typical use, up to about 45% for context-heavy agentic work. Worth measuring your own split before quoting a numberBENCH — Terminal-Bench-Science 0.1 climbs from 24.7% on Fable 5 to 52.6%. Anthropic also states a standard error of 3.5-4.5 points, which is worth remembering before reading small gaps as realSAFEGUARDS — Sharper cyber safeguards cut interventions in Claude Code sessions by roughly 60% on average. Finding vulnerabilities is now allowed; developing exploits still is notAPI — New API accounts created from today can no longer edit prior context while preserving Claude's thinking transcript. It is an anti-distillation measure, and existing accounts are unaffected for now
TAG

Automation

152 articles
Back to all tags
Related:
Claude Code68claude-code29Cowork14MCP13Claude API12reliability11cowork10headless9hooks8mcp8scheduled tasks7troubleshooting7
Claude Code/2026-05-04Intermediate

Build a Pipeline Where Docs Update Automatically Every Time Your Code Changes

Build a CI/CD pipeline that auto-generates README, CHANGELOG, and API docs whenever code changes. Use Claude Haiku 4.5 for cost-efficient classification and Sonnet 4.6 for quality output — cutting API costs by up to 70% while keeping documentation accurate.

Claude Code/2026-05-04Intermediate

Setting Up Claude Code's GitHub PR Trigger for Automated Code Review

A step-by-step guide to configuring Claude Code's GitHub PR trigger, writing effective CLAUDE.md review policies, and what two weeks of real usage taught me about keeping the signal-to-noise ratio high.

Cowork/2026-05-04Advanced

Why Cowork Scheduled Tasks Stop Mid-Run and How to Recover

Diagnose Cowork scheduled task failures using measured exit codes and real error output — why safe.directory delays failure instead of fixing it, how to pick a writable root before cloning, and how to structure logs with reason codes.

Claude Code/2026-05-04Intermediate

Claude Code MCP Servers in Practice — From Setup to Real-World Use

A practical guide to connecting MCP servers in Claude Code — covering configuration tips, common errors, and real project setups that actually work.

API & SDK/2026-05-04Intermediate

Auto-Classify and Draft Gmail Replies with Claude API and Google Apps Script

A hands-on guide to building a Gmail automation system using Claude API and Google Apps Script. Automatically classify incoming emails and generate reply drafts — with copy-paste code.

Cowork/2026-05-03Intermediate

Honest 6-Month Review of Claude Cowork — What Actually Worked for an Indie Developer

A candid 6-month review of Claude Cowork from an indie developer's perspective. Covers scheduled tasks, skills, and the memory system — what exceeded expectations, what was genuinely painful, and the hard-won lessons that changed how I use AI automation.

Cowork/2026-05-03Intermediate

Claude in Chrome × Google Sheets — Automate Repetitive Tasks with Apps Script

A practical guide to generating and running Google Sheets Apps Script with Claude in Chrome. No programming experience required — automate data cleanup, aggregation, and conditional formatting in minutes.

Claude Code/2026-04-30Advanced

Composing Claude Code Skills — Building Automation a Single Skill Can't Reach

A practical guide to going beyond one-skill-at-a-time and composing multiple Claude Code Skills into real workflows. Pipeline, branching, and meta-skill patterns with full implementation examples and the failure modes you should design against.

Claude Code/2026-04-30Intermediate

Automating Frontend Accessibility Audits with Claude Code — axe-core, Hooks, and PR Comments That Actually Get Read

A practical way to make accessibility audits actually stick in a real codebase. Combine axe-core with Claude Code skills, pre-commit hooks, and a GitHub Actions PR comment, with code you can paste in today.

Cowork/2026-04-29Intermediate

Designing the One Page You Open Every Morning — Building Living Dashboards with Cowork Artifacts and MCP

Cowork Artifacts promote a chat answer into a re-openable page that fetches live MCP data. Here is how I design pages that replace recurring questions.

Claude Code/2026-04-28Intermediate

Automate Presentation Slides in 30 Minutes with Claude Code Skills

Learn how to combine Claude Code Skills with Markdown intermediate format to generate presentation slides from planning to Google Slides export in just 30 minutes.

Claude Code/2026-04-27Advanced

Claude Code Hooks: A Field Guide to the 8 Core Hooks — and the 33-Event Catalog They Now Live In

Claude Code hooks are powerful, but most people give up before figuring out which event does what. Here's the field guide I wish I had when I started — six months of running hooks in production, distilled.