Collision-free parallel sessions with claude --worktree, EnterWorktree, copying .env via .worktreeinclude, isolation: worktree subagents and /batch, worktree.baseRef, sparsePaths and symlinkDirectories, worktrees from PRs, cleanup rules, WorktreeCreate hooks and common errors. (Turkish)
DeepSeek's new 552B open-weight model: deepseek-flash pricing and off-peak hours, thinking mode with low/high/max effort, tool calling with reasoning_content, DeepSeek's benchmark claims, the official Claude Code setup and a cost comparison with Claude Haiku/Sonnet/Opus 5.5. (Turkish)
Released October 7, 2026: benchmarks vs Haiku 4.5 and Sonnet 5.5, $0.10/$0.50 pricing with the 100K-token tier, tokenizer cost impact, effort and adaptive thinking, the Haiku 4.5 migration checklist and running Haiku 5.5 as a subagent in Claude Code 2.1.293. (Turkish)
Mistral's new 1T-parameter open-weight model: specs and 1M context, pricing and launch discount, thinking mode via reasoning_effort, API and function calling examples, Mistral's benchmark claims and a cost and use-case comparison with Claude Opus 5.5 / Sonnet 5.5. (Turkish)
Google's open-source terminal agent: install and release channels, auth options and free quotas, model selection, GEMINI.md and a shared AGENTS.md, approval modes and Plan Mode, TOML custom commands, policy engine, MCP, hooks, sandbox, headless mode and a Claude Code comparison table. (Turkish)
The /statusline command, statusLine settings (padding, refreshInterval), the JSON fields on stdin, context/cost/rate-limit gauges, colored multi-line scripts, OSC 8 links, caching, subagentStatusLine, Windows setup and troubleshooting. (Turkish)
Anthropic's official VS Code extension: install and sign-in, per-change diff approval, permission modes and the extension's own startup order, /plan, prompt box tools, session history and groups, plugin/MCP dialogs, settings table, the built-in ide MCP server and JetBrains differences. (Turkish)
Released September 28, 2026: benchmarks vs Sonnet 5 and Opus 5.5, $2/$10 pricing, 1M context, recalibrated effort levels, between_tools and the five breaking changes, safety fallback and usage in Claude Code 2.1.284. (Turkish)
The Code tab, Local/Cloud/SSH/WSL environments, permission modes, diff view, Browser pane and launch.json, worktree isolation, local scheduled tasks, computer use and a CLI comparison. (Turkish)
Lower pricing than Opus 5, 1M context, medium default effort, always-on thinking, the four breaking API changes, preserved thinking, fast mode and usage in Claude Code 2.1.280. (Turkish)
The claude remote-control server mode, --remote-control flag, /rc command, QR pairing, push notifications, Trusted Devices and troubleshooting: drive a local session from your phone. (Turkish)
The --chrome flag, /chrome command, Claude in Chrome extension, console debugging, form filling, file uploads, GIF recording, the permission model and troubleshooting. (Turkish)
Telegram, Discord and iMessage plugins, the --channels flag, pairing and allowlists, permission relay and building your own webhook channel to push events into a running session. (Turkish)
The claude agents dashboard, --bg background sessions, keyboard shortcuts, peek & reply, worktree isolation and JSON-based automation for managing multiple sessions. (Turkish)
Tracking token cost with /usage, /cost, /context and the new /skill-doctor command; cutting cost via prompt cache, MCP, CLAUDE.md and agent teams. (Turkish)
allow/ask/deny rules, Bash/Read/Edit/WebFetch/MCP rule syntax, permission modes, wildcard pitfalls, extending with hooks and managed settings. (Turkish)
Running the Bash tool with filesystem and network isolation: /sandbox setup, auto-allow mode, allowWrite/denyRead, credential protection and limitations. (Turkish)
The classifier-based permission mode: decision order, what's blocked/allowed by default, autoMode.environment, allow/soft_deny/hard_deny rules and limitations. (Turkish)
Creating plugins, testing with --plugin-dir, plugin.json and directory structure, adding marketplaces, the official/community marketplaces and extraKnownMarketplaces. (Turkish)
Automatic checkpoints, the /rewind menu, restoring code/conversation, summarizing, limitations, and how it compares to /branch. (Turkish)
--cloud, --teleport, cloud environments, auto-fix pull requests and Routines: the complete guide to running Claude Code in the cloud. (Turkish)
SendMessage and ListAgents for messaging between sessions: /list-agents, delivery rules, crossSessionInbound, isolatePeerMachines and cross-machine messaging. (Turkish)
The /code-review command, effort levels, --fix/--comment flags, cloud-based ultrareview and automated PR review on GitHub. (Turkish)
The agent(), pipeline(), parallel() script API, the ultracode keyword, the /workflows command, the approval flow, limits and saving runs for multi-agent orchestration. (Turkish)
Which accounts default to it, the /model and /effort commands, the thinking behavior change, fast mode and what's new in v2.1.219. (Turkish)
OpenAI's new model family: how the three models differ, the 1.05M-token context window, API pricing, reasoning effort/mode settings and which one to pick. (Turkish)
/install-github-app setup, workflow YAML, claude_args, triggers, Bedrock/Vertex support and automated PR review for Claude Code + GitHub Actions. (Turkish)
Built-in agents (Explore, Plan), frontmatter fields, model selection, tool restrictions, hooks, and chaining workflows for subagents in Claude Code. (Turkish)
Adding servers (claude mcp add), scopes, .mcp.json, OAuth authentication, resources and security for the Model Context Protocol in Claude Code. (Turkish)
PreToolUse, PostToolUse, SessionStart and Notification events, JSON schema, exit codes and real examples for event-driven automation in Claude Code. (Turkish)
SKILL.md structure, frontmatter fields, arguments, dynamic context injection and running skills in a subagent — a guide to writing custom skills in Claude Code. (Turkish)
CLAUDE.md file locations, load order, @import syntax, .claude/rules/, and Auto Memory — a guide to persistent project memory in Claude Code. (Turkish)
Print mode, output formats, permission modes and --allowedTools — using Claude Code from scripts and CI. (Turkish)
Komut İstemcisinde Claude Code Kullanmak İçin Yapılması Gerekenler — installing, logging in and first steps with Claude Code in the terminal. (Turkish)
Aykırı Değerler: Tanımı, Tespiti ve Yönetim Stratejileri — detecting and managing outliers with IQR, Z-score, Mahalanobis and LOF. (Turkish)
Veri Biliminde Eksik Veriler ile Nasıl Başa Çıkarız? — from dropping rows to model-based imputation, with Python examples. (Turkish)
Dengesiz Veri Setleri ile Nasıl Başa Çıkılır? — SMOTE, resampling and the right metrics, through a credit card fraud case study. (Turkish)