Claude Coders: do THIS once weekly. Run '/doctor' to... clear context clutter. 2 mins saved me 24k tokens of unnecessary skills, CLAUDE.md context and unused MCPs that were clogging context every session. Makes Claude faster, more efficient and more capable.show more

GPT-5.5 in Codex is built for long-session agent work.... But context still doesn't follow you across projects, agents, or teammates. ByteRover does that + Save you tokens -> No rewriting context when you switch from Claude Code to Codex. Now connecting Codex, Claude Code, OpenClaw, Hermes, and 22+ more agents. Your context moves with you. → personal context for solo work → team context for shared decisions and bug historyshow more

I just open sourced the ultimate vibecoding (meta-context) framework... that has allowed me to reliably build beautiful apps No more: "claude WHAT DID YOU DO" "I NEVER SAID PUSH TO MAIN" "this isn't working" archē:show more

ANTHROPIC 🔥: A new Managed Projects feature has been... spotted in testing on Claude. > Claude takes on tasks and keeps the project organized. > A project is a home for one stream of work. Sessions share memory and instructions so context carries forward, and Claude runs more autonomously. Projects only create and manage cloud sessions. This feature may be built on top of Claude Managed Agents, where each project gets a dedicated cloud environment so Claude can execute periodic tasks and refine project context via "Dreams". It could also be a successor to Conway, which is set to be removed this Friday internally.show more

CANCEL your parties and weekend plans. You NEED to:... > Install the Karpathy CLAUDE.md file — 2 minutes > Watch how Claude Code actually works after — 10 minutes > Read the 33-page Claude Skills guide — 1 sitting > Build your first Skill — 15 minutes > Teach Claude your entire workflow — once. forever. > Never explain context again — ever Then make $10K/month. $20K/month. $30K/month. You had the whole week. Now it's the weekend. This is your last chance before Monday. All links are below.show more

THIS GUY TURNS NOTES, DOCUMENTS, AND IDEAS INTO AN... AI SECOND BRAIN the system stores all the context of your work and helps claude not forget anything how to build one yourself: install obsidian connect claude code keep your projects, notes, and sessions in one vault link similar ideas together use the graph to discover new connections as a result, claude gets memory of your projects and understands the context without you constantly having to explain everything the more you work, the smarter the system gets don’t collect notes build connections between them insteadshow more

We built Attio to be the context layer at... the center of your GTM stack, and now that context becomes available everywhere you work. Today we're launching native connections for Attio in Claude R Perrin, @ChatGPT, and Notion. Research prospects, update records, surface deal insights, and connect with other AI tools, all from wherever you're already working. Learn more:show more

that’s it. you only have to read this one... article to: > learn claude skill foundations > learn claude skill architecture > learn claude skill testing > learn claude skill production which will let you create claude skills that: 1: automate your workflow’s 2: make you more productive 3: outperform your competitors welcome to the land of automation my claude cowork and claude code friends!show more

Your Claude Code setup is probably bloated and you... don't even know it. Every MCP server you add loads its full tool list into your context window the second your session starts. Stack too many and you're burning context before you type a word. So the move was never "add more." It's "add the right ones." Anthropic dropped an official plugin that does exactly that. It scans your actual codebase and tells you what's worth adding across all five layers: → hooks → skills → MCP servers → subagents → slash commands React project? It suggests Playwright. Auth code? It flags a security reviewer. It's read-only. Touches nothing. Just hands you the blueprint. The plugin isn't the edge. Knowing it exists is. /plugin install claude-code-setup@claude-plugins-official Steal this before everyone does.show more

Every serious Claude Code user is using this repo.... if you're not, you're leaving 90% of Claude Code's power on the table. It's called claude-code-best-practice - 84 sourced tips, implementation examples for every major feature, workflow comparisons across 8 major repos, and the actual tips from Boris Cherny (creator of Claude Code) compiled in one place. Here's what's actually in it: → 84 tips organized by category -- prompting, planning, CLAUDE.md, agents, commands, skills, hooks, workflows, debugging, utilities, daily habits → best practice + implemented examples for every core concept: subagents, commands, skills, hooks, MCP servers, plugins, settings, memory, checkpointing, CLI flags → workflow comparison table -- Superpowers, BMAD-METHOD, Get Shit Done, OpenSpec, gstack, HumanLayer -- what makes each unique, how many agents/commands/skills each has → orchestration workflow -- Command → Agent → Skill pattern with a live demo → Boris Cherny tips compiled across 3 tweet threads (13 + 10 + 12 tips) and 5 podcast/video appearances → "billion dollar questions" section -- open questions about CLAUDE.md, agents vs commands vs skills, specs -- that nobody has definitively answered yet here's a few of the tips that actually change how you use it: → use subagents with "say use subagents" to throw more compute at a problem -- offload tasks to keep your main context clean → spin up a second Claude to review your plan as a staff engineer before executing → CLAUDE.md should target under 200 lines -- wrap domain-specific rules in ` ` tags so Claude doesn't ignore them as files grow → compress KV context at max 50%, not at the end -- avoid the "agent dumb zone" by doing manual /compact proactively → after a mediocre fix: "knowing everything you know now, scrap this and implement the elegant solution" was #1 trending on GitHub in March 2026. 19.7K GitHub stars. 1.7K forks. MIT license. 100% open source. (link in the comments)show more

for everyone who already thinks this video is amazing,... i need to add context that makes it even more incredible. this month we celebrate our independence day and we were not expecting liam gallagher to chant the name of our country back… 🇲🇽 loves oasis and they love us back !!!show more

After a few more hours, I think I've figured... out Opus 5. Opus 5 is trained to be more agentic than anything I've used. All Claude 5 models are like that. So what changes? The way to interact with Opus 5 or contextualize it won't work the same way as with other models. It loves exploring, so it doesn't need much guidance for it. Unique preferences, artifacts, and references compliment it well and enable cleaner and more effective exploration and execution. Now that it can explore more effectively on its own and understand intent better, the best thing to do is to get out of its way (e.g., it doesn't need examples of your preferences; a clear high-level description of it works best). It's truly agentic in that sense. A good first step to provide better context for Opus 5 is to distinguish between what's situational and what needs persistence. Regardless, persistent system prompts and CLAUDE.MD needs to stay lightweight. Remove memories and tool descriptions from these. CLAUDE.MD is also a great place to tap into progressive disclosure by linking command/skills to it. On the situational side, agent skills and auto-memory can leverage progressive disclosure and the improved ability of the model to use its external context/knowledge. Conflicting and unnecessary instructions, which are common at this layer (mainly to ensure reliability), are going to throw off this model easily. That's the biggest change I had to make. Simple, clean, and clear prompts and skills work best. I had to clean a lot of my skills and system prompts. The way I prompt remains the same (usually clear and well-scoped). MCP tool descriptions are also more descriptive and have been deduped from the system prompt. Anthropic released a guide on the new rules for context engineering, which was helpful here. I started to test the recommendations and created a little artifact with the things that worked along the way. This might feel like a lot of work. Believe me, it has been frustrating. But I think we can expect future frontier models to become more agentic and smarter at figuring out the right context/gaps. The best thing to do is to prepare for that now. Boris Cherny mentioned that Opus 5 is their least prompt-injectable model yet. I am not sure if that was something they intentionally trained for or if it emerged based on how it was trained, which is to be extremely agentic in nature and more direct in execution.show more

Claude Code Desktop now opens a new window for... each session This makes it much easier to visualize multiple Claude Code agents running in parallel My current stack depends on the task: - Ghostty: when starting a project. Bash commands, git, env variables, provider connections. All manual through the terminal with a Claude panel running alongside. - Claude Code Desktop: once everything is configured. GitHub connected, CLAUDE.md, Skills, subagents and Hooks ready. Claude Code runs on its own, no more terminal setup, just panels running and outputs to review. - VSCode: when I need to review code by hand. I use it less and less, but there are moments where I have to confirm Claude got it right. I usually open the Claude extension inside VSCode, but it lacks most of the CLI features so it's limited Solid update. Worth trying once your workflows are already set up 👇show more

if you use claude code, this will save you... real money. the problem: every time you make an edit, your ai rereads the whole codebase to figure out what changed. tens of thousands of tokens, every turn, for context it already had. this repo fixes it. it’s called code review graph, and it just maps your entire codebase: every file, every function, every connection laid out so you can see the actual shape of your project how to set up (2 min): 1. pip install code-review-graph 2. code-review-graph install - auto-configures Claude Code, Cursor, Codex, Gemini CLI + more 3. code-review-graph build change one function, and it traces exactly what that touches... every caller, every dependent file, every test. your ai only reads what's affected, not the whole repo. and the savings are wild. a task that used to burn ~100,000 tokens (about a dollar) now runs closer to a penny.show more

Microsoft teases a faster and configurable context menu (right-click... menu) for Windows 11 after years of complaints! Marcus Ash, who leads Design and Research for Windows and Devices, says Microsoft is working on making context menus faster, simpler by default, and configurable to what you use most. That last part is huge. Windows 11’s context menu was supposed to fix the cluttered Windows 10 right-click menu. Instead, it became slower, padded, inconsistent, and still messy. You often need “Show more options” just to reach the old menu, which defeats the whole point of redesigning it. Now Microsoft is taking the same approach it used with Start and taskbar: give users control. Resizable Start. Movable taskbar. Smaller taskbar. Customizable Start sections. And now, configurable context menus. This is the Windows 11 reset users wanted 🥳show more

Anthropic is giving away free Claude certifications - and... I don't know why more people aren't taking advantage. If I knew nothing about AI and wanted to become AI-native in 30 days, this is what I'd do: < sign up for free Anthropic courses < use Claude to study pre-exam < once certified, extract the course content to a Claude project < prompt Claude: "Based on this course, build me a 201 version and some real hands-on exams to test my knowledge." < Complete 201 < Rinse and repeat There isn't a faster way to learn AI right now (+ this is 100% free).show more

The teases, drips of info, and context around this... Chapter has been PERFECT for an original. We were able to accurately figure out what it is without any sort of leaks, spread hype across MONTHS, and get rewarded with the community being right in our guesses!!! MORE OF THAT!show more

New feature in Claude Code 2.1.14 just dropped! You... can now search and install plugins from the marketplaces installed in your current Claude Code session. This is huge if you’re building plugins on top of Claude Code’s marketplace layer (Skills, Agents, Hooks, etc). How it works: - Run /plugin - The official Claude marketplace is installed by default - Use the search bar to find the plugin you want - Select one or multiple plugins with space, then press i to install - Go to the Installed tab to browse and enable them With the exponential growth of Skills and Agent-based components running in the CLI, improving plugin discoverability is a big win. Pretty sure more marketplace-related features are comingshow more

AI coding agents re-explore the same codebase every single... session. Repowise indexes a repo once and gives Claude Code, Codex, or any MCP agent a real dependency graph, git history, and a bug-predictive code health score. No re-grepping the same files. No stale docs. No guessing which file is about to break. The loop is simple: measure every file > locate where the risk concentrates > generate the exact refactoring plan to fix it Indexing a repo takes under 30 seconds and updates automatically on every commit. Paired benchmarks show up to 96% fewer tokens spent loading context and 70% fewer agent tool calls, at the same answer quality.show more

SpaceXai just made grok 4.5 FREE in your coding... agent starting today it's xAI's new coding model. 500k context. built for long agent sessions. no card. what you get for $0: -83.3% on terminal-bench 2.1 -64.7% on swe-bench pro - 4.2x more efficient than Opus 4.8 -500k context for big repos -$2/M in, $6/M out once it goes paid what this replaces: -Claude Opus 4.8: $15/M in, $75/M out -SuperGrok: $30-50/mo all for $0 how to set it up (2 min): >curl -fsSL | bash > grok → localhost:8000/v1 > point hermes / aider / opencode / cline to it > model: grok-4.5 Or API key at - base url Works in Hermes, Aider, OpenCode, Cline, Claude Code, and any OpenAI-compatible tool. Important: Free for a limited time. EU waits till mid-July. Rate limits apply. bookmark this before the free window closesshow more

50% more context unlocked for Qwen 3.8 27b Q4_K_XL... dflash 2 on a single RTX 4090 (24 GB VRAM) I found a hidden VRAM tax in llama.cpp. By combining my custom 2 bit DFlash 2 drafter with one overlooked server flag, I just unlocked another +80,000 tokens of context. Qwen3.8-27B is now running a massive 250,000 context at 75 tokens/s on a single RTX 4090. Here is the secret: By default, `llama-server` reserves massive chunks of your VRAM to handle multiple concurrent users (batching). If you are running a single user session, you are bleeding memory for features you aren't using. By passing the `--parallel 1` flag, you force the engine to dedicate 100% of your 24GB VRAM buffer to a single user. When we combine the VRAM saved by our Q2_K 2-bit drafter with the VRAM saved by `--parallel 1`, the context ceilings absolutely explode: Note: all benchmarks carried out with a massive 28k prompt. Ubuntu 22. ### THE NEW 24GB PHYSICAL LIMITS (Single RTX 4090): # 1. The "Repo Swallower" (Q4 KV Cache): - Context: 250,000 tokens (Up from 170k!) - Speed: 73.66 t/s decode | 1,608 t/s prefill - Peak VRAM: 23.8 GB # 2. The "High-Precision SWE" (Q8 KV Cache): - Context: 150,000 tokens (Up from 100k!) - Speed: 75.01 t/s decode | 1,667 t/s prefill - Peak VRAM: 23.9 GB # 3. The "Pristine Attention" (Unquantized FP16 KV): - Context: 90,000 tokens - Speed: 80.58 t/s decode | 1,699 t/s prefill - Peak VRAM: 23.92 GB ### HOW TO RUN THE 250K GOD STACK TODAY: (Requires PR #27342 + my Q2_K Hugging Face drafter) llama.cpp flags: ./build/bin/llama-server -m Qwen3.8-27B-UD-Q4_K_XL.gguf -md Qwen3.8-27B-DFlash2-Q2_K.gguf --spec-type draft-dflash --spec-draft-n-max 3 -c 250000 -ngl 99 --parallel 1 --port 8080 -ctv q4_0 -ctk q4_0 We are pushing a quarter million tokens of context with speculative DFlash 2 decoding at 73 tokens/second on a single consumer gaming GPU. I dropped my custom 2 bit Hugging Face GGUF links, visual performance graphs, and the PR #27342 build instructions in the replies below. If you own a single RTX 3090 or 4090, it is officially time to cancel your API subscriptions and let local silicon eat the cloud. how much monthly API spend does an optimized 4090 rig like this actually replace for you?show more