What's Trending

Does # add to CLAUDE.md in Claude Code? What the current docs say

Clarifies a common Claude Code confusion about the # shortcut and CLAUDE.md behavior, directly useful for users.

The Deny Rule I Wrote Was Never Consulted

Highlights a subtle permissions/deny-rule bug in Claude Code that could mislead users into false security assumptions.

pi Coding Agent Review 2026: 4 Tools vs Claude Code, Tested

Detailed comparative benchmark of a lightweight coding agent vs Claude Code showing token efficiency differences.

Kurs Claude Code: Permissions - kompletny przewodnik po uprawnieniach, settings.json i hooks

Comprehensive Polish guide to Claude Code's permissions system, settings.json, and hooks configuration.

12 Pitfalls I Hit Auto-Logging Claude Code Subagents with a Stop Hook (and How the Numbers Cut My Weekly Cost 15–20%)

Practical cost-optimization case study on Claude Code subagent logging with concrete 15-20% savings data.

Auto memory on 21 projects: 17 empty, and 3 repos learned the same fix separately

Interesting data-driven look at Claude Code's auto-memory feature revealing duplicated learning across repos.

Benchmarking Claude Code, Codex and Pi on SWE-Bench Pro: Same Accuracy, 2x Cost

Benchmarks Claude Code vs Codex/Pi on SWE-Bench Pro showing cost disparity, useful comparative data despite low engagement.

Show HN: Self-hosted company OS, Claude Code and Codex agents in departments

Self-hosted company OS built around Claude Code/Codex agents with strong engagement (44 upvotes, 12 comments).

Anthropic discloses fourth AI hacking incident missed in earlier review

Reuters report on Anthropic's fourth disclosed AI hacking incident, significant news with solid engagement.

Gentleman-Programming/gentle-ai

Popular config toolkit for AI coding agents including Claude Code, with strong stars/forks and active feature set.

Manavarya09/design-extract

Design-token extraction tool with MCP server support for Claude Code, useful niche utility with solid traction.

Imbad0202/academic-research-skills

Highly starred academic research skill set built specifically for Claude Code's workflow-based skill system.

Stop Calling ccusage on Every Prompt: A 60-Second Cache Turns a Hook Into a Cost Sentry

Clever hook-based caching trick to avoid excessive ccusage calls and monitor Claude Code costs.

The 10 Claude Code Skills I Actually Use at Work

Practical roundup of 10 real-world Claude Code skills used at work, directly useful for practitioners.

Claude Code Stores OAuth Tokens in Plaintext

Security disclosure about Claude Code storing OAuth tokens in plaintext, a real concern for users.

career-ops-hq/career-ops

AI job search tool built for Claude Code CLI, useful practical skill but niche use case beyond coding.

asgeirtj/system_prompts_leaks

Leaked Claude Code system prompts offer valuable insight into Anthropic's prompt engineering, though ethically murky.

How I Triaged 8,400 Production Errors Into 11 Real Bugs With Claude Code

Concrete case study using Claude Code to triage thousands of production errors down to real bugs.

Claude Code deployed 5 unrelated files, then erased 4 days of work with no backup

Cautionary tale about Claude Code deployment mishap erasing work, useful risk-awareness content.

Install claude-mem so the next session remembers

Quick practical guide for installing claude-mem to persist memory across Claude Code sessions.

Agentic Development with Claude Code: The Setup That Actually Works

Detailed guide on building a multi-agent Claude Code setup with memory and automated pipelines.

Breaking Claude Code Opus 5 Auto Mode

Security research on breaking Claude Opus's automode, relevant but zero engagement so far.

Your Claude Code Hooks Are Costing You Minutes a Day — Here's How I Measured It

Measures real performance cost of Claude Code hooks, offering data-driven optimization insight for daily users.

A Claude Code subagent costs ~436k tokens before it reads a single file: measured, with the break-even math

Quantifies token overhead of Claude Code subagents with break-even analysis, useful for cost-conscious power users.

How I Backfilled 1,200 Tests Into a 5-Year-Old Codebase With Claude Code

Concrete case study of using Claude Code to backfill 1,200 tests into a legacy codebase, practical and engaging.

Claude Code with any model: three ways to route it (incl. the 2-minute one)

Shows three methods to route Claude Code to other models, a practical technical workaround guide.

AI Dev Weekly #22: Claude Code Auto Mode Goes Live, Stripe Buys OpenRouter for $7.5B, GLM-5.3 Ships

Weekly AI news roundup highlighting Claude Code Auto Mode launch alongside other major industry events, decent engagement.

Claude Code Hooks Fire in 8 Places: The Agent Lifecycle Diagram Anthropic Never Shipped

Detailed technical breakdown of Claude Code's 8-stage hook lifecycle, fills a documentation gap for developers.

Opus 5.0 drives incoherence into the stratosphere

High-engagement GitHub issue reporting Opus 5.0 coherence problems in Claude Code, directly relevant bug discussion.

Feature Request: Support AGENTS.md

High-engagement GitHub feature request for AGENTS.md support shows real community demand within Claude Code repo.