Latest

MCP stdio vs Streamable HTTP: which transport to use
Choose stdio for a client-owned local process and Streamable HTTP for a separately managed network service.

Gemini CLI 0.64.0: atomic file edits and @file:line references
Gemini CLI 0.64.0 (Oct 13, 20:48 UTC on npm) makes file edits atomic, recovers corrupt state and resolves @file:line.

Google Jules vs Antigravity: cloud tasks or local agents?
Compare Google Jules and Antigravity by execution environment, review flow, permissions and best-fit tasks.

Claude Code compact: context checks and continuation
Use /context and focused /compact prompts, then verify the saved work and source details before continuing.

GitHub Copilot custom agents: .agent.md files and tools
Set up GitHub Copilot custom agents with .agent.md files, scoped tools, precedence and CLI invocation.

Best MCP servers for Cursor, with mcp.json setup
Best MCP servers for Cursor: GitHub, Playwright, Context7, Supabase and more, with each vendor's mcp.json config.

Cursor student discount: current options and renewal rules
Cursor's old student discount is closed. See free access, academic credits and existing-plan renewal rules.

effortless: a Claude Code Mod that sets effort per prompt
effortless, a Claude Code Mod by HeyCubit, has Haiku 5.5 pick the effort for each prompt and tracks the cache.

Claude Code sandbox: files, network and strict mode
Claude Code sandbox limits for files and networks, strict mode, retries and the tools outside its boundary.

CLAUDE.md vs AGENTS.md: which file each coding agent reads
Claude Code now reads AGENTS.md when no CLAUDE.md exists. Here is what Codex, Copilot, Cursor and Gemini CLI read.

Codex CLI vs Codex app vs IDE extension: which surface to use
What the Codex CLI, the Codex app in the ChatGPT desktop app and the IDE extension each do, and when to pick each.

Claude Code 2.1.296: subagent and hook fixes
Claude Code 2.1.296 adds subagent compaction controls, managed hook fixes and an explicit large-file read option.

Where Claude Code stores sessions, settings and memory
Claude Code keeps sessions in ~/.claude/projects/ for 30 days, settings in settings.json files and memory per repo.

GitHub Copilot CLI: install, sign in and tool approvals
GitHub Copilot CLI setup from GitHub's docs: install, sign in, plan mode, -p prompts and safe tool approvals.

Gemini CLI in VS Code: Companion Setup and Diff Review
Connect Gemini CLI to VS Code, inspect editor context and review changes through the Companion extension.

GitHub Copilot AI credits: plans, reset and legacy requests
GitHub Copilot AI credits by plan: what uses them, when they reset, and why premium requests are now mostly legacy.

Claude Desktop vs Claude Code: which workspace fits the job?
Claude Desktop and Claude Code share a model family but organise work differently. Here is the practical split.

Example CLAUDE.md files for Bun, Python and React
Adapt real CLAUDE.md files from Anthropic's Bun, Python and React projects, with sourced commands and pitfalls.

Serve Claude Code as MCP: Setup and Limits
Run Claude Code as a local stdio MCP server, configure the client and keep approvals at the client boundary.

Cursor rules: .mdc files, AGENTS.md and scope
Choose between .cursor/rules, AGENTS.md and user rules, and check when Cursor actually includes your instructions.

Codex: dangerously skip permissions and safer modes
The exact Codex bypass flag, what it removes, and how to run unattended jobs while keeping a sandbox.

Global CLAUDE.md: personal instructions across projects
Global CLAUDE.md: file location, personal preferences, project scope and checks for loaded instructions.

harness-scope: Claude Code skills per repo, picked by named profiles
shimo4228's harness-scope Mod lets each repo pick which global skills, agents and rules Claude Code sees.

Claude Code 2.1.289: deny-rule fixes and agent.spawn for mods
Claude Code 2.1.289 (Oct 3, 20:12 UTC) closes gaps in Bash and Read deny rules and repairs plugins and mods.

