» Tag
claude
44 postsBullshit Detector: Open Agent Skills That Fact-Check Viral Videos
Open-source agent skills toolkit fact-checks YouTube, TikTok, articles and tweets, producing per-claim verdicts and a 0-10 bullshit score.
Cutting Token Costs with Claude Code: Insights and Strategies
Discover methods for reducing token costs and optimizing speed with Claude Code.
When a Rival Blog Vanished: AI-Assisted Ethical Link Repair
A niche technical blog vanished overnight, breaking thousands of links. Here's how a small content team used Claude to run ethical broken-link building in a single day.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comClaude Code Orchestration: 96% Performance at 46% of Cost
Anthropic's Fable-Sonnet orchestration pattern now runs natively in Claude Code: 96% performance at 46% cost. Details plus the pilotfish package inside.
A plugin can pass validation and still fail after install
Plugin validators check manifest compliance but do not ensure post-install functionality.
Running Claude Code on AWS Bedrock: IAM and SCP Pitfalls to Avoid
Learn about IAM and SCP configurations to avoid pitfalls when running Claude Code on AWS Bedrock.
Stop Hooks: Enforcing Claude Code Behavior with Hard Constraints
Stop hooks enforce Claude Code behavior with hard constraints, ensuring reliable adherence to rules.
Importance of Running Tests in CLAUDE.md and How Hooks Help
Hooks in CLAUDE.md provide a critical mechanism to ensure tests are always run. Explore how these mechanisms function in this article.
Building an MCP Server in Go: A Guide for Claude Code
Discover how to build an MCP server in Go. A step-by-step guide for integration with Claude Code.
Cutting Claude API Costs 84% by Separating Vision and Reasoning
An OCR pipeline routed page images to Haiku and reasoning to Sonnet instead of Opus, cutting Claude API costs by 84%. Includes the model-routing math and a real JSON parsing bug.