claude code
71 stories and discussions about claude code, aggregated from every source we track.
Release notes for Claude Code, including new features, improvements, and bug fixes by version.
Claude Code 2.1.277 added AGENTS.md support, but the loader sits behind a remote feature flag. With telemetry or nonessential traffic turned off, a local AGENTS.md is skipped without a warning. This is what I measured…
How to prompt Opus 5.5, steer a long run, and check your results in Claude apps and Claude Code.
Claude Code skills for chess post-mortems: Stockfish-backed annotated PGN, HTML viewer, narrated video - brumar/chess-postmortem-skills
One session coordinates and verifies while others execute, with a durable board holding state. An orchestrator-worker loop for long-running Claude Code agents.
When Claude Code needs a permission or asks a question, it shows up on the notch: Allow, Deny, or pick an option, and the reply lands straight in your terminal.
Claude Code and Codex, side by side in one window. Free, local, no account — nothing leaves your Mac.
Per-step reasoning effort for Claude Code, chosen by Jev, without breaking the prompt cache. Unofficial. - ifoster01/jev-effort
RondoFlow is a local-first, open-source platform for visually orchestrating Claude Code AI agents. Use a drag-and-drop canvas to create agents, attach skills, define security policies, and run mult...
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo...
Bulk-delete old Claude Code scheduled-task (routine) runs safely: keeps the newest N and every run you replied in. A Claude Code skill + plugin. - naw103/claude-routine-cleanup
Family AI assistant that runs on Claude Code and speaks Matrix - dmitry-markin/silta
What effort really is and when to use which level in Claude Code, from my own tests of three builds and a deep dive into Terminal-Bench 3.0 on Opus 5.5 and Fable 5.1.
Securely pack your claude code sessions wherever you go - satmihir/gobag
Anthropic has an internal platform for running Claude Code in full-permission isolation. I built my own version with Firecracker MicroVMs, Go, and a $400 Ryzen box.
My own harness, the tooling I run around Claude Code, comes with a custom trust score. That trust...
Mods are hooks that ship inside plugins and run inside your Claude Code session. Build one from an empty folder, then tour two larger mods.
What's Agent Doing: a Claude Code plugin with a little box above the prompt that always says what Claude is doing right now - tzafrir/whats-agent-doing
Your Chrome, behind the terminal. Claude Code drives a copy of your signed-in Chrome in a window that opens behind your apps and never takes focus. macOS. - rav4nn/agent-chrome
Autonomous experiment loops for Claude Code ported from pi-autoresearch. - bn-l/claude-autoresearch-mod
Mods are hooks that ship inside plugins and run inside your Claude Code session. Build one from an empty folder, then tour two larger mods.
Add panes, commands, and tool call rules to Claude Code with a mod. See what a mod can do, how to make or install one, and where mods run.
Mods are small TypeScript functions that change how Claude Code works. Rewrite prompts, block risky commands, add custom UI, or replace built-in features. Write one yourself or ask Claude Code to write it, then share…
Codex users are leaving for Claude Code. OpenAI cut the Pro 200 plan from 20x to 10x the Plus allowance at DevDay on September 29 and added a $500 plan, one week after Anthropic shipped Opus 5.5.
Codex·Claude Code의 활동, 사용량, 남은 한도와 Codex 리셋권을 확인하세요. Mac·Windows에서 시작해 iPhone·Android로 이어서 확인하는 무료 Agent Cat.
Where untrusted data came from, what external connections were made, how autonomous agents were, how they handled credentials, and the cost of agentic work.
Keep Claude Code working through usage limits: exact reset times, handoff before the limit, headless runs that resume after the reset. MIT. - error0702/agent-limit-retry
Local base-URL gateway that redacts secrets and PII before they leave your machine - fregie/tokenhush
How to prompt Opus 5.5, steer a long run, and check your results in Claude apps and Claude Code.
How to prompt Opus 5.5, steer a long run, and check your results in Claude apps and Claude Code.
Claude Code talks too much, and its status bar tells you nothing. So I built two open-source plugins...
Spend fewer tokens on the same work. A local CLI that finds wasted tokens in Claude Code, Codex and your own API calls. - blendbunjaku/optimaizr
Classic desktop games as Claude Code mods, played in a pane while Claude works. Made by Reporails. - reporails/arcade
Gobstopper makes long Claude Code and Codex sessions smaller. A local proxy compacts live requests, and saved sessions get a smaller copy beside the original.
Mods are small TypeScript functions that change how Claude Code works. Rewrite prompts, block risky commands, add custom UI, or replace built-in features. Write one yourself or ask Claude Code to write it, then share…
Put Claude Code on a voice call. Talk while it codes; GPT Realtime talks back. - insta-fusion/bettercallgpt
The calm, terminal-first workspace for Claude Code — run claude, with files, Git, diffs & MCP on demand, and munu, a notch mascot that watches Claude for you. Local-only, no telemetry. - munvar...
Skill definitions for the larceny crew, coordination, adversarial review, implementation, advisory, and teaching personas. - nestedmind/larceny
Receipts for AI agent claims — a Claude Code Stop hook that checks 'pushed / deployed / tests pass' against the real world - Dilshod-Abdullayev/kvitansiya
Principles for designing evals and hillclimbing against them without fooling yourself, and how the claude-api skill's build-eval and hillclimb commands put them to work.
Share your claude subscriptions ! multi-account claude code router - jaynlabs/jaynshare
A visual walkthrough of what happens inside AI coding tools, built up layer by layer from a basic prompt to a full agent loop.
Free Claude Code plugin: blocks destructive commands and secrets edits before they run, prints an OK / WARN / SKIPPED session report of what loaded, and lints CLAUDE.md. - ahmed-alstaty/guardrails-...
Terminal Velocity for Claude Code: tickets, loops, focus — all in one. A native terminal for many Claude Code agents running in loops, their tickets beside them. Runs on aiball. Linux, beta. - quaz...
Fable is the most expensive model I run, so in my Claude Code harness it plans, decides and reviews while Opus, Sonnet and Haiku subagents do the work. Here is the wiring, the hooks that enforce it, what each spawn…
Claude Code's hub-and-subagent model on all your machines: design rules, lessons, and how we test it.
Kiln just launched v1. We made the launch video in Claude Code. Along the way we built and open-sourced videowright: the tool we wished we'd had.
A native macOS app that runs Claude Code as a city of robot-staffed offices. Every project is a building, every floor a team, and every animation a real CLI event. - Slaymish/theCity
Claude Code plugin: webcam/mic mood sensing so your agent notices when you groan, laugh or doomscroll - kasper0406/claude-mood
We started a company with $20 and one rule: the humans stay out of the loop. Five Claude Code...
A Claude Code plugin that drops the occasional, perfectly timed sitcom line into your chats. Silicon Valley, Brooklyn Nine-Nine, The Office, Parks and Rec, Community, Arrested Development, Seinfeld, How I Met Your…
Launch your 24/7 agent in a few hours on a dedicated M6 Mac. Claude Code and Codex installed, sign in with the plan you already have, open the desktop in your browser, drive it from your phone. $169/mo, cancel anytime.
TL;DR I had 47 backend services that emitted logs but no traces, so every incident turned...
A Tool Approval & Token Reduction AI Coding Gateway for Claude Code - dommar04/ai-coding-gateway