Practical AI Coding Workflows with Awesome Agent SkillsAn AI agent can finish a feature, pass the tests, and still leave behind unnecessary abstractions, misleading comments, or a README that no longer matches the product. Asking it to "check everything" 4d ago · 8 min readkhasky.hashnode.dev
Non-English Prompts Cost More Tokens, Context and Money in Most LLMsClaude Opus 5 costs $5 per million input tokens whether a prompt arrives in English or in Russian. What changes between the two languages is how many tokens the same paragraph becomes, and the bill is2AIOct 5 · 7 min readkhasky.hashnode.dev
Fable Becomes the Advisor to Opus 5.5 in Claude CodeWith Opus 5.5 as the main model in a Claude Code session, a Fable quota can still go to work without Fable taking over the session. The /advisor fable command connects Fable as an advisor that Opus coOct 3 · 3 min readkhasky.hashnode.dev
Rejudge Replaces Self-Review With 3 Independent Models and a JudgeI have a hard time trusting an AI coding agent to review code it just wrote. The model already made the decision that the implementation was good enough to produce. Then we ask it to inspect that sameOct 1 · 5 min readkhasky.hashnode.dev
Gemini 4 Argon Beats GPT-6 Astra and Claude on Most BenchmarksGoogle DeepMind has announced Gemini 4 Argon, a frontier model aimed at long software engineering jobs, legal and finance work, and cyber defense. In Google's own evaluation it beats GPT-6 Astra, ClauOct 1 · 5 min readkhasky.hashnode.dev
